Search

Background: Patients often struggle with determining which outpatient specialist to consult based on their symptoms. Natural language processing models in health care offer the potential to assist patients in making these decisions before visiting a hospital., Objective: This study aimed to evaluate the performance of ChatGPT in recommending medical specialties for medical questions., Methods: We used a dataset of 31,482 medical questions, each answered by doctors and labeled with the appropriate medical specialty from the health consultation board of NAVER (NAVER Corp), a major Korean portal. This dataset includes 27 distinct medical specialty labels. We compared the performance of the fine-tuned Korean Medical bidirectional encoder representations from transformers (KM-BERT) and ChatGPT models by analyzing their ability to accurately recommend medical specialties. We categorized responses from ChatGPT into those matching the 27 predefined specialties and those that did not. Both models were evaluated using performance metrics of accuracy, precision, recall, and F 1 -score., Results: ChatGPT demonstrated an answer avoidance rate of 6.2% but provided accurate medical specialty recommendations with explanations that elucidated the underlying pathophysiology of the patient's symptoms. It achieved an accuracy of 0.939, precision of 0.219, recall of 0.168, and an F 1 -score of 0.134. In contrast, the KM-BERT model, fine-tuned for the same task, outperformed ChatGPT with an accuracy of 0.977, precision of 0.570, recall of 0.652, and an F 1 -score of 0.587., Conclusions: Although ChatGPT did not surpass the fine-tuned KM-BERT model in recommending the correct medical specialties, it showcased notable advantages as a conversational artificial intelligence model. By providing detailed, contextually appropriate explanations, ChatGPT has the potential to significantly enhance patient comprehension of medical information, thereby improving the medical referral process., (©Eunbeen Jo, Hakje Yoo, Jong-Ho Kim, Young-Min Kim, Sanghoun Song, Hyung Joon Joo. Originally published in JMIR Formative Research (https://formative.jmir.org), 18.10.2024.)

Enabling patients to actively document their health information significantly improves understanding of how therapies work, disease progression, and overall life quality affects for those living with chronic disorders such as hematologic malignancies. Advancements in artificial intelligence, particularly in areas such as natural language processing and speech recognition, have resulted in the development of interactive tools tailored for healthcare. This paper introduces an innovative conversational agent tailored to the Greek language. The design and deployment of this tool, which incorporates sentiment analysis, aims at gathering detailed family histories and symptom data from individuals diagnosed with hematologic malignancies. Furthermore, we discuss the preliminary findings from a feasibility study assessing the tool's effectiveness. Initial feedback on the user experience suggests a positive reception towards the agent's usability, highlighting its potential to enhance patient engagement in a clinical setting.

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., (© 2022. The Author(s).)

Purpose/objectives: This study proposes the utilization of a Natural Language Processing tool to create a semantic search engine for dental education while addressing the increasing concerns of accuracy, bias, and hallucination in outputs generated by AI tools. The paper focuses on developing and evaluating DentQA, a specialized question‐answering tool that makes it easy for students to seek information to access information located in handouts or study material distributed by an institution. Methods: DentQA is structured upon the GPT3.5 language model, utilizing prompt engineering to extract information from external dental documents that experts have verified. Evaluation involves non‐human metrics (BLEU scores) and human metrics for the tool's performance, relevance, accuracy, and functionality. Results: Non‐human metrics confirm DentQA's linguistic proficiency, achieving a Unigram BLEU score of 0.85. Human metrics reveal DentQA's superiority over GPT3.5 in terms of accuracy (p = 0.00004) and absence of hallucination (p = 0.026). Additional metrics confirmed consistent performance across different question types (X2 (4, N = 200) = 13.0378, p = 0.012). User satisfaction and performance metrics support DentQA's usability and effectiveness, with a response time of 3.5 s and over 70% satisfaction across all evaluated parameters. Conclusions: The study advocates using a semantic search engine in dental education, mitigating concerns of misinformation and hallucination. By outlining the workflow and the utilization of open‐source tools and methods, the study encourages the utilization of similar tools for dental education while underscoring the importance of customizing AI models for dentistry. Further optimizations, testing, and utilization of recent advances can contribute to dental education significantly. [ABSTRACT FROM AUTHOR]

