Search

Socially assistive robotics (SAR) aims at designing robots capable of guaranteeing social interaction to human users in a variety of assistance scenarios that range, e.g., from giving reminders for medications to monitoring of Activity of Daily Living, from giving advices to promote an healthy lifestyle to psychological monitoring. Among possible users, frail older adults deserve a special focus as they present a rich variability in terms of both alternative possible assistive scenarios (e.g., hospital or domestic environments) and caring needs that could change over time according to their health conditions. In this perspective, robot behaviors should be customized according to properly designed user models. One of the long-term research goals for SAR is the realization of robots capable of, on the one hand, personalizing assistance according to different health-related conditions/states of users and, on the other, adapting behaviors according to heterogeneous contexts as well as changing/evolving needs of users. This work proposes a solution based on a user model grounded on the international classification of functioning, disability and health (ICF) and a novel control architecture inspired by the dual-process theory. The proposed approach is general and can be deployed in many different scenarios. In this paper, we focus on a social robot in charge of the synthesis of personalized training sessions for the cognitive stimulation of older adults, customizing the adaptive verbal behavior according to the characteristics of the users and to their dynamic reactions when interacting. Evaluations with a restricted number of users show good usability of the system, a general positive attitude of users and the ability of the system to capture users personality so as to adapt the content accordingly during the verbal interaction. [ABSTRACT FROM AUTHOR]

The widespread use of temporal aspects in user modeling indicates their importance, and their consideration showed to be highly effective in various domains related to user modeling, especially in recommender systems. Still, past and ongoing research, spread over several decades, provided multiple ad-hoc solutions, but no common understanding of the issue. There is no standardization and there is often little commonality in considering temporal aspects in different applications. This may ultimately lead to the problem that application developers define ad-hoc solutions for their problems at hand, sometimes missing or neglecting aspects that proved to be effective in similar cases. Therefore, a comprehensive survey of the consideration of temporal aspects in recommender systems is required. In this work, we provide an overview of various time-related aspects, categorize existing research, present a temporal abstraction and point to gaps that require future research. We anticipate this survey will become a reference point for researchers and practitioners alike when considering the potential application of temporal aspects in their personalized applications. [ABSTRACT FROM AUTHOR]

Although privacy settings are important not only for data privacy, but also to prevent hacking attacks like social engineering that depend on leaked private data, most users do not care about them. Research has tried to help users in setting their privacy settings by using some settings that have already been adapted by the user or individual factors like personality to predict the remaining settings. But in some cases, neither is available. However, the user might have already done privacy settings in another domain, for example, she already adapted the privacy settings on the smartphone, but not on her social network account. In this article, we investigate with the example of four domains (social network posts, location sharing, smartphone app permission settings and data of an intelligent retail store), whether and how precise privacy settings of a domain can be predicted across domains. We performed an exploratory study to examine which privacy settings of the aforementioned domains could be useful, and validated our findings in a validation study. Our results indicate that such an approach works with a prediction precision about 15%–20% better than random and a prediction without input coefficients. We identified clusters of domains that allow model transfer between their members, and discuss which kind of privacy settings (general or context-based) leads to a better prediction accuracy. Based on the results, we would like to conduct user studies to find out whether the prediction precision is perceived by users as a significant improvement over a "one-size-fits-all" solution, where every user is given the same privacy settings. [ABSTRACT FROM AUTHOR]

Gamification has been discussed as a standout approach to improve user experience, with different studies showing that users can have different preferences over game elements according to their user types. However, relatively less is known how different kinds of users may react to different types of gamification. Therefore, in this study ( N = 331 ) we investigate how user orientation (Achiever, Disruptor, Free Spirit, Philanthropist, Player, and Socializer) is associated with the preference for and perceived sense of accomplishment from different gamification designs. Beyond singular associations between the user orientation and the gamification designs, the findings indicate no comprehensive and consistent patterns of associations. From the six user orientations, five presented significant associations: Socializer orientation was positively associated with Social, Fictional, and Personal designs, while negatively associated with Performance design; Player orientation was positively associated with Social (Accomplishment), Personal, and Ecological designs, while negatively associated with the Social design (Preference); Disruptor orientation was positively associated with Social design; Achiever orientation was positively associated with Performance and Social designs; and Free Spirit orientation was negatively associated with Social design. Based on the results, we provide recommendations on how to personalize gamified systems and set further research trajectories on personalized gamification. [ABSTRACT FROM AUTHOR]

