Search

In the past ten years, chatbot development has matured to become one of the most well-distinguished outcomes of artificial intelligence. Despite some criticism, Bing AI, ChatGPT and other natural language processing (NLP) products of similar nature are becoming more popular. The creation of chatbots can close several gaps in geographic information retrieval as well. This research introduces and successfully implements, for the first time, a model for integrating task-oriented chatbots into geoportals, with the goal of easing user requests, improving access to geospatial services, and fostering human-computer interactions (HCI). Additionally, it presents a novel recommendation solution for matching the most appropriate volunteer to the user’s geospatial needs based on expertise similarity, semantic similarity, and community feedback. The three categories of finding map services, discovering geoprocessing services, and volunteer expert recommendations were shown to be the most significant geoportal bot intents. Depending on the requirement, each intent additionally includes various entities such as time, place, description, skill, etc. The notion of deep transfer learning (DTL) was then put into practice by customizing a pre-trained BERT (Bidirectional Encoder Representations from Transformers) model for our particular aim and creating a task-oriented conversational agent. According to the results, effective intent classification and entity recognition in the geospatial domain could arise from this approach. We performed the training process with 200 sample data, 20% of which were utilized in a stratified manner for testing, and we obtained f1-scores of at least 0.75. Finally, a pilot Geoportal Chabot that combines crowdsourcing and conversational agents’ approaches was put into use and tested with success. In keeping with SDI technical purposes, the system might direct users to common geospatial web services, namely WMS and WPS, in addition to including natural language understanding (NLU) and natural language generation (NLG) capabilities. Result of user-centered evaluation indicated that the integration of a chatbot significantly reduces the average time required to access geospatial data and processing services by more than 50%. Notably, this effect is even more pronounced when locating an expert, with a fivefold decrease in the time required. Finally, overall user satisfaction rose from 86% to 94%.

IntroductionRadiologists frequently lack direct patient contact due to time constraints. Digital medical interview assistants aim to facilitate the collection of health information. In this paper, we propose leveraging conversational agents to realize a medical interview assistant to facilitate medical history taking, while at the same time offering patients the opportunity to ask questions on the examination.MethodsMIA, the digital medical interview assistant, was developed using a person-based design approach, involving patient opinions and expert knowledge during the design and development with a specific use case in collecting information before a mammography examination. MIA consists of two modules: the interview module and the question answering module (Q&A). To ensure interoperability with clinical information systems, we use HL7 FHIR to store and exchange the results collected by MIA during the patient interaction. The system was evaluated according to an existing evaluation framework that covers a broad range of aspects related to the technical quality of a conversational agent including usability, but also accessibility and security.ResultsThirty-six patients recruited from two Swiss hospitals (Lindenhof group and Inselspital, Bern) and two patient organizations conducted the usability test. MIA was favorably received by the participants, who particularly noted the clarity of communication. However, there is room for improvement in the perceived quality of the conversation, the information provided, and the protection of privacy. The Q&A module achieved a precision of 0.51, a recall of 0.87 and an F-Score of 0.64 based on 114 questions asked by the participants. Security and accessibility also require improvements.ConclusionThe applied person-based process described in this paper can provide best practices for future development of medical interview assistants. The application of a standardized evaluation framework helped in saving time and ensures comparability of results.

Background: Obesity is a global health issue affecting over 2 billion people. Mobile health apps, specifically nutrition apps, have been identified as promising solutions to combat obesity. However, research on adherence to nutrition apps is scarce, especially for publicly available apps without monetary incentives and personal onboarding. Understanding factors associated with adherence is essential to improve the efficacy of these apps. This study aims to identify such factors by analyzing a large dataset of a free and publicly available app (“MySwissFoodPyramid”) that promotes healthy eating through dietary self-monitoring and nutrition literacy delivered via a conversational agent. Methods: A retrospective analysis was conducted on 19,805 users who used the app for at least two days between November 2018 and May 2022. Adherence was defined as completing a food diary by tracking dietary intake over a suggested period of three days. Users who finished multiple diaries were considered long-term adherent. The associations between the day and time of installation, tutorial use, reminder use, and conversational agent choice were examined regarding adherence, long-term adherence, and the number of completed diaries. Results: Overall, 66.8% of included users were adherent, and 8.5% were long-term adherent. Users who started the intervention during the day (5 a.m.–7 p.m.) were more likely to be adherent and completed more diaries. Starting to use the intervention between Sunday and Wednesday was associated with better adherence and a higher number of completed diaries. Users who chose the female conversational agent were more likely to be adherent, long-term adherent, and completed more diaries. Users who skipped the tutorial were less adherent and completed fewer diaries. Users who set a follow-up reminder were more likely to be long-term adherent and completed more diaries. Conclusions: This study demonstrates the potential of digital health interventions to achieve comparably high adherence rates, even without monetary incentives or human-delivered support. It also reveals factors associated with adherence highlighting the importance of app tutorials, customizable reminders, tailored content, and the date and time of user onboarding for improving adherence to mHealth apps. Ultimately, these findings may help improve the effectiveness of digital health interventions in promoting healthy behaviors.

Artificial intelligence chatbots recently caused a stir in the world by promising to transform education systems in a multitude of ways. To analyze pertinent publications in the SSCI journals, a systematic review was conducted for this study, which investigates the trends of chatbots in education studies, with a focus on English speaking skills. Despite the increasing use of AI-powered chatbots in education, limited research has explored how to develop the merits of AI-powered chatbots in English-speaking teaching or learning. The empirical evidence of chatbot applications from 24 research studies conducted in an English-speaking learning environment and published between 2017 and 2023 was examined in this systematic review. The topic of study on chatbots in English language-speaking practice skills was determined to be in its early stages, which suggests that there is a lot of space for performing pertinent research to support creative English-speaking learning and work with chatbots to enhance learning results. The findings suggest that the AI chatbot learning approach for English-speaking proficiency was intended to speed up the English learning process and assist students in meeting the goals or results of the courses. Also, some benefits (e.g. alleviating speaking anxiety and improving speaking pronunciation) were highlighted in each area. Specifically, the study provides insights into the effectiveness of AI chatbots in enhancing students’ English-speaking learning outcomes, confidence, engagement and motivation. This study concludes with recommendations for in-service English teachers, chatbot designers and chatbot researchers in the future.

Recently, we have observed a noticeable evolution and growing use and incorporation of chatbots on websites, mobile and social networking apps. A chatbot is a computer program that exhibits a capacity to converse quite naturally with users in a way that resembles a human dialogue. Examples of chatbots can be found in several areas, including education, commerce, and tourism. The use of Artificial Intelligence (AI) and its sub-fields, such as Machine Learning, Deep Learning, and Natural Language Processing (NLP), is increasing across all business sectors. One of the most advanced applications of this technology is the chatbot, which is particularly beneficial due to the quick response times and its simplicity. Nevertheless, although studies on chatbots exist in tourism, academic research covering their adoption, technological evolution, and impact on this sector is still relatively sparse. Therefore, this study aims to provide a comprehensive overview of chatbots and their effect on tourism. First, we provide a new classification of chatbots based on specific criteria. Second, we explore the conceptual architecture of chatbots and their key components. Third, this study aims to assess and contrast the main existing tools for developing chatbots, classifying them and highlighting their key advantages and disadvantages. Fourth, this study aims to examine the integration of chatbots in the tourism sector by identifying their key applications in the industry over the past decade. Additionally, it seeks to analyze the impact of chatbots on the various functionalities outlined in the 6A framework for tourism. To achieve this, a thorough search will be conducted using five prominent databases - Scopus, ACM, IEEE Xplore, Springer Link, and Web of Science - covering the period from 2013 to 2023. For this study, 1155 academic publications were reviewed after applying a systematic review protocol including purpose, research questions, keywords, digital libraries, search strings, and inclusion and exclusion criteria. Only 31 were identified to be primary studies.