Artificial Intelligence (AI) technologies have increasingly become vital in our everyday lives. Education is one of the most visible domains in which these technologies are being used. Conversational Agents (CAs) are among the most prominent AI systems for assisting teaching and learning processes. Their integration into an e-learning system can provide replies suited to each learner's specific needs, allowing them to study at their own pace. In this paper, based on recent advancements in Natural Language Processing (NLP) and deep learning techniques, we present an experimental implementation of an educational chatbot intended to instruct secondary school learners Logo, an educational programming language. The related chatbot was implemented and evaluated in Moroccan public schools with the support of teachers from the Regional Center for Education and Training Professions of Souss Massa. The experiments included 109 students grouped into three separate classes. One is a control class group that uses a traditional approach, while the other two are experimental groups that employ digital content and the chatbot-based method. Preliminary findings indicate that employing chatbots can greatly enhance student learning experiences by allowing them to study at their own speed with less stress, saving them time, and keeping them motivated. Furthermore, integrating these AI systems into a smart classroom will not only create a supportive environment by encouraging good interactions with students, it will also allow learners to be more engaged and achieve better academic objectives. [ABSTRACT FROM AUTHOR]

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.

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 < 0.01); the anxiety subsample had significant reductions in anxiety symptoms at Week 8 (mean change = -7.45, SD = 5.99, Cohen's d = -1.24, p < 0.01). No significant associations were found between sex at birth, age, employment status, educational background and Week 8 symptom changes. Significant associations between depressive and anxiety symptom outcomes and sexual orientation, marital status, concurrent mental health treatment, and baseline symptom severity were found. Conclusions: The present study suggests early promise for W-MA-02 as an intervention for depression and/or anxiety symptoms. Although exploratory in nature, this study revealed potential user characteristics associated with outcomes that can be investigated in future studies. Trial Registration: This study was retrospectively registered on ClinicalTrials.gov (#NCT05672745) on January 5th, 2023. [ABSTRACT FROM AUTHOR]

Conversational agents (CA) are software programs that can converse with users using natural language. They are now widely used in various domains, such as tourism, healthcare, and others, to perform tasks and provide permanent assistance to users by interacting with them in natural language. The development of such applications is a task that requires expertise in several fields, such as software engineering, machine learning, deep learning, and natural language processing (NLP). However, several platforms and frameworks on the market facilitate the building of CA, such as Dialogflow, Rasa, and others. Recently, several research studies have proposed solutions to reduce the workload of developers and designers by offering their model-driven development approaches using domain-specific languages (DSLs), which facilitate the automation of the development of CA. This work aims to provide an Overview of CA to identify and describe their architecture and the details of its key components. and discuss the tools and technologies for their development. At the same time, discover the research topics that focus on using DSLs for model-driven development to automate and speed up the creation of these agents and discover approaches and technologies employed to implement each of these DSLs. [ABSTRACT FROM AUTHOR]

Intelligent learning systems provide relevant learning materials to students based on their individual pedagogical needs and preferences. However, providing personalized learning objects based on learners’ preferences, such as learning styles which are particularly important for the recommendation of learning objects, re-mains a challenge. Recommending the most appropriate learning objects for learners has always been a challenge in the field of e-learning. This challenge has driven educators and researchers to implement new ideas to help learners improve their learning experience and knowledge. New solutions use artificial intelligence (AI) techniques such as machine learning (ML) and natural language processing (NLP). In this paper, we propose and develop a new personalization approach for recommendation that implements the adaptation of learning objects according to the learners’ learning style mainly focused on the use of a chatbot, named LearningPartnerBot, which will be integrated into the Moodle platform. We use the Felder-Silverman Learning Styles Model to determine learners’ learning styles in order to recommend learning objects, and also to overcome the cold start problem. A chatbot is an automated communication tool that attempts to imitate a conversation by detecting the intentions of its user. The proposed LearningPartnerBot should be able to answer learners’ questions in real time and provide a relevant set of suggestions according to their needs. [ABSTRACT FROM AUTHOR]

Featured Application: The chatbot developed in this study can be used by human milk banks in the process of breastfeeding education and recruitment of mothers to donate human milk. 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 FROM AUTHOR]

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 throughmulti-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. [ABSTRACT FROM AUTHOR]

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. [ABSTRACT FROM AUTHOR]

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.