In this study, we attempt to specify the cognitive support behavior of a previously designed embodied conversational agent coach that provides learning support to low-literates. Three knowledge gaps are identified in the existing work: an incomplete specification of the behaviors that make up 'support,' an incomplete specification of how this support can be personalized, and unclear speech recognition rules. We use the socio-cognitive engineering method to update our foundation of knowledge with new online banking exercises, low-level scaffolding and user modeling theory, and speech recognition. We then refine the design of our coach agent by creating comprehensive cognitive support rules that adapt support based on learner needs (the 'Generalized' approach) and attune the coach's support delay to user performance in previous exercises (the 'Individualized' approach). A prototype is evaluated in a 3-week within- and between-subjects experiment. Results show that the specified cognitive support is effective: Learners complete all exercises, interact meaningfully with the coach, and improve their online banking self-efficacy. Counter to hypotheses, the Individualized approach does not improve on the Generalized approach. Whether this indicates suboptimal operationalization or a deeper problem with the Individualized approach remains as future work. [ABSTRACT FROM AUTHOR]

In this article, we present a platform that allows the creation of a comprehensive representation of the user that we call a holistic user model (HUM). Such a representation is based on the intuition that users' personal data take different forms and come from several heterogeneous sources. Accordingly, we designed a pipeline that: (1) extracts personal data from three examples of important classes of such sources, namely social networks, wearable devices and smartphones; (2) processes these data through natural language processing and machine learning techniques; (3) stores the output of such processing in a user model that encodes different aspects of people's life, such as demographic data, interests, affect values, social relations, activities and physical states. The resulting representation is made available to the user and to external developers. In the first case, a web interface allows the user to browse through her own personal data and to consult different facets of her HUM, in order to improve her self-awareness. In the latter, holistic user profiles are exposed through a REST interface and can be exploited by third-party applications to provide personalized services based on HUMs. In the experimental session, we evaluated usability and acceptability of the HUM in a user study which investigated how people were willing to use it. The results confirmed the effectiveness of our design choices and built the foundations for future usage of these profiles in personalized applications. [ABSTRACT FROM AUTHOR]

Previous research has shown that various user characteristics (e.g., cognitive abilities, personality traits, and learning abilities) can influence user experience during information visualization tasks. These findings have prompted researchers to investigate user-adaptive information visualizations that can help users by providing personalized support based on their specific needs. Whereas existing work has been mostly limited to tasks involving just visualizations, the aim of our research is to broaden this work to include scenarios where users process textual documents with embedded visualizations, i.e., Magazine Style Narrative Visualizations, or MSNVs for short. In this paper, we analyze eye tracking data collected from a user study with MSNVs to uncover processing behaviors that are negatively impacting user experience (i.e., time on task) for users with low abilities in these user characteristics. Our analysis leverages Linear Mixed-Effects Models to evaluate the relationships among user characteristics, gaze processing behaviors, and task performance. Our results identify several MSNV processing behaviors within the visualization that contribute to poor task performance for users with low reading proficiency. For instance, we identify that users with low reading proficiency transition significantly more often compared to their counterparts between relevant and non-relevant bars, and transition more often from bars to the labels. We present our findings as a step toward designing user-adaptive support mechanisms to alleviate these difficulties with MSNVs, and provide suggestions on how our results can be leveraged for creating a set of meaningful interventions for future evaluation (e.g., dynamically highlighting relevant bars and labels in the visualization to help users with low reading proficiency locate them more effectively). [ABSTRACT FROM AUTHOR]