In large-scale enterprises, vast amounts of textual information are shared across corporate repositories and intranet websites. Traditional search techniques that lack context sensitivity, often fail to retrieve pertinent data efficiently. Modern techniques that use a distributed representation of words require a considerable training dataset and computation, thereby presenting financial and operational burdens. Generative models for information search suffer from problems of transparency and hallucination, which can be detrimental, especially for organizations and their stakeholders who rely on these results for critical business operations. This paper presents a non-goal oriented conversational agent based on a collection of finite state machines and an information search model for text search from an extensive collection of stored corporate documents and intranet websites. We used a distributed representation of words derived from the BERT model, which allows for contextual searching. We minimally fine-tuned a BERT model on a multi-label text classification task specific to a closed-domain knowledge base. Based on DCG metrics, our information retrieval model using distributed embeddings from the minimally trained BERT model and Word Movers Distance for calculating topic similarity is more relevant to user queries than BERT embeddings with cosine similarity and BM25. Our architecture promises to significantly expedite and improve the accuracy of information retrieval in closed-domain systems without the need for a massive training dataset or expensive computing while maintaining transparency.

Abstract Background Digital mental health interventions (DMHIs) may reduce treatment access issues for those experiencing depressive and/or anxiety symptoms. DMHIs that incorporate relational agents may offer unique ways to engage and respond to users and to potentially help reduce provider burden. This study tested Woebot for Mood & Anxiety (W-MA-02), a DMHI that employs Woebot, a relational agent that incorporates elements of several evidence-based psychotherapies, among those with baseline clinical levels of depressive or anxiety symptoms. Changes in self-reported depressive and anxiety symptoms over 8 weeks were measured, along with the association between each of these outcomes and demographic and clinical characteristics. Methods This exploratory, single-arm, 8-week study of 256 adults yielded non-mutually exclusive subsamples with either clinical levels of depressive or anxiety symptoms at baseline. Week 8 Patient Health Questionnaire-8 (PHQ-8) changes were measured in the depressive subsample (PHQ-8 ≥ 10). Week 8 Generalized Anxiety Disorder-7 (GAD-7) changes were measured in the anxiety subsample (GAD-7 ≥ 10). Demographic and clinical characteristics were examined in association with symptom changes via bivariate and multiple regression models adjusted for W-MA-02 utilization. Characteristics included age, sex at birth, race/ethnicity, marital status, education, sexual orientation, employment status, health insurance, baseline levels of depressive and anxiety symptoms, and concurrent psychotherapeutic or psychotropic medication treatments during the study. Results Both the depressive and anxiety subsamples were predominantly female, educated, non-Hispanic white, and averaged 38 and 37 years of age, respectively. The depressive subsample had significant reductions in depressive symptoms at Week 8 (mean change =—7.28, SD = 5.91, Cohen’s d = -1.23, p

The present narrative review seeks to unravel where we are now, and where we need to go to delineate the active ingredients in psychotherapy delivered by conversational agents (e.g., chatbots). While psychotherapy delivered by conversational agents has shown promising effectiveness for depression, anxiety, and psychological distress across several randomized controlled trials, little emphasis has been placed on the therapeutic processes in these interventions. The theoretical framework of this narrative review is grounded in prominent perspectives on the active ingredients in psychotherapy. Based on search terms derived from various theoretical perspectives, we conducted a systematic literature search of four scientific databases and identified 17 studies. Across the selected studies, three themes emerged: relationship variables, emotional venting, and cognitive factors. While methodological issues compromise the epistemic value of this evidence base, core questions also remain to be answered. Such questions include, but are not limited to, whether humans can form affectionate bonds to inanimate beings and whether these kind of mental health treatments should be understood as psychotherapy or something else. Researchers should therefore be cautious when applying theories of psychotherapy in the realm of conversational agents. We conclude the paper by introducing recommendations for future research, which we hope will help instigate methodologically sound studies in this field.

Brain activity is a biological signal with unique characteristics that can determine important patterns for recording and processing. The electroencephalogram (EEG) is the most used signal because it measures brain electrical activity, offering greater resolution and data accuracy. When associated to brain activities in user-computer interactions, it can provide information that allows analyzing adequacy and user satisfaction. Thus, the objective of this paper is to identify works that specify which information on electroencephalography assessment may be used to compose an analysis of its interactions with conversational systems. The delimited that the research problems are: (1) What information about user experience by electroencephalography can be used to compose an analysis of their interactions with conversational systems? (2) What techniques are used to present user experience information by EEG to individuals? Based on the Systematic Review method, seven studies were identified that examined commercial EEG devices for UX assessment between 2011 and 2022. The current study found that multiple emotional stimuli were used and reported. The most popular technique among researchers is event induced emotional stimulation, in which participants passively perceive emotional stimuli such as images, music and videos to evoke certain emotions.

eHealth lifestyle interventions without human support (self-help interventions) are generally less effective, as they suffer from lower adherence levels. To solve this, we investigated whether (1) using a text-based conversational agent (TCA) and applying human cues contribute to a working alliance with the TCA, and whether (2) adding human cues and establishing a positive working alliance increase intervention adherence. Participants (N = 121) followed a TCA-supported app-based physical activity intervention. We manipulated two types of human cues: visual (ie, message appearance) and relational (ie, message content). We employed a 2 (visual cues: yes, no) x 2 (relational cues: yes, no) between-subjects design, resulting in four experimental groups: (1) visual and relational cues, (2) visual cues only, (3) relational cues only, or (4) no human cues. We measured the working alliance with the Working Alliance Inventory Short Revised form and intervention adherence as the number of days participants responded to the TCA's messages. Contrary to expectations, the working alliance was unaffected by using human cues. Working alliance was positively related to adherence (t(78) = 3.606, p = .001). Furthermore, groups who received visual cues showed lower adherence levels compared to those who received relational cues only or no cues (U = 1140.5, z = −3.520, p

AbstractIntegrating pleasure may be a successful strategy for reaching young people with sexual and reproductive health and rights (SRHR) interventions. However, sexual pleasure-related programming and research remains sparse. We aimed to assess chatbot acceptability and describe changes in SRHR attitudes and behaviours among Kenyan young adults engaging with a pleasure-oriented SRHR chatbot. We used an exploratory mixed-methods study design. Between November 2021 and January 2022, participants completed a self-administered online questionnaire before and after chatbot engagement. In-depth phone interviews were conducted among a select group of participants after their initial chatbot engagement. Quantitative data were analysed using paired analyses and interviews were analysed using thematic content analysis. Of 301 baseline participants, 38% (115/301) completed the endline survey, with no measured baseline differences between participants who did and did not complete the endline survey. In-depth interviews were conducted among 41 participants. We observed higher satisfaction at endline vs. baseline on reported ability to exercise sexual rights (P ≤ 0.01), confidence discussing contraception (P ≤ 0.02) and sexual feelings/needs (P ≤ 0.001) with their sexual partner(s). Qualitative interviews indicated that most participants valued the chatbot as a confidential and free-of-judgment source of trustworthy “on-demand” SRHR information. Participants reported improvements in sex-positive communication with partners and safer sex practices due to new learnings from the chatbot. We observed increases in SRHR empowerment among young Kenyans after engagement with the chatbot. Integrating sexual pleasure into traditional SRHR content delivered through digital tools is a promising strategy to advance positive SRHR attitudes and practices among youth.

Digital skills, particularly programming, have become a vital prerequisite for succeeding in today’s work life. Developing those skills is, however, a challenging task, as it requires perseverance, effort, and practice. To teach coding, individualized tutoring adapted to the novice programmers’ state of knowledge has evolved as the most promising learning strategy. However, offering sufficient learning support while practicing coding tasks is a challenge due to resource constraints. Following a three-cycle design science research approach, we developed a chatbot-based digital tutor that can support novice programmers using individualized, automated conversations based on adaptive learning paths and in-depth code analyses. In this article, we present the final version of the digital tutor software and report the findings of introducing it in a field setting over two entire lecture periods. We show that digital tutors can effectively provide individualized guidance in moments of need and offer high learning satisfaction in a long-term learning setting. This article expands the state of research by presenting insights into how students interact with a digital tutor over an entire lecture period. This also provides insights on how to design digital tutors for developing skills.