Pregnant women constantly need some information to support nutritional decisions during pregnancy, and many do not receive such assistance at all. This study aims to present a conversational agent to provide reliable information to pregnant women, focusing on nutritional education and evaluating the perception of pregnant women and health professionals about the agent. As a scientific contribution, this article developed and implemented a conversational agent in a real environment capable of generating reliable responses on the basis of a set of health documents. We proposed an intervention study with 25 women and 10 healthcare providers through a survey to measure the perceptions of these groups towards conversational agents. The results show that the intended design could ensure positive support for pregnant women, clarify certain issues for the public, and remove some knowledge barriers. The results showed no significant difference between the groups (p-value = 0.713). Depending on the perception of the pregnant group, the conversational agent model can teach new knowledge during the prenatal period (Mean = 4.56). The model presented for health professionals could already be indicated as a support tool for pregnant women (Mean = 4.7). [ABSTRACT FROM AUTHOR]

Background: Chat Generative Pre-trained Transformer (ChatGPT) is a 175-billion-parameter natural language processing model that can generate conversation-style responses to user input. Objective: This study aimed to evaluate the performance of ChatGPT on questions within the scope of the United States Medical Licensing Examination Step 1 and Step 2 exams, as well as to analyze responses for user interpretability. Methods: We used 2 sets of multiple-choice questions to evaluate ChatGPT's performance, each with questions pertaining to Step 1 and Step 2. The first set was derived from AMBOSS, a commonly used question bank for medical students, which also provides statistics on question difficulty and the performance on an exam relative to the user base. The second set was the National Board of Medical Examiners (NBME) free 120 questions. ChatGPT's performance was compared to 2 other large language models, GPT-3 and InstructGPT. The text output of each ChatGPT response was evaluated across 3 qualitative metrics: logical justification of the answer selected, presence of information internal to the question, and presence of information external to the question. Results: Of the 4 data sets, AMBOSS-Step1, AMBOSS-Step2, NBME-Free-Step1, and NBME-Free-Step2, ChatGPT achieved accuracies of 44% (44/100), 42% (42/100), 64.4% (56/87), and 57.8% (59/102), respectively. ChatGPT outperformed InstructGPT by 8.15% on average across all data sets, and GPT-3 performed similarly to random chance. The model demonstrated a significant decrease in performance as question difficulty increased (P=.01) within the AMBOSS-Step1 data set. We found that logical justification for ChatGPT's answer selection was present in 100% of outputs of the NBME data sets. Internal information to the question was present in 96.8% (183/189) of all questions. The presence of information external to the question was 44.5% and 27% lower for incorrect answers relative to correct answers on the NBME-Free-Step1 (P<.001) and NBME-Free-Step2 (P=.001) data sets, respectively. Conclusions: ChatGPT marks a significant improvement in natural language processing models on the tasks of medical question answering. By performing at a greater than 60% threshold on the NBME-Free-Step-1 data set, we show that the model achieves the equivalent of a passing score for a third-year medical student. Additionally, we highlight ChatGPT's capacity to provide logic and informational context across the majority of answers. These facts taken together make a compelling case for the potential applications of ChatGPT as an interactive medical education tool to support learning. [ABSTRACT FROM AUTHOR]

Background: The COVID-19 pandemic raised novel challenges in communicating reliable, continually changing health information to a broad and sometimes skeptical public, particularly around COVID-19 vaccines, which, despite being comprehensively studied, were the subject of viral misinformation. Chatbots are a promising technology to reach and engage populations during the pandemic. To inform and communicate effectively with users, chatbots must be highly usable and credible. Objective: We sought to understand how young adults and health workers in the United States assessed the usability and credibility of a web-based chatbot called Vira, created by the Johns Hopkins Bloomberg School of Public Health and IBM Research using natural language processing technology. Using a mixed method approach, we sought to rapidly improve Vira's user experience to support vaccine decision-making during the peak of the COVID-19 pandemic. Methods: We recruited racially and ethnically diverse young people and health workers, with both groups from urban areas of the United States. We used the validated Chatbot Usability Questionnaire to understand the tool's navigation, precision, and persona. We also conducted 11 interviews with health workers and young people to understand the user experience, whether they perceived the chatbot as confidential and trustworthy, and how they would use the chatbot. We coded and categorized emerging themes to understand the determining factors for participants' assessment of chatbot usability and credibility. Results: In all, 58 participants completed a web-based usability questionnaire and 11 completed in-depth interviews. Most questionnaire respondents said the chatbot was "easy to navigate" (51/58, 88%) and "very easy to use" (50/58, 86%), and many (45/58, 78%) said its responses were relevant. The mean Chatbot Usability Questionnaire score was 70.2 (SD 12.1) and scores ranged from 40.6 to 95.3. Interview participants felt the chatbot achieved high usability due to its strong functionality, performance, and perceived confidentiality and that the chatbot could attain high credibility with a redesign of its cartoonish visual persona. Young people said they would use the chatbot to discuss vaccination with hesitant friends or family members, whereas health workers used or anticipated using the chatbot to support community outreach, save time, and stay up to date. Conclusions: This formative study conducted during the pandemic's peak provided user feedback for an iterative redesign of Vira. Using a mixed method approach provided multidimensional feedback, identifying how the chatbot worked well--being easy to use, answering questions appropriately, and using credible branding--while offering tangible steps to improve the product's visual design. Future studies should evaluate how chatbots support personal health decision-making, particularly in the context of a public health emergency, and whether such outreach tools can reduce staff burnout. Randomized studies should also be conducted to measure how chatbots countering health misinformation affect user knowledge, attitudes, and behavior. [ABSTRACT FROM AUTHOR]