Although abundant research work has been published in the area of path recommendation and its applications on travel and routing topics, scarce work has been reported on context-aware route recommendation systems aimed to stimulate optimal cultural heritage experiences. This paper tries to address this issue, by proposing a personalized and content adaptive cultural heritage path recommendation system, where location is modeled using mean-shift clustering trained with actual user movement patters. Additionally, topic modeling is incorporated to formalize the implicit cultural heritage content, while first order Markov models address the movement as a temporal transition aspect of the problem. The overall architecture is applied on data collected from actual visits to the archaeological sites of Gournia and Çatalhöyük and extensive analysis on visitor movement patterns follows, especially in comparison to the curated paths in the aforementioned sites. Finally, the offline evaluation results of the proposed recommendation scheme are encouraging, validating its efficiency and setting a positive paradigm for cultural heritage route recommendations. [ABSTRACT FROM AUTHOR]

With the growing popularity of microblogging services such as Twitter in recent years, an increasing number of users are using these services in their daily lives. The huge volume of information generated by users raises new opportunities in various applications and areas. Inferring user interests plays a significant role in providing personalized recommendations on microblogging services, and also on third-party applications providing social logins via these services, especially in cold-start situations. In this survey, we review user modeling strategies with respect to inferring user interests from previous studies. To this end, we focus on four dimensions of inferring user interest profiles: (1) data collection, (2) representation of user interest profiles, (3) construction and enhancement of user interest profiles, and (4) the evaluation of the constructed profiles. Through this survey, we aim to provide an overview of state-of-the-art user modeling strategies for inferring user interest profiles on microblogging social networks with respect to the four dimensions. For each dimension, we review and summarize previous studies based on specified criteria. Finally, we discuss some challenges and opportunities for future work in this research domain. [ABSTRACT FROM AUTHOR]

Confident usage of information visualizations is thought to be influenced by cognitive aspects as well as amount of exposure and training. To support the development of individual competency in visualization processing, it is important to ascertain if we can track users' progress or difficulties they might have while working with a given visualization. In this paper, we extend previous work on predicting in real time a user's learning curve-a mathematical model that can represent a user's skill acquisition ability-when working with a visualization. First, we investigate whether results we previously obtained in predicting users' learning curves during visualization processing generalize to a different visualization. Second, we study to what extent we can make predictions on a user's learning curve without information on the visualization being used. Our models leverage various data sources, including a user's gaze behavior, pupil dilation, and cognitive abilities. We show that these models outperform a baseline that leverages knowledge on user task performance so far. Our best performing model achieves good accuracies in predicting users' learning curves even after observing users' performance on a few tasks only. These results represent an important step toward understanding how to support users in learning a new visualization. [ABSTRACT FROM AUTHOR]

Mind wandering is a ubiquitous phenomenon where attention involuntarily shifts from task-related thoughts to internal task-unrelated thoughts. Mind wandering can have negative effects on performance; hence, intelligent interfaces that detect mind wandering can improve performance by intervening and restoring attention to the current task. We investigated the use of eye gaze and contextual cues to automatically detect mind wandering during reading with a computer interface. Participants were pseudorandomly probed to report mind wandering while an eye tracker recorded their gaze during the reading task. Supervised machine learning techniques detected positive responses to mind wandering probes from eye gaze and context features in a user-independent fashion. Mind wandering was detected with an accuracy of 72 % (expected accuracy by chance was 60 %) when probed at the end of a page and an accuracy of 67 % (chance was 59 %) when probed in the midst of reading a page. Global gaze features (gaze patterns independent of content, such as fixation durations) were more effective than content-specific local gaze features. An analysis of the features revealed diagnostic patterns of eye gaze behavior during mind wandering: (1) certain types of fixations were longer; (2) reading times were longer than expected; (3) more words were skipped; and (4) there was a larger variability in pupil diameter. Finally, the automatically detected mind wandering rate correlated negatively with measures of learning and transfer even after controlling for prior knowledge, thereby providing evidence of predictive validity. Possible improvements to the detector and applications that utilize the detector are discussed. [ABSTRACT FROM AUTHOR]