Chatbots and voice assistants are digital transformers of the interface between companies and customers. They have become part of the current practice of companies and represent a distinct domain of business research. This trend is significant in the broad business context marked by the digital transformation of companies, the fast development of e-commerce and the omnichannel behavior of customers. This article is a systematic review of the high-quality business research literature on chatbots and voice assistants. The purpose of this review is to critically analyze the current status of this literature from the perspective of the theories, contexts, characteristics and methodologies applied. The final aim of this review is to support the domain of study by suggesting a relevant agenda for future research. This review brings several contributions to the research domain, including the following: the identification of the main streams of high-quality business research in function of the theories in which the studies are grounded; the development of a conceptual framework of the investigated variables (antecedents, mediators, moderators and consequences); the creation of a conceptual framework of the humanlikeness of chatbots and voice assistants; the development of a conceptual framework of the consumer experience with chatbots and voice assistants and the presentation of insights for business practice.

Alexander Wang,1,2 Zhiyu Qian,1,2 Logan Briggs,1,2 Alexander P Cole,1,2 Leonardo O Reis,1– 3 Quoc-Dien Trinh1,2 1Division of Urological Surgery, Brigham and Women’s Hospital, Harvard Medical School, Boston, MA, USA; 2Center for Surgery and Public Health, Brigham and Women’s Hospital, Harvard Medical School, Boston, MA, USA; 3UroScience, School of Medical Sciences, University of Campinas, UNICAMP, and Immuno-Oncology Division, Pontifical Catholic University of Campinas, PUC-Campinas, Sao Paulo, BrazilCorrespondence: Quoc-Dien Trinh, Surgery, Harvard Medical School, Division of Urological Surgery, Brigham and Women’s Hospital, 45 Francis St, ASB II-3, Boston, MA, 02115, USA, Tel +1 617 525-7350, Fax +1 617 525-6348, Email qtrinh@bwh.harvard.eduBackground: Few reports have investigated chatbots in patient care. We aimed to assess the current applications, limitations, and challenges in the literature on chatbots employed in oncological care.Methods: We queried the PubMed database through April 2022 and included studies that investigated the use of chatbots in different phases of oncological care. The search used five different combinations of the specific terms “chatbot”, “cancer”, “oncology”, and “conversational agent”. Inclusion criteria were chatbot use in any aspect of oncological care—prevention, patient education, treatment, and surveillance.Results: The initial search yielded 196 records, 21 of which met inclusion criteria. The identified chatbots mostly focused on breast and ovarian cancer (n=8), with the second most common being cervical cancer (n=3). Good patient satisfaction was reported among 14 of 21 chatbots. The most reported chatbot applications were cancer screening, prevention, risk stratification, treatment, monitoring, and management. Of 12 studies examining efficacy of care via chatbot, 9 demonstrated improvements compared to standard care.Conclusion: Chatbots used for oncological care to date demonstrate high user satisfaction, and many have shown efficacy in improving patient-centered communication, accessibility to cancer-related information, and access to care. Currently, chatbots are primarily limited by the need for extensive user-testing and iterative improvement before widespread implementation.Keywords: chatbot, conversational agent, artificial intelligence, AI, cancer, oncology

Purpose – This paper aims to explore the overall research question “How can artificial intelligence (AI) influence consumer information disclosure?”. It considers how anthropomorphism of AI, personalisation and privacy concerns influence consumers’ attitudes and encourage disclosure of their private information. Design/methodology/approach – This research draws upon the personalisation-privacy paradox (PPP) and privacy calculus theory (PCT) to address the research question and examine how AI can influence consumer information disclosure. It is proposed that anthropomorphism of AI and personalisation positively influence consumer attitudes and intentions to disclose personal information to a digital assistant, while privacy concerns negatively affect attitude and information disclosure. Findings – This paper develops a conceptual model based on and presents seven research propositions (RPs) for future research. Originality/value – Building upon PPP and PCT, this paper presents a view on the benefits and drawbacks of AI from a consumer perspective. This paper contributes to literature by critically reflecting upon on the question how consumer information disclosure is influenced by AI. In addition, seven RPs and future research areas are outlined in relation to privacy and consumer information disclosure in relation to AI. ¿Cómo anima la IA a los consumidores a compartir sus secretos? – El papel del antropomorfismo, la personalización y los problemas de privacidad y perspectivas para la investigación futura Resumen Propósito – Este artículo explora la pregunta general de investigación “¿Cómo puede influir la inteligencia artificial (IA) en la divulgación de información por parte de los consumidores? Se analiza cómo el antropomorfismo de la IA, la personalización y la preocupación por la privacidad influyen en la actitud de los consumidores y fomentan la revelación de su información privada. Diseño/metodología/enfoque – Esta investigación se basa en la paradoja de la personalización y la privacidad y en la teoría del cálculo de la privacidad para abordar la pregunta de investigación y examinar cómo la IA puede influir en la revelación de información de los consumidores. Se propone que el antropomorfismo de la IA y la personalización influyen positivamente en las actitudes de los consumidores y en su intención de revelar información personal a un asistente digital, mientras que la preocupación por la privacidad afecta negativamente a la actitud y a la revelación de información. Conclusiones – Este artículo desarrolla un modelo conceptual basado en siete propuestas de investigación para el futuro. Originalidad – Basándose en la paradoja de la personalización y la privacidad y en la teoría del cálculo de la privacidad, este artículo presenta un punto de vista sobre los beneficios e inconvenientes de la IA desde la perspectiva del consumidor. Este artículo contribuye a la literatura al reflexionar de forma crítica sobre la cuestión de cómo influye la IA en la revelación de información del consumidor. Además, se esbozan siete propuestas de investigación y futuras áreas de investigación en relación con la privacidad y la divulgación de información del consumidor en relación con la IA. 人工智能如何 – 鼓励消费者分享他们的秘密？拟人化、个性化和隐私问题的作用以及未来研究的途径 摘要 目的 – 本文探讨了 “人工智能如何影响消费者的信息披露？"这一总体研究问题。它考虑了人工智能（AI）的拟人化、个性化和隐私问题是如何影响消费者的态度并鼓励他们披露私人信息的。 设计/方法/途径 – 本研究借鉴了个性化-隐私悖论和隐私计算理论来解决研究问题, 并研究人工智能如何影响消费者信息披露。本文提出, 人工智能的拟人化和个性化对消费者向数字助理披露个人信息的态度和意图有积极影响, 而隐私问题对态度和信息披露有消极影响。 研究结果 – 本文在此基础上建立了一个概念模型, 并为未来的研究提出了七个研究命题。 原创性 – 在个性化-隐私悖论和隐私计算理论的基础上, 本文从消费者的角度提出了对人工智能的好处和坏处的看法。本文通过对消费者信息披露如何受到人工智能影响的问题进行批判性反思, 对文献做出了贡献。此外, 本文概述了与人工智能相关的隐私和消费者信息披露方面的七个研究命题和未来研究领域。

Background Although psychoeducation is generally recommended for the treatment of adult attention-deficit hyperactivity disorder (ADHD), participation in clinical psychoeducation groups is impeded by waiting times and the constrained number of patients who can simultaneously attend a group. Digital psychoeducation attempts are promising, but the rapidly expanding number of apps lack evidence and are mostly limited to only a few implemented interactive elements. Aims To determine the potential of digital, self-guided psychoeducation for adult ADHD, a newly developed interactive chatbot was compared with a previously validated, conventional psychoeducation app. Method Forty adults with ADHD were randomised, of whom 17 participants in each group completed self-guided psychoeducation based on either a chatbot or conventional psychoeducation app between October 2020 and July 2021. ADHD core symptoms were assessed before and after the 3-week interventions, using both the blinded observer-rated Integrated Diagnosis of ADHD in Adulthood interview and the self-rated ADHD Self-Assessment Scale (ADHS-SB). Results Observer- and patient-rated ADHD symptoms were significantly reduced from pre- to post-intervention (observer-rated: mean difference −6.18, 95% CI −8.06 to −4.29; patient-rated: mean difference −2.82, 95% CI −4.98 to −0.67). However, there were no group × intervention interaction effects that would indicate a stronger therapeutic benefit of one of the interventions. Likewise, administered psychoeducational knowledge quizzes did not show differences between the groups. No adverse events were reported. Conclusions Self-guided psychoeducation based on a chatbot or a conventional app appears similarly effective and safe for improving ADHD core symptoms. Future research should compare additional control interventions and examine patient-related outcomes and usability preferences in detail.