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. [ABSTRACT FROM AUTHOR]

Conversational Intelligent Tutoring Systems (CITS) have drawn increasing interest in education because of their capacity to tailor learning experiences, improve user engagement, and contribute to the effective transfer of knowledge. Conversational agents employ advanced natural language techniques to engage in a convincing human-like tutorial conversation. In solving math word problems, a significant challenge arises in enabling the system to understand user utterances and accurately map extracted entities to the essential problem quantities required for problem-solving, despite the inherent ambiguity of human natural language. In this study, we propose two possible approaches to enhance the performance of a particular CITS designed to teach learners to solve arithmetic–algebraic word problems. Firstly, we propose an ensemble approach to intent classification and entity extraction, which combines the predictions made by two distinct individual models that use constraints defined by human experts. This approach leverages the intertwined nature of the intents and entities to yield a comprehensive understanding of the user's utterance, ultimately aiming to enhance semantic accuracy. Secondly, we introduce an adapted Term Frequency-Inverse Document Frequency technique to associate entities with problem quantity descriptions. The evaluation was conducted on the AWPS and MATH-HINTS datasets, containing conversational data and a collection of arithmetical and algebraic math problems, respectively. The results demonstrate that the proposed ensemble approach outperforms individual models, and the proposed method for entity–quantity matching surpasses the performance of typical text semantic embedding models. • Methods to enhance NLU models and entity–quantity matching are proposed. • Enhance semantic accuracy by detecting entity–intent inconsistencies. • Improving NLU relies on a crafted set of rules and an ensemble model. • An adapted TF-IDF approach is used for entity–quantity matching. • A comprehensive evaluation with our datasets shows the advantages of the approaches. [ABSTRACT FROM AUTHOR]

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.

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.

Copyright of 3C Tecnologia is the property of Area de Innovacion y Desarrollo, SL and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

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.

Within the anamnesis, medical information is frequently withheld, incomplete, or incorrect, potentially causing negative consequences for the patient. The use of conversational agents (CAs), computer-based systems using natural language to interact with humans, may mitigate this problem. The present research examines whether CAs differ from physicians in their ability to elicit truthful disclosure and discourage concealment of medical information. We conducted an online questionnaire with German participants (N = 148) to assess their willingness to reveal medical information. The results indicate that patients would rather disclose medical information to a physician than to a CA; there was no difference in the tendency to conceal information. This research offers a frame of reference for future research on applying CAs during the anamnesis to support physicians. From a practical view, physicians might gain better understanding of how the use of CAs can facilitate the anamnesis. [ABSTRACT FROM AUTHOR]

We propose a new approach towards emotional natural language generation using bidirectional seq2seq model. Our goal is to generate emotionally relevant language that accommodates the emotional tone of the prior context. To incorporate emotional information, we train our own embeddings appended with emotion values through valence, arousal and dominance scores. We use a reinforcement-learning framework, which is tuned using policy gradient method. Two of the internal rewards in our reinforcement learning framework, viz. Ease of Answering and Semantic Coherence are based on prior state-of-the-art. We propose a new internal reward, Emotional Intelligence, computed by minimizing the affective dissonance between the source and generated text. We also train a separate external reward analyzer to predict the rewards as well as to maximize the expected rewards (both internal and external). We evaluate the system on two common corpora used for Natural Language Generation tasks: the Cornell Movie Dialog and Yelp Restaurant Review Corpus. We report standard evaluation metrics including BLEU, ROUGE-L and perplexity as well as human evaluation to validate our approach. We demonstrate the ability of proposed model to generate emotionally appropriate responses on both corpora. [ABSTRACT FROM AUTHOR]

Copyright of Revista de Ciencia y Tecnología is the property of Revista de Ciencia y Tecnologia and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

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. [ABSTRACT FROM AUTHOR]