In order to adapt functionality to their individual users, systems need information about these users. The Social Web provides opportunities to gather user data from outside the system itself. Aggregated user data may be useful to address cold-start problems as well as sparse user profiles, but this depends on the nature of individual user profiles distributed on the Social Web. For example, does it make sense to re-use Flickr profiles to recommend bookmarks in Delicious? In this article, we study distributed form-based and tag-based user profiles, based on a large dataset aggregated from the Social Web. We analyze the completeness, consistency and replication of form-based profiles, which users explicitly create by filling out forms at Social Web systems such as Twitter, Facebook and LinkedIn. We also investigate tag-based profiles, which result from social tagging activities in systems such as Flickr, Delicious and StumbleUpon: to what extent do tag-based profiles overlap between different systems, what are the benefits of aggregating tag-based profiles. Based on these insights, we developed and evaluated the performance of several cross-system user modeling strategies in the context of recommender systems. The evaluation results show that the proposed methods solve the cold-start problem and improve recommendation quality significantly, even beyond the cold-start. [ABSTRACT FROM AUTHOR]

Reconciling personalization with privacy has been a continuing interest in user modeling research. This aim has computational, legal and behavioral/attitudinal ramifications. We present a dynamic privacy-enhancing user modeling framework that supports compliance with users' individual privacy preferences and with the privacy laws and regulations that apply to each user. The framework is based on a software product line architecture. It dynamically selects personalization methods during runtime that meet the current privacy constraints. Since dynamic architectural reconfiguration is typically resource-intensive, we conducted a performance evaluation with four implementations of our system that vary two factors. The results demonstrate that at least one implementation of our approach is technically feasible with comparatively modest additional resources, even for websites with the highest traffic today. To gauge user reactions to privacy controls that our framework enables, we also conducted a controlled experiment that allowed one group of users to specify privacy preferences and view the resulting effects on employed personalization methods. We found that users in this treatment group utilized this feature, deemed it useful, and had fewer privacy concerns as measured by higher disclosure of their personal data. [ABSTRACT FROM AUTHOR]

User goals are of major importance for an interface agent because they serve as a context to define what the user's focus of attention is at a given moment. The user's goals should be detected as soon as possible, after observing few user actions, in order to provide the user with timely assistance. In this article, we describe an approach for modeling and recognizing user goals from observed sequences of user actions by using Variable Order Markov models combined with an exponential moving average (EMA) on the prediction probabilities. The validity of our approach has been tested using data collected from real users in the Unix domain. The results obtained show that an interface agent can achieve near 90% average accuracy and over 58% online accuracy in predicting the most probable user goal after each observed action, in a time linear to the number of goals being modeled. We also found that the use of an EMA allows a faster convergence in the actual user goal. [ABSTRACT FROM AUTHOR]

The emotional power of music is exploited in a personalized affective music player (AMP) that selects music for mood enhancement. A biosignal approach is used to measure listeners' personal emotional reactions to their own music as input for affective user models. Regression and kernel density estimation are applied to model the physiological changes the music elicits. Using these models, personalized music selections based on an affective goal state can be made. The AMP was validated in real-world trials over the course of several weeks. Results show that our models can cope with noisy situations and handle large inter-individual differences in the music domain. The AMP augments music listening where its techniques enable automated affect guidance. Our approach provides valuable insights for affective computing and user modeling, for which the AMP is a suitable carrier application. [ABSTRACT FROM AUTHOR]

Nowadays a large number of user-adaptive systems has been developed. Commonly, the effort to build user models is repeated across applications and domains, due to the lack of interoperability and synchronization among user-adaptive systems. There is a strong need for the next generation of user models to be interoperable, i.e. to be able to exchange user model portions and to use the information that has been exchanged to enrich the user experience. This paper presents an overview of the well-established literature dealing with user model interoperability, discussing the most representative work which has provided valuable solutions to face interoperability issues. Based on a detailed decomposition and a deep analysis of the selected work, we have isolated a set of dimensions characterizing the user model interoperability process along which the work has been classified. Starting from this analysis, the paper presents some open issues and possible future deployments in the area. [ABSTRACT FROM AUTHOR]