Conversational agents are a piece of software widely used nowadays in several domains, such as e-commerce, customer support, education, among others. To build one, proficiency in distinct areas of knowledge is necessary. Moreover, its development demands the availability of frameworks, tools, and proposals to facilitate its application in several domain areas. Recently, the adoption of models in a software development process has increased through the application of Model-Driven Development in several areas to improve and increase productivity in software development. This work aims to provide state of the art through a Systematic Mapping Study regarding to Model-Driven Development approaches to automate or semi-automate the development of Chatbots. For this study, 429 scientific articles were analyzed, of which, after the inclusion and exclusion criteria, only 20 were considered primary studies.

Conversational artificial intelligence (AI) is a type of artificial intelligence that uses machine learning techniques to understand and respond to user inputs. This paper presents a conversational chat system that uses an attention mechanism to respond to COVID-19 inquiries. The model is based on the Luong Attention Mechanism’s three scoring methodologies the Dot Attention Mechanism, the General Attention Mechanism, and the Concat Attention Mechanism. The results show that the accuracy of the dot attention mechanism is highest and is 87% when the test questions were obtained directly from the database, as determined by an examination of the results, compared to 38% when the attention mechanism is not used. Furthermore, when the questions are asked with natural variations, human verification accuracy is 63% compared to 16% when the attention mechanism is not used. The research suggests that chatbots can be used everywhere due to their accuracy and accessibility around the clock.

Smart speakers and conversational agents have been accepted into our homes for a number of tasks such as playing music, interfacing with the internet of things, and more recently, general chit-chat. However, they have been less readily accepted in our workplaces. This may be due to data privacy and security concerns that exist with commercially available smart speakers. However, one of the reasons for this may be that a smart speaker is simply too abstract and does not portray the social cues associated with a trustworthy work colleague. Here, we present an in-depth mixed method study, in which we investigate this question of embodiment in a serious task-based work scenario of a first responder team. We explore the concepts of trust, engagement, cognitive load, and human performance using a humanoid head style robot, a commercially available smart speaker, and a specially developed dialogue manager. Studying the effect of embodiment on trust, being a highly subjective and multi-faceted phenomena, is clearly challenging, and our results indicate that potentially, the robot, with its anthropomorphic facial features, expressions, and eye gaze, was trusted more than the smart speaker. In addition, we found that embodying a conversational agent helped increase task engagement and performance compared to the smart speaker. This study indicates that embodiment could potentially be useful for transitioning conversational agents into the workplace, and further in situ, “in the wild” experiments with domain workers could be conducted to confirm this.

BackgroundThe current paper details findings from Elena+: Care for COVID-19, an app developed to tackle the collateral damage of lockdowns and social distancing, by offering pandemic lifestyle coaching across seven health areas: anxiety, loneliness, mental resources, sleep, diet and nutrition, physical activity, and COVID-19 information.MethodsThe Elena+ app functions as a single-arm interventional study, with participants recruited predominantly via social media. We used paired samples T-tests and within subjects ANOVA to examine changes in health outcome assessments and user experience evaluations over time. To investigate the mediating role of behavioral activation (i.e., users setting behavioral intentions and reporting actual behaviors) we use mixed-effect regression models. Free-text entries were analyzed qualitatively.ResultsResults show strong demand for publicly available lifestyle coaching during the pandemic, with total downloads (N = 7′135) and 55.8% of downloaders opening the app (n = 3,928) with 9.8% completing at least one subtopic (n = 698). Greatest areas of health vulnerability as assessed with screening measures were physical activity with 62% (n = 1,000) and anxiety with 46.5% (n = 760). The app was effective in the treatment of mental health; with a significant decrease in depression between first (14 days), second (28 days), and third (42 days) assessments: F2,38 = 7.01, p = 0.003, with a large effect size (η2G = 0.14), and anxiety between first and second assessments: t54 = 3.7, p =

Despite the increasing number of companies employing chatbots for tasks that previously needed human involvement, researchers and managers are only now beginning to examine chatbots in customer-brand relationship-building efforts. Not much is known, however, about how managers could modify their chatbot greeting, especially incorporating humour, to increase engagement and foster positive customer–brand interactions. The research aims to investigate how humour in a chatbot welcome message influences customers’ emotional attachment and conversion-to-lead through the mediating role of engagement. The findings of the experiment indicate that conversion-to-lead and emotional attachment rise when chatbots begin with a humorous (vs neutral) greeting. Engagement mediates this effect such that a humorous (vs neutral) greeting sparks engagement and thus makes users more emotionally attached and willing to give out their contact information to the brand. The study contributes to the existing research on chatbots, combining and expanding previous research on human–computer interaction and, more specifically, human–chatbot interaction, as well as the usage of humour in conversational marketing contexts. This study provides managers with insight into how chatbot greetings can engage consumers and convert them into leads.

BackgroundPeople with diabetes mellitus not only have to deal with physical health problems, but also with the psycho-social challenges their chronic disease brings. Currently, technological tools that support the psycho-social context of a patient have received little attention.ObjectiveThe objective of this work is to determine the feasibility and preliminary efficacy of an automated conversational agent to deliver, to people with diabetes, personalised psycho-education on dealing with (psycho-)social distress related to their chronic illness.MethodsIn a double-blinded between-subject study, 156 crowd-workers with diabetes received a social help program intervention in three sessions over three weeks. They were randomly assigned to receive support from either an interactive conversational support agent (n=79) or a self-help text from the book “Diabetes burnout” as a control condition (n=77). Participants completed the Diabetes Distress Scale (DDS) before and after the intervention, and after the intervention, the Client Satisfaction Questionnaire (CSQ-8), Feeling of Being Heard (FBH), and System Usability Scale (SUS).ResultsResults indicate that people using the conversational agent have a larger reduction in diabetes distress (M=−0.305, SD=0.865) than the control group (M=0.002, SD=0.743) and this difference is statistically significant (t(154)=2.377, p=0.019). A hypothesised mediation effect of “attitude to the social help program” was not observed.ConclusionsAn automated conversational agent can deliver personalised psycho-education on dealing with (psycho-)social distress to people with diabetes and reduce diabetes distress more than a self-help book.Ethics, Study Registration and Open ScienceThis study has been preregistered with the Open Science Foundation (osf.io/yb6vg) and has been accepted by the Human Research Ethics Committee - Delft University of Technology under application number 1130. The data and analysis script are available: https://surfdrive.surf.nl/files/index.php/s/4xSEHCrAu0HsJ4P.