Due to the advance of indoor positioning technology, it is now possible to trace mobile medical equipment (such as electrocardiography machines, patient monitors, and so on) being moved around a hospital ward. With the support of an object tracking system, nurses can easily locate and find a device, especially when they prepare for a shift change or a medical treatment. As nurses usually face high workloads, it is highly desirable to provide nurses with a user-friendly search interface integrated into a popular mobile app that they use daily. For this, DBOS, a dialog-based object query system, is proposed, which simulates a real conversation with users via the Line messaging app’s chatbot interface. A hybrid method that combines cosine similarity (CS) and term frequency–inverse document frequency (TF-IDF) is used to determine user intent. The result is returned to the user through Line’s interface. To evaluate the applicability of DBOS, 70 search queries given by a head nurse were tested. DBOS was compared with CS, TF-IDF, and Facebook Wit.ai respectively. The experiment results show that DBOS outperforms the abovementioned methods and can achieve a 92.8% accuracy in identifying user intent.

Conversational Agents, or more commonly known as chatbots have been well-accepted in most enterprises. Chatbots have been widely used in major enterprises to perform the main purpose of customer service in delivering routine and frequently asked questions on behalf of humans. Bearing the goal to create believable conversational agents in providing accurate, reliable and up-to-date information, researchers have practiced natural language processing, machine learning, and deep learning in chatbot creation. In order to create a chatbot which is indistinguishable from human, many researchers have attempted to create human-like chatbots by neglecting the necessity to evaluate the general knowledge of the chatbot before proceeding into the creation of domain-specific knowledge. This paper presents the black-box approach to evaluate the response quality of a developed conversational agent named Tarie through datasets obtained from Loebner Prize Competition. The black-box approach is therefore deemed necessary to be used as the evaluation approach to evaluate the response quality of the conversational agent. The intelligence of the chatbot denotes the correct answers given to the user's queries. The results obtained via the black-box approach is further deduced to indicate whether the chatbot is ready for the domain-specific knowledge creation or to further improve its current general knowledge. This paper presents the black-box approach to evaluate the response quality of a proposed conversational agent named Tarie through datasets obtained from Loebner Prize Competition. [ABSTRACT FROM AUTHOR]

Children have been increasingly becoming active users of the Internet and, although any segment of the population is susceptible to falling victim to the existing risks, they in particular are one of the most vulnerable. Thus, some of the major scourges of this cyber society are paedophile behaviours on the Internet, child pornography or sexual exploitation of children. In light of this background, Negobot is a conversational agent posing as a child, in chats, social networks and other channels suffering from paedophile behaviour. As a conversational agent, Negobot, has a strong technical base of Natural Language Processing and information retrieval, as well as Artificial Intelligence and Machine Learning. However, the most innovative proposal of Negobot is to consider the conversation itself as a game, applying game theory. In this context, Negobot proposes, first, a competitive game in which the system identifies the best strategies for achieving its goal, to obtain information that leads us to infer if the subject involved in a conversation with the agent has paedophile tendencies, while our actions do not bring the alleged offender to leave the conversation due to a suspicious behaviour of the agent. [ABSTRACT FROM AUTHOR]

Background: Automated conversational agents, or chatbots, have a role in reinforcing evidence-based guidance delivered through other media and offer an accessible, individually tailored channel for public engagement. In early-to-mid-2021, young adults and minority populations disproportionately affected by COVID-19 in the U.S. were more likely to be hesitant toward COVID-19 vaccines, citing concerns regarding vaccine safety and effectiveness. Successful chatbot communication requires purposive understanding of user needs.Objective: We sought to review the acceptability of messages to be delivered by a chatbot named VIRA from Johns Hopkins University. The study investigated which message styles were preferred by young, urban-dwelling Americans as well as public health workers, since we anticipated the chatbot would be used by the latter as a job aid.Methods: We conducted four virtual focus groups with 20 racially and ethnically diverse young adults 18-28 and public health workers 25-61 years old living in or near eastern U.S. cities. We tested six message styles, asking participants to select a preferred response style for a chatbot answering common questions about COVID-19 vaccines. We transcribed, coded, and categorized emerging themes within discussions of message content, style, and framing.Results: Participants preferred messages that began with an empathetic reflection of a user concern and concluded with a straightforward, fact-supported response. Most participants disliked moralistic or reasoning-based appeals to get vaccinated, although public health workers felt such strong statements appealing to communal responsibility were warranted. Responses tested with humor and testimonials did not appeal.Conclusions: To foster credibility, chatbots targeting young people with vaccine-related messaging should aim to build rapport with users by deploying empathic, reflective statements, followed by direct and comprehensive responses to user queries. Further studies are needed to inform the appropriate utilization of user-tailored testimonials and humor in the context of chatbot communication.Clinicaltrial: [ABSTRACT FROM AUTHOR]