Monitoring and interpreting sequential learner activities has the potential to improve adaptivity and personalization within educational environments. We present an approach based on the modeling of learners' problem solving activity sequences, and on the use of the models in targeted, and ultimately automated clustering, resulting in the discovery of new, semantically meaningful information about the learners. The approach is applicable at different levels: to detect pre-defined, well-established problem solving styles, to identify problem solving styles by analyzing learner behaviour along known learning dimensions, and to semi-automatically discover learning dimensions and concrete problem solving patterns. This article describes the approach itself, demonstrates the feasibility of applying it on real-world data, and discusses aspects of the approach that can be adjusted for different learning contexts. Finally, we address the incorporation of the proposed approach in the adaptation cycle, from data acquisition to adaptive system interventions in the interaction process. [ABSTRACT FROM AUTHOR]

Computer users have different levels of system skills. Moreover, each user has different levels of skill across different applications and even in different portions of the same application. Additionally, users’ skill levels change dynamically as users gain more experience in a user interface. In order to adapt user interfaces to the different needs of user groups with different levels of skills, automatic methods of skill detection are required. In this paper, we present our experiments and methods, which are used to build automatic skill classifiers for desktop applications. Machine learning algorithms were used to build statistical predictive models of skill. Attribute values were extracted from high frequency user interface events, such as mouse motions and menu interactions, and were used as inputs to our models. We have built both task-independent and task-dependent classifiers with promising results. [ABSTRACT FROM AUTHOR]

With many daily tasks now performed on the Internet, productivity and efficiency in working with web pages have become transversal necessities for all users. Many of these tasks involve the inputting of user information, obligating the user to interact with a webform. Research has demonstrated that productivity depends largely on users’ personal characteristics, implying that it will vary from user to user. The webform development process must therefore, include modeling of its intended users to ensure the interface design is appropriate. Taking all potential users into account is difficult, however, primarily because their identity is unknown, and some may be effectively excluded by the final design. Such discrimination can be avoided by incorporating rules that allow webforms to adapt automatically to the individual user’s characteristics, the principal one being the person’s culture. In this paper we report two studies that validate this option. We begin by determining the relationships between a user’s cultural dimension scores and their behavior when faced with a webform. We then validate the notion that rules based on these relationships can be established for the automatic adaptation of a webform in order to reduce the time taken to complete it. We conclude that the automatic webform adaptation to the cultural dimensions of users improves their performance. [ABSTRACT FROM AUTHOR]

We present a probabilistic model of user affect designed to allow an intelligent agent to recognise multiple user emotions during the interaction with an educational computer game. Our model is based on a probabilistic framework that deals with the high level of uncertainty involved in recognizing a variety of user emotions by combining in a Dynamic Bayesian Network information on both the causes and effects of emotional reactions. The part of the framework that reasons from causes to emotions ( diagnostic model) implements a theoretical model of affect, the OCC model, which accounts for how emotions are caused by one’s appraisal of the current context in terms of one’s goals and preferences. The advantage of using the OCC model is that it provides an affective agent with explicit information not only on which emotions a user feels but also why, thus increasing the agent’s capability to effectively respond to the users’ emotions. The challenge is that building the model requires having mechanisms to assess user goals and how the environment fits them, a form of plan recognition. In this paper, we illustrate how we built the predictive part of the affective model by combining general theories with empirical studies to adapt the theories to our target application domain. We then present results on the model’s accuracy, showing that the model achieves good accuracy on several of the target emotions. We also discuss the model’s limitations, to open the ground for the next stage of the work, i.e., complementing the model with diagnostic information. [ABSTRACT FROM AUTHOR]