This study examines the potential of AI-powered personal voice assistants (PVAs) in reducing loneliness and increasing social support among older adults. With the aging population rapidly expanding, innovative solutions are essential. Prior research has indicated the effectiveness of various interactive communication technologies (ICTs) in mitigating loneliness, but studies focusing on PVAs, particularly considering their modality (audio vs. video), are limited. This research aims to fill this gap by evaluating how voice assistants, in both audio and video formats, influence perceived loneliness and social support. This study examined the impact of voice assistant technology (VAT) interventions, both audio-based (A-VAT) and video-based (V-VAT), on perceived loneliness and social support among 34 older adults living alone. Over three months, participants engaged with Amazon Alexa™ PVA through daily routines for at least 30 min. Using a hybrid natural language processing framework, interactions were analyzed. The results showed reductions in loneliness (Z = −2.99, p < 0.01; pre-study loneliness mean = 1.85, SD = 0.61; post-study loneliness mean = 1.65, SD = 0.57), increases in social support post intervention (Z = −2.23, p < 0.05; pre-study social support mean = 5.44, SD = 1.05; post-study loneliness mean = 5.65, SD = 1.20), and a correlation between increased social support and loneliness reduction when the two conditions are combined (ρ = −0.39, p < 0.05). In addition, V-VAT was more effective than A-VAT in reducing loneliness (U = 85.50, p < 0.05) and increasing social support (U = 95, p < 0.05). However, no significant correlation between changes in perceived social support and changes in perceived loneliness was observed in either intervention condition (V-VAT condition: ρ = −0.24, p = 0.37; A-VAT condition: ρ = −0.46, p = 0.06). This study’s findings could significantly contribute to developing targeted interventions for improving the well-being of aging adults, addressing a critical global issue.

The emergence of generative language models (GLMs), such as OpenAI’s ChatGPT, is changing the way we communicate with computers and has a major impact on the educational landscape. While GLMs have great potential to support education, their use is not unproblematic, as they suffer from hallucinations and misinformation. In this paper, we investigate how a very limited amount of domain-specific data, from lecture slides and transcripts, can be used to build knowledge-based and generative educational chatbots. We found that knowledge-based chatbots allow full control over the system’s response but lack the verbosity and flexibility of GLMs. The answers provided by GLMs are more trustworthy and offer greater flexibility, but their correctness cannot be guaranteed. Adapting GLMs to domain-specific data trades flexibility for correctness.

Abstract Background Dietary supplements (DS) have been widely used by consumers, but the information around the efficacy and safety of DS is disparate or incomplete, thus creating barriers for consumers to find information effectively. Conversational agent (CA) systems have been applied to healthcare domain, but there is no such system to answer consumers regarding DS use, although widespread use of DS. In this study, we develop the first CA system for DS use. Methods Our CA system for DS use developed on the MindMeld framework, consists of three components: question understanding, DS knowledge base, and answer generation. We collected and annotated 1509 questions to develop a natural language understanding module (e.g., question type classifier, named entity recognizer) which was then integrated into MindMeld framework. CA then queries the DS knowledge base (i.e., iDISK) and generates answers using rule-based slot filling techniques. We evaluated the algorithms of each component and the CA system as a whole. Results CNN is the best question classifier with an F1 score of 0.81, and CRF is the best named entity recognizer with an F1 score of 0.87. The system achieves an overall accuracy of 81% and an average score of 1.82 with succ@3 + score of 76.2% and succ@2 + of 66% approximately. Conclusion This study develops the first CA system for DS use using the MindMeld framework and iDISK domain knowledge base.

SQL is a key programming language for data scientists, but its learning is sometimes challenging, especially if the learner does not have a proper computer science background. This article introduces ChatbotSQL, a conversational agent that aims to support the autonomous learning of the SQL language for database querying. ChatbotSQL proposes exercises and guides about the steps to be taken by the learner in case of doubts, providing customised feedback. ChatbotSQL has been created on top of IBM Watson Assistant and is available in a web platform. Students in a higher education database subject used ChatbotSQL extensively, showing a positive perception of its usefulness in supporting the resolution of complex queries.

As psychological diseases become more prevalent and are identified as the leading cause of acquired disability, it is essential to assist people in improving their mental health. Digital therapeutics (DTx) has been widely studied to treat psychological diseases with the advantage of cost savings. Among the techniques of DTx, a conversational agent can interact with patients through natural language dialog and has become the most promising one. However, conversational agents' ability to accurately show emotional support (ES) limits their role in DTx solutions, especially in mental health support. One of the main reasons is that the prediction of emotional support systems does not extract effective information from historical dialog data and only depends on the data derived from one single-turn interaction with users. To address this issue, we propose a novel emotional support conversation agent called the STEF agent that generates more supportive responses based on a thorough view of past emotions. The proposed STEF agent consists of the emotional fusion mechanism and strategy tendency encoder. The emotional fusion mechanism focuses on capturing the subtle emotional changes throughout a conversation. The strategy tendency encoder aims at foreseeing strategy evolution through multi-source interactions and extracting latent strategy semantic embedding. Experimental results on the benchmark dataset ESConv demonstrate the effectiveness of the STEF agent compared with competitive baselines.

The development and use of conversational agents grow every day. However, those systems still need to meet users' expectations. As a result, new design practices for conversational agents are emerging. One facet is the culturally informed design of those systems. Tailoring conversational agents culturally can increase engagement, trustworthiness, and acceptance. While an emerging trend, literature still needs to discuss research and application of design practices related to culture and conversational agents. The present study investigates 5398 articles involving conversational agents and culture over the last seven years. In this context, we selected 23 articles based on their approaches and objectives related to our main subject. The findings indicate that most studies in the field are mainly focused on the feasibility of cultural markers tailored to those systems. The main contribution is the identification of the main challenges, contexts and design practices in the field. These results contributed to discussions regarding conversational agents and highlighted some research gaps for future study.

Sign language (SL) avatar systems aid communication between the hearing and deaf communities. Despite technological progress, there is a lack of a standardized avatar development framework. This paper offers a systematic review of SL avatar systems spanning from 1982 to 2022. Using PRISMA guidelines, we shortlisted 47 papers from an initial 1765, focusing on sign synthesis techniques, corpora, design strategies, and facial expression methods. We also discuss both objective and subjective evaluation methodologies. Our findings highlight key trends and suggest new research avenues for improving SL avatars.

BackgroundThe use of chatbots to address mental health conditions have become increasingly popular in recent years. However, few studies aimed to teach parenting skills through chatbots, and there are no reports on parental user experience. Aim: This study aimed to assess the user experience of a parenting chatbot micro intervention to teach how to praise children in a Spanish-speaking country.MethodsA sample of 89 parents were assigned to the chatbot micro intervention as part of a randomized controlled trial study. Completion rates, engagement, satisfaction, net promoter score, and acceptability were analyzed.Results66.3% of the participants completed the intervention. Participants exchanged an average of 49.8 messages (SD = 1.53), provided an average satisfaction score of 4.19 (SD = .79), and reported that they would recommend the chatbot to other parents (net promoter score = 4.63/5; SD = .66). Acceptability level was high (ease of use = 4.66 [SD = .73]; comfortability = 4.76 [SD = .46]; lack of technical problems = 4.69 [SD = .59]; interactivity = 4.51 [SD = .77]; usefulness for everyday life = 4.75 [SD = .54]).ConclusionsOverall, users completed the intervention at a high rate, engaged with the chatbot, were satisfied, would recommend it to others, and reported a high level of acceptability. Chatbots have the potential to teach parenting skills however research on the efficacy of parenting chatbot interventions is needed.