Personalization is considered a powerful methodology for improving the effectiveness of information search and decision making. It has led to the dissemination of systems capable of suggesting relevant and personalized information (or items) to the users, according to their characteristics and preferences, as represented by a User Model (UM). Since the quality of the personalization largely depends on the size and accuracy of the managed UMs, it would be beneficial to enrich the UMs by mediating, i.e., importing and integrating, UMs built by other personalization systems. This work discusses and evaluates a cross-representation mediation of UMs from collaborative filtering to content-based recommender systems. According to this approach, a content-based recommender system, having partial or no UM data, can generate recommendations for users by mediating UM data of the same users, collected by a collaborative filtering system. The mediation process transforms the UMs from the collaborative filtering ratings to the content-based weighted item features. The mediation process exploits the item descriptions that are typically not used by the collaborative filtering recommender systems. An experimental evaluation conducted in the domain of movies shows that for users with small collaborative filtering UMs, i.e., users with few item ratings, the accuracy of the recommendations provided using the mediated content-based UMs is superior to that using the original collaborative filtering UMs. Moreover, it shows that the mediation can be used to improve a content-based recommender system by incrementally mediating collaborative filtering UM data (item ratings) and enriching the available content-based UMs. [ABSTRACT FROM AUTHOR]

Modern personalized information systems have been proven to support the user with information at the appropriate level and in the appropriate form. In specific environments like museums and exhibitions, focusing on the control of such a system is contradictory to establishing a relationship with the artifacts and exhibits. Preferably, the technology becomes invisible to the user and the physical reality becomes the interface to an additional virtual layer: by naturally moving in the space and/or manipulating physical objects in our surroundings the user will access information and operate the virtual layer. The LISTEN project is an attempt to make use of the inherent “everyday” integration of aural and visual perception, developing a tailored, immersive audio-augmented environment for the visitors of art exhibitions. The challenge of the LISTEN project is to provide a personalized immersive augmented environment, an aim which goes beyond the guiding purpose. The visitors of the museum implicitly interact with the system because the audio presentation is adapted to the users’ contexts (e.g. interests, preferences, motion, etc.), providing an intelligent audio-based environment. This article describes the realization and user evaluation of the LISTEN system focusing on the personalization component. As this system has been installed at the Kunstmuseum Bonn in the context of an exhibition comprising artworks of the painter August Macke, a detailed evaluation could be conducted. [ABSTRACT FROM AUTHOR]

We describe an Affect and Belief Adaptive Interface System (ABAIS) designed to compensate for performance biases caused by users’ affective states and active beliefs. The ABAIS architecture implements an adaptive methodology consisting of four steps: sensing/inferring user affective state and performance-relevant beliefs; identifying their potential impact on performance; selecting a compensatory strategy; and implementing this strategy in terms of specific GUI adaptations. ABAIS provides a generic adaptive framework for integrating a variety of user assessment methods (e.g. knowledge-based, self-reports, diagnostic tasks, physiological sensing), and GUI adaptation strategies (e.g. content- and format-based). The ABAIS performance bias prediction is based on empirical findings from emotion research combined with detailed knowledge of the task context. The initial ABAIS prototype was demonstrated in the context of an Air Force combat task, used a knowledge-based approach to assess the pilot’s anxiety level, and adapted to the pilot’s anxiety and belief states by modifying selected cockpit instrument displays in response to detected changes in these states. [ABSTRACT FROM AUTHOR]

An abundant amount of information is created and delivered over electronic media. Users risk becoming overwhelmed by the flow of information, and they lack adequate tools to help them manage the situation. Information filtering (IF) is one of the methods that is rapidly evolving to manage large information flows. The aim of IF is to expose users to only information that is relevant to them. Many IF systems have been developed in recent years for various application domains. Some examples of filtering applications are: filters for search results on the internet that are employed in the Internet software, personal e-mail filters based on personal profiles, listservers or newsgroups filters for groups or individuals, browser filters that block non-valuable information, filters designed to give children access them only to suitable pages, filters for e-commerce applications that address products and promotions to potential customers only, and many more. The different systems use various methods, concepts, and techniques from diverse research areas like: Information Retrieval, Artificial Intelligence, or Behavioral Science. Various systems cover different scope, have divergent functionality, and various platforms. There are many systems of widely varying philosophies, but all share the goal of automatically directing the most valuable information to users in accordance with their User Model, and of helping them use their limited reading time most optimally. This paper clarifies the difference between IF systems and related systems, such as information retrieval (IR) systems, or Extraction systems. The paper defines a framework to classify IF systems according to several parameters, and illustrates the approach with commercial and academic systems. The paper describes the underlying concepts of IF systems and the techniques that are used to implement them. It discusses methods and measurements that are used for evaluation of IF systems and limitations of the current systems. In the conclusion we present research issues in the Information Filtering research arena, such as user modeling, evaluation standardization and integration with digital libraries and Web repositories. [ABSTRACT FROM AUTHOR]