Abstract Background This systematic review aimed to evaluate AI chatbot characteristics, functions, and core conversational capacities and investigate whether AI chatbot interventions were effective in changing physical activity, healthy eating, weight management behaviors, and other related health outcomes. Methods In collaboration with a medical librarian, six electronic bibliographic databases (PubMed, EMBASE, ACM Digital Library, Web of Science, PsycINFO, and IEEE) were searched to identify relevant studies. Only randomized controlled trials or quasi-experimental studies were included. Studies were screened by two independent reviewers, and any discrepancy was resolved by a third reviewer. The National Institutes of Health quality assessment tools were used to assess risk of bias in individual studies. We applied the AI Chatbot Behavior Change Model to characterize components of chatbot interventions, including chatbot characteristics, persuasive and relational capacity, and evaluation of outcomes. Results The database search retrieved 1692 citations, and 9 studies met the inclusion criteria. Of the 9 studies, 4 were randomized controlled trials and 5 were quasi-experimental studies. Five out of the seven studies suggest chatbot interventions are promising strategies in increasing physical activity. In contrast, the number of studies focusing on changing diet and weight status was limited. Outcome assessments, however, were reported inconsistently across the studies. Eighty-nine and thirty-three percent of the studies specified a name and gender (i.e., woman) of the chatbot, respectively. Over half (56%) of the studies used a constrained chatbot (i.e., rule-based), while the remaining studies used unconstrained chatbots that resemble human-to-human communication. Conclusion Chatbots may improve physical activity, but we were not able to make definitive conclusions regarding the efficacy of chatbot interventions on physical activity, diet, and weight management/loss. Application of AI chatbots is an emerging field of research in lifestyle modification programs and is expected to grow exponentially. Thus, standardization of designing and reporting chatbot interventions is warranted in the near future. Systematic review registration International Prospective Register of Systematic Reviews (PROSPERO): CRD42020216761 .

Social robots have grown increasingly integrated into our daily lives in recent years. Robots can be good social agents who engage with people, such as assistants and counselors, and good partners and companions with whom people can form good relationships. Furthermore, unlike devices such as smart speakers or virtual agents on a screen, robots have physicality, which allows them to observe the actual environment using sensors and respond behaviorally with full-body motions. In order to engage people in dialogue and create good relationships with robots as close partners, real-time interaction is important. In this article, we present a dialogue system platform developed with the aim of providing robots with social skills. We also built a system architecture for the robot to respond with speech and gestures within the dialogue system platform, which attempts to enable natural engagement with the robot and takes advantage of its physicality. In addition, we think the process called “co-creation” is important to build a good human–robot interaction system. Engineers must bridge the gap between users and robots in order for them to interact more effectively and naturally, not only by building systems unilaterally but also from a range of views based on the opinions of real users. We reported two experiments using the developed dialogue interaction system with a robot. One is an experiment with elderly people as the initial phase in this co-creation process. The second experiment was conducted with a wide range of ages, from children to adults. Through these experiments, we can obtain a lot of useful insights for improving the system. We think that repeating this co-creation process is a useful approach toward our goal that humans and robots can communicate in a natural way as good partners such as family and friends.

Human milk is the most important way to feed and protect newborns as it has the components to ensure human health. Human Milk Banks (HMBs) form a network that offers essential services to ensure that newborns and mothers can take advantage of the benefits of human milk. Despite this, there is low adherence to exclusive breastfeeding in Brazil, and human milk stocks available in HMBs are usually below demand. This study aimed to co-develop a smart conversational agent (Lhia chatbot) for breastfeeding education and human milk donor recruitment for HMBs. The co-design methodology was carried out with health professionals from the HMB of the University Hospital of the Federal University of Maranhão (HMB-UHFUMA). Five natural language processing pipelines based on deep learning were trained to classify different user intents. During the rounds in the co-design procedure, improvements were made in the content and structure of the conversational flow, and the data produced were used in subsequent training sessions of pipelines. The best-performing pipeline achieved an accuracy of 93%, with a fallback index of 15% for 1851 interactions. In addition, the conversational flow improved, reaching 2904 responses given by the chatbot during the last co-design round. The pipeline with the best performance and the most improved conversational flow were deployed in the Lhia chatbot to be put into production.

Abstract Background Less than 2% of overweight children and adolescents in Switzerland can participate in multi-component behaviour changing interventions (BCI), due to costs and lack of time. Stress often hinders positive health outcomes in youth with obesity. Digital health interventions, with fewer on-site visits, promise health care access in remote regions; however, evidence for their effectiveness is scarce. Methods This randomized controlled not blinded trial (1:1) was conducted in a childhood obesity center in Switzerland. Forty-one youth aged 10–18 years with body mass index (BMI) > P.90 with risk factors or co-morbidities or BMI > P.97 were recruited. During 5.5 months, the PathMate2 group (PM) received daily conversational agent counselling via mobile app, combined with standardized counselling (4 on-site visits). Controls (CON) participated in a BCI (7 on-site visits). We compared the outcomes of both groups after 5.5 (T1) and 12 (T2) months. Primary outcome was reduction in BMI-SDS (BMI standard deviation score: BMI adjusted for age and sex). Secondary outcomes were changes in body fat and muscle mass (bioelectrical impedance analysis), waist-to-height ratio, physical capacities (modified Dordel-Koch-Test), blood pressure and pulse. Additionally, we hypothesized that less stressed children would lose more weight. Thus, children performed biofeedback relaxation exercises while stress parameters (plasma cortisol, stress questionnaires) were evaluated. Results At intervention start median BMI-SDS of all patients (18 PM, 13 CON) was 2.61 (obesity > + 2SD). BMI-SDS decreased significantly in CON at T1, but not at T2, and did not decrease in PM during the study. Muscle mass, strength and agility improved significantly in both groups at T2; only PM reduced significantly their body fat at T1 and T2. Average daily PM app usage rate was 71.5%. Cortisol serum levels decreased significantly after biofeedback but with no association between stress parameters and BMI-SDS. No side effects were observed. Conclusions Equally to BCI, PathMate2 intervention resulted in significant and lasting improvements of physical capacities and body composition, but not in sustained BMI-SDS decrease. This youth-appealing mobile health intervention provides an interesting approach for youth with obesity who have limited access to health care. Biofeedback reduces acute stress and could be an innovative adjunct to usual care.

Background Despite their increasing prevalence and potential, eHealth applications for behavior change suffer from a lack of adherence and from dropout. Advances in virtual coach technology provide new opportunities to improve this. However, these applications still do not always offer what people need. We, therefore, need a better understanding of people’s needs and how to address these, based on both actual experiences of users and their reflections on envisioned scenarios. Methods We conducted a longitudinal study in which 671 smokers interacted with a virtual coach in five sessions. The virtual coach assigned them a new preparatory activity for quitting smoking or increasing physical activity in each session. Participants provided feedback on the activity in the next session. After the five sessions, participants were asked to describe barriers and motivators for doing their activities. In addition, they provided their views on videos of scenarios such as receiving motivational messages. To understand users’ needs, we took a mixed-methods approach. This approach triangulated findings from qualitative data, quantitative data, and the literature. Results We identified 14 main themes that describe people’s views of their current and future behaviors concerning an eHealth application. These themes relate to the behaviors themselves, the users, other parties involved in a behavior, and the environment. The most prevalent theme was the perceived usefulness of behaviors, especially whether they were informative, helpful, motivating, or encouraging. The timing and intensity of behaviors also mattered. With regards to the users, their perceived importance of and motivation to change, autonomy, and personal characteristics were major themes. Another important role was played by other parties that may be involved in a behavior, such as general practitioners or virtual coaches. Here, the themes of companionableness, accountability, and nature of the other party (i.e., human vs AI) were relevant. The last set of main themes was related to the environment in which a behavior is performed. Prevalent themes were the availability of sufficient time, the presence of prompts and triggers, support from one’s social environment, and the diversity of other environmental factors. We provide recommendations for addressing each theme. Conclusions The integrated method of experience-based and envisioning-based needs acquisition with a triangulate analysis provided a comprehensive needs classification (empirically and theoretically grounded). We expect that our themes and recommendations for addressing them will be helpful for designing applications for health behavior change that meet people’s needs. Designers should especially focus on the perceived usefulness of application components. To aid future work, we publish our dataset with user characteristics and 5,074 free-text responses from 671 people.