At first blush, user modeling appears to be a prime candidate for straightforward application of standard machine learning techniques. Observations of the user's behavior can provide training examples that a machine learning system can use to form a model designed to predict future actions. However, user modeling poses a number of challenges for machine learning that have hindered its application in user modeling, including: the need for large data sets; the need for labeled data; concept drift; and computational complexity. This paper examines each of these issues and reviews approaches to resolving them. [ABSTRACT FROM AUTHOR]

A fundamental objective of human–computer interaction research is to make systems more usable, more useful, and to provide users with experiences fitting their specific background knowledge and objectives. The challenge in an information-rich world is not only to make information available to people at any time, at any place, and in any form, but specifically to say the “right” thing at the “right” time in the “right” way. Designers of collaborative human–computer systems face the formidable task of writing software for millions of users (at design time) while making it work as if it were designed for each individual user (only known at use time). User modeling research has attempted to address these issues. In this article, I will first review the objectives, progress, and unfulfilled hopes that have occurred over the last ten years, and illustrate them with some interesting computational environments and their underlying conceptual frameworks. A special emphasis is given to high-functionality applications and the impact of user modeling to make them more usable, useful, and learnable. Finally, an assessment of the current state of the art followed by some future challenges is given. [ABSTRACT FROM AUTHOR]

We describe the user modeling and personalization techniques adopted in SETA, a prototype toolkit for the construction of adaptive Web stores which customize the interaction with users. The Web stores created using SETA suggest the items best fitting the customers' needs and adapt the layout and the description of the store catalog to their preferences and expertise. SETA uses stereotypical information to handle the user models and applies personalization rules to dynamically generate the hypertextual pages presenting products. The system adapts the graphical aspect, length and terminology used in the descriptions to parameters like the user's receptivity, expertise and interests. Moreover, it maintains a model associated with each person the goods are selected for; in this way, multiple criteria can be applied for tailoring the selection of items to the preferences of their beneficiaries. [ABSTRACT FROM AUTHOR]

We present a framework for adaptive news access, based on machine learning techniques specifically designed for this task. First, we focus on the system's general functionality and system architecture. We then describe the interface and design of two deployed news agents that are part of the described architecture. While the first agent provides personalized news through a web-based interface, the second system is geared towards wireless information devices such as PDAs (personal digital assistants) and cell phones. Based on implicit and explicit user feedback, our agents use a machine learning algorithm to induce individual user models. Motivated by general shortcomings of other user modeling systems for Information Retrieval applications, as well as the specific requirements of news classification, we propose the induction of hybrid user models that consist of separate models for short-term and long-term interests. Furthermore, we illustrate how the described algorithm can be used to address an important issue that has thus far received little attention in the Information Retrieval community: a user's information need changes as a direct result of interaction with information. We empirically evaluate the system's performance based on data collected from regular system users. The goal of the evaluation is not only to understand the performance contributions of the algorithm's individual components, but also to assess the overall utility of the proposed user modeling techniques from a user perspective. Our results provide empirical evidence for the utility of the hybrid user model, and suggest that effective personalization can be achieved without requiring any extra effort from the user. [ABSTRACT FROM AUTHOR]