IntroductionAnthropomorphic conversational agents (ACA) are a promising digital tool to support self-management of type 2 diabetes (T2D), albeit little explored. There is a dearth of literature on the detailed content of these interventions, which may limit effectiveness and replication. Our aim is to describe the development of an evidence and theory-based intervention to improve physical activity in older adults with T2D, subsumed in a multi-behavior intervention via a mobile application with an ACA.MethodsOverall decisions on the multi-behavior intervention design, such as the use of standardized behavior change techniques (BCTTv1), guided the development of the physical activity component. Firstly, recommendations on ambulatory activity were used to select the target behavior (walking). Meta-research on effective behavior change techniques (BCTs) was then identified. One meta-analysis linked effective BCTs with the three basic psychological needs of the self-determination theory (SDT). This meta-analysis, taken together with additional evidence on SDT, led to the selection of this theory to inform the design. BCTs were extracted from meta-research; we selected the most appropriate to be operationalized via the conversational agent through multidisciplinary discussions. Rules governing the dialogue flow and BCTs tailoring, taking the form “if some conditions hold then execute some action,” were derived based on the Basic Psychological in Exercise Scale (competence, autonomy, and relatedness scores), in conjunction with published evidence and multidisciplinary discussions.ResultsThirteen BCTs were implemented in the prototype via the ACA (e.g., goal setting behavior 1.1). Six if-then rules were derived and depicted in the dialogue steps through process flow diagrams, which map how the system functions. An example of a rule is “If competence score ≤ 10 then, apply BCT 1.1 with 500 steps increments as options for the daily walking goal; If competence score > 10 then, apply BCT 1.1 with 1,000 steps increments as options for the daily walking goal.”ConclusionEvidence and SDT were translated into a mobile application prototype using an ACA to promote physical activity in older adults with T2D. This approach, which includes 13 BCTs and six if-then rules for their tailoring, may leverage the efforts of others in developing similar interventions.

E-mental health for depression is increasingly used in clinical practice, but patient adherence suffers as therapist involvement decreases. One reason may be the low responsiveness of existing programs: especially autonomous systems are lacking in their input interpretation and feedback-giving capabilities. Here, we explore (a) to what extent a more socially intelligent and, therefore, technologically advanced solution, namely a conversational agent, is a feasible means of collecting thought record data in dialog, (b) what people write about in their thought records, (c) whether providing content-based feedback increases motivation for thought recording, a core technique of cognitive therapy that helps patients gain an understanding of how their thoughts cause their feelings. Using the crowd-sourcing platform Prolific, 308 participants with subclinical depression symptoms were recruited and split into three conditions of varying feedback richness using the minimization method of randomization. They completed two thought recording sessions with the conversational agent: one practice session with scenarios and one open session using situations from their own lives. All participants were able to complete thought records with the agent such that the thoughts could be interpreted by the machine learning algorithm, rendering the completion of thought records with the agent feasible. Participants chose interpersonal situations nearly three times as often as achievement-related situations in the open chat session. The three most common underlying schemas were the Attachment, Competence, and Global Self-evaluation schemas. No support was found for a motivational effect of providing richer feedback. In addition to our findings, we publish the dataset of thought records for interested researchers and developers.

The user experience of an asynchronous video interview system, conventionally is not reciprocal or conversational. Interview applicants expect that, like a typical face-to-face interview, they are innate and coherent. We posit that the planned adoption of limited probing through follow-up questions is an important step towards improving the interaction. We propose a follow-up question generation model (followQG) capable of generating relevant and diverse follow-up questions based on the previously asked questions, and their answers. We implement a 3D virtual interviewing system, Maya, with capability of follow-up question generation. Existing asynchronous interviewing systems are not dynamic with scripted and repetitive questions. In comparison, Maya responds with relevant follow-up questions, a largely unexplored feature of irtual interview systems. We take advantage of the implicit knowledge from deep pre-trained language models to generate rich and varied natural language follow-up questions. Empirical results suggest that followQG generates questions that humans rate as high quality, achieving 77% relevance. A comparison with strong baselines of neural network and rule-based systems show that it produces better quality questions. The corpus used for fine-tuning is made publicly available.

Conversational agents are being increasingly adopted in various domains, such as e-commerce and customer services, and as a direct communication channel between companies and end-users. Several tools have been developed to facilitate their definition and deployment. They exploit existing cloud infrastructures and artificial intelligence (AI) techniques to efficiently process users’ input and extract conversational information. Major Information Technology (IT) companies, such as Google, IBM, Microsoft, and Amazon, have provided powerful tools to develop conversational agents. Still, choosing the most appropriate tool is not easy, as it may require high costs associated with automatic natural language processing (NLP) services and expertise in software engineering and AI. Therefore, this paper aims to analyze different tools to help developers and non-developers to choose the optimal tool for their specific scenario of creating a conversational agent.

Introduction: Virtual humans have expanded the training opportunities available to healthcare learners. Particularly, virtual humans have allowed simulation to display visual cues that were not previously possible in other forms of healthcare training. However, the effect of virtual human fidelity on the perception of visual cues is unclear. Therefore, we explore the effect of virtual human rendering style on the perceptions of visual cues in a healthcare context.Methods: To explore the effect of rendering style on visual cues, we created a virtual human interface that allows users to interact with virtual humans that feature different rendering styles. We performed a mixed design user study that had undergraduate healthcare students (n = 107) interact with a virtual patient. The interaction featured a patient experiencing an allergic reaction and required trainees to identify visual cues (patient symptoms). The rendering styles explored include a 3D modeled virtual human and an AI generated photorealistic virtual human. Visual cues were applied using a Snapchat Lens.Results: When users are given a frame of reference (users could directly compare symptoms on both rendering styles), they rated the realism and severity of the photorealistic virtual human’s symptoms significantly higher than the realism of the 3D virtual human’s symptoms. However, we were unable to find significant differences in symptom realism and severity ratings when users were not given a frame of reference (users only interacted with one style of virtual humans). Additionally, we were unable to find significant differences in user interpersonal communication behaviors between the 3D and photorealistic rendering styles.Conclusion: Our findings suggest 1) higher fidelity rendering styles may be preferred if the learning objectives of a simulation require observing subtle visual cues on virtual humans and 2) the realism of virtual human rendering style does not necessarily affect participants’ interpersonal communication behaviors (time spent, questions asked).

User's experience evaluation is a key challenge when studying human-agent interaction. Besides user's satisfaction, this question is addressed in virtual reality through the sense of presence and social presence, generally assessed thanks to subjective post-experience questionnaires. We propose in this article a novel approach making it possible to evaluate automatically these notions by correlating objective multimodal cues produced by users to their subjective sense of presence and social presence. This study is based on a multimodal human-agent interaction corpus collected in a task-oriented context: a virtual environment aiming at training doctors to break bad news to a patient played by a virtual agent. Based on a corpus study, we applied machine learning approaches to build a model predicting the user's sense of presence and social presence thanks to specific multimodal behavioral cues. We explore different classification algorithms and machine learning techniques (oversampling and clustering) to cope with the dimensionality of the dataset and to optimize the prediction performance. We obtain models to automatically and accurately predict the level of presence and social presence. The results highlight the relevance of a multimodal model, based both on verbal and non-verbal cues as objective measures of (social) presence. The main contribution of the article is two-fold: 1/ proposing the first presence and social prediction presence models offering a way to automatically provide a user's experience evaluation and 2/ showing the importance of multimodal information for describing these notions.

According to the World Health Organization, half the adult population around the world suffers from headaches. Even though this condition remains in most cases innocuous, it can have a major impact on the patient's quality of life but also on public health expenditure. Moreover, most patients manage their headaches on their own, without consulting a doctor. Therefore, self-medication can eventually lead to drug overuse, and consequently the emergence of a secondary disease called medication-overuse headache (MOH). The detection and follow-up of these unconventional patients represent a major challenge. Some of the latest technology advancements seem to be tailored and fitting for this context. The goal of this study is to investigate medication overuse in French patients suffering from headaches using the chatbot Vik Migraine. Data collection and analysis were assembled from answers to a questionnaire of 28 questions divided into three parts: socio-demographic profile, drug consumption, and medical follow-up. The study showed that medication overuse was often linked to increased headache frequency. Prescription drugs like triptans and opioids, were the most overused drugs among the cohort. This suggests that healthcare professionals could play a critical role in targeting these drugs in prevention of overuse.

Intent identification is one of the most critical components in conversational agent design. Conversational agent “is any dialogue system that not only conducts natural language processing but also responds automatically using human language.” (Conversational Agent, 2019). The crux of designing human-like conversational agent is to mimic how human understands another human and then responds “naturally”. The current study attempts to answer the fundamental question: how to model human processes of understanding another human? In order to answer that question, it starts from exploring some basic concepts relevant to intent identification from Conversation Analysis (CA). CA is a mature field that studies authentic human interaction. The basic concepts from CA are then synthesised into a model that potentially fit to existing framework and paradigm in conversational agent design, i.e. Natural Conversation Framework (NCF) and Intent-Entity-Context-Response (IECR) paradigm. Instead of using a made-up sentence, the model is then tested to an authentic conversational turn seksi sekali dirimu ‘you’re very sexy’. The test shows that the model is able to detect several possible intents contain in this authentic conversational turn. The model is also able to handle Conversational Indonesian and multi-modality. Considering the versatility of Conversation Analysis, in all likelihood the model will be able to handle any language and all kinds of modalities. Future study can be done to analyse more Conversational Indonesian data (to develop library of intent for Conversational Indonesian Language), as well as conversational data from different languages and conversational data containing diverse modalities.

In recent decades, the development of conversational agents or chatbots has increased, especially in the commercial sector. Although the first chatbot in computational history was presented as a psychotherapist, few virtual agents with this type of function have been built since then. In the present article we describe the fundamental aspects of designing a psychologistchatbot and, more specifically, a bot with psychological assessment functions. We review the available tools and the basic concepts for its construction. We also propose a series of assessment objectives that would guide the conversational agent’s dialogue. Finally, we discuss the advantages and disadvantages of chatbots and the scientific guarantees that they need to fulfill.

Abstract Background In the United States and parts of the world, the human papillomavirus vaccine uptake is below the prescribed coverage rate for the population. Some research have noted that dialogue that communicates the risks and benefits, as well as patient concerns, can improve the uptake levels. In this paper, we introduce an application ontology for health information dialogue called Patient Health Information Dialogue Ontology for patient-level human papillomavirus vaccine counseling and potentially for any health-related counseling. Results The ontology’s class level hierarchy is segmented into 4 basic levels - Discussion, Goal, Utterance, and Speech Task. The ontology also defines core low-level utterance interaction for communicating human papillomavirus health information. We discuss the design of the ontology and the execution of the utterance interaction. Conclusion With an ontology that represents patient-centric dialogue to communicate health information, we have an application-driven model that formalizes the structure for the communication of health information, and a reusable scaffold that can be integrated for software agents. Our next step will to be develop the software engine that will utilize the ontology and automate the dialogue interaction of a software agent.

While massive open online courses (MOOCs) can be effective in scaling education, orchestrating collaborative learning activities for large audiences remains a non-trivial task that introduces a series of practical challenges, such as the lack of adequate human support. Even when collaboration takes place, there is uncertainty whether meaningful interactions will occur among learners. This work presents the architecture of a prototype system called PeerTalk. The system was created to enable instructors to easily incorporate real-time collaborative learning activities into their online courses. Furthermore, PeerTalk employs a conversational agent service that aims to scaffold students’ online collaboration and provide valuable guidance, which can be configured by the course instructor. In order to investigate the user-acceptance of the system, two evaluation studies took place. The first one involved a group of experts, i.e., MOOC instructors who are expected to use such a system in their course, whereas the second study featured 44 postgraduate students. The study findings were encouraging in terms of the system efficiency and usability levels, laying the foundation for a conversational agent service, which can effectively scale the support of the teaching staff and be easily integrated in MOOC platforms, creating further opportunities for valuable social interaction among learners.

Conversational agents also known as Chatbots are the future of human-machine interaction. Classes with large number of students turn out to be a source of worry to the lecturers since they have to respond to their inquiries immediately. Embedding Chatbots in education systems is a necessity to boost the interaction between students and lectures especially those shy students feel ashamed of asking. Such systems possibly will assist the students to attain better learning outcomes. This paper presents Labeeb (Wiseman in Arabic) a conversational agents respond to student inquiries in specific course, objectives, learning outcomes and academic rules and regulations. Labeeb receives either text or speech inquiries, then respond in both written text and speech reply.

Chatbots are going to be the main tool for automated conversations with customers. Still, there is no consistent methodology for choosing a suitable chatbot platform for a particular business. This paper proposes a new method for chatbot platform evaluation. To describe the current state of chatbot platforms, two high-level approaches to chatbot platform design are discussed and compared. WYSIWYG platforms aim to simplicity but may lack some advanced features. All-purpose chatbot platforms require extensive technical skills and are more expensive but give their users more freedom in chatbot design. We provide an evaluation of six major chatbot solutions. The proposed method for the chatbot selection is demonstrated on two sample businesses – a large bank and a small taxi service.

Conversational agents and smart speakers have grown in popularity offering a variety of options for use, which are available through intuitive speech operation. In contrast to the standard dyad of a single user and a device, voice-controlled operations can be observed by further attendees resulting in new, more social usage scenarios. Referring to the concept of ‘media equation’ and to research on the idea of ‘computers as social actors,’ which describes the potential of technology to trigger emotional reactions in users, this paper asks for the capacity of smart speakers to elicit empathy in observers of interactions. In a 2 × 2 online experiment, 140 participants watched a video of a man talking to an Amazon Echo either rudely or neutrally (factor 1), addressing it as ‘Alexa’ or ‘Computer’ (factor 2). Controlling for participants’ trait empathy, the rude treatment results in participants’ significantly higher ratings of empathy with the device, compared to the neutral treatment. The form of address had no significant effect. Results were independent of the participants’ gender and usage experience indicating a rather universal effect, which confirms the basic idea of the media equation. Implications for users, developers and researchers were discussed in the light of (future) omnipresent voice-based technology interaction scenarios.

Sickle cell disease (SCD) is the most common genetic blood disorder in the world and affects millions of people. With aging, patients encounter an increasing number of comorbidities that can be acute, chronic, and potentially lethal (e.g., pain, multiple organ damages, lung disease). Comprehensive and preventive care for adults with SCD faces disparities (e.g., shortage of well-trained providers). Consequently, many patients do not receive adequate treatment, as outlined by evidence-based guidelines, and suffer from mistrust, stigmatization or neglect. Thus, adult patients often avoid necessary care, seek treatment only as a last resort, and rely on self-management to maintain control over the course of the disease. Hopefully, self-management positively impacts health outcomes. However, few patients possess the required skills (e.g., disease-specific knowledge, self-efficacy), and many lack motivation for effective self-care. Health coaching has emerged as a new approach to enhance patients' self-management and support health behavior changes. Recent studies have demonstrated that conversational agents (chatbots) could effectively support chronic patients' self-management needs, improve self-efficacy, encourage behavior changes, and reduce disease-severity. To date, the use of chatbots to support SCD self-management remains largely under-researched. Consequently, we developed a high-fidelity prototype of a fully automated health coaching chatbot, following patient-important requirements and preferences collected during our previous work. We recruited a small convenience sample of adults with SCD to examine the usability and perceived usefulness of the system. Participants completed a post-test survey using the System Usability Scale and the Usefulness Scale for Patient Information Material questionnaire. Thirty-three patients participated. The majority (64%) was affected by the most clinically severe SCD genotypes (Hb SS, HbSβ0). Most participants (94%) rated the chatbots as easy and fun to use, while 88% perceived it as useful support for patient empowerment. In the qualitative phase, 72% of participants expressed their enthusiasm using the chatbot, and 82% emphasized its ability to improve their knowledge about self-management. Findings suggest that chatbots could be used to promote the acquisition of recommended health behaviors and self-care practices related to the prevention of the main symptoms of SCD. Further work is needed to refine the system, and to assess clinical validity.