This paper presents a stereotype-based user model for adaptive hypermedia systems. We use a suitable algebraic fuzzy structure which can adequately reflect some features of the user in the model, and apply this model to adapt the navigation and the content of hypermedia nodes to the user's needs. The model includes temporal representations of the user and approximates every real user by a set of stereotypes, from which the one realizing the best approximation can always be extracted. The set of stereotypes is the support set of the structure and the operations defined therein may be supplied with adequate semantics which allow for the selection of the stereotype. [ABSTRACT FROM AUTHOR]

The text recommendation task involves delivering sets of documents to users on the basis of user models. These models are improved over time, given feedback on the delivered documents. When selecting documents to recommend, a system faces an instance of the exploration/exploitation tradeoff: whether to deliver documents about which there is little certainty, or those which are known to match the user model learned so far. In this paper, a simulation is constructed to investigate the effects of this tradeoff on the rate of learning user models, and the resulting compositions of the sets of recommended documents, in particular World-Wide Web pages. Document selection strategies are developed which correspond to different points along the tradeoff. Using an exploitative strategy, our results show that simple preference functions can successfully be learned using a vector-space representation of a user model in conjunction with a gradient descent algorithm, but that increasingly complex preference functions lead to a slowing down of the learning process. Exploratory strategies are shown to increase the rate of user model acquisition at the expense of presenting users with suboptimal recommendations; in addition they adapt to user preference changes more rapidly than exploitative strategies. These simulated tests suggest an implementation for a simple control that is exposed to users, allowing them to vary a system's document selection behavior depending on individual circumstances. [ABSTRACT FROM AUTHOR]

The huge amount of information available in the currently evolving world wide information infrastructure at any one time can easily overwhelm end-users. One way to address the information explosion is to use an ‘information filtering agent’ which can select information according to the interest and/or need of an end-user. However, at present few information filtering agents exist for the evolving world wide multimedia information infrastructure. In this study, we evaluate the use of feature-based approaches to user modeling with the purpose of creating a filtering agent for the video-on-demand application. We evaluate several feature and clique-based models for 10 voluntary subjects who provided ratings for the movies. Our preliminary results suggest that feature-based selection can be a useful tool to recommend movies according to the taste of the user and can be as effective as a movie rating expert. We compare our feature-based approach with a clique-based approach, which has advantages where information from other users is available. [ABSTRACT FROM AUTHOR]

Uncertainty and fuzziness are ubiquitous in the field of computerized selling. Therefore the mastery of these domains might be a key factor for the success of electronic selling. In this paper the Sales Assistant is introduced. It employs user models in the problem solving and dialog control layers, and fuzzy techniques for the management of imprecision. Fuzzy Multiple Criteria Analysis has proven its usefulness in product evaluation if there are no severe interdependencies among the product attributes. The user model in the Sales Assistant is constructed unobtrusively on the basis of user behavior, and it uses short-term information. It increases the transparency and usability of a large hypertext-like information system. [ABSTRACT FROM AUTHOR]

The application of user-expertise modeling for adaptive interfaces is confronted with a number of difficult challenges, namely, efficiency and reliability, the cost-benefit ratio, and the practical usability of user modeling techniques. We argue that many of these obstacles can be overcome by standard, automatic means of performing knowledge assessment. Within this perspective, we present the basis of a probabilistic user modeling approach, the POKS technique, which could serve as a standard user-expertise modeling tool. The POKS technique is based on the cognitive theory of knowledge structures: a formalism for the representation of the order in which we learn knowledge units (KU). The technique permits the induction of knowledge structures from a small number of empirical data cases. It uses an evidence propagation scheme within these structures to infer an individual's knowledge state from a sample of KU. The empirical induction technique is based, in part, on statistical hypothesis testing over conditional probabilities that are determined by the KUs' learning order. Experiments with this approach show that the technique is successful in partially inferring an individual's knowledge state, either through the monitoring of a user's behavior, or through a selective questioning process. However, the selective process, based on entropy minimization, is shown to be much more effective in reducing the standard error score of knowledge assessment than random sampling. [ABSTRACT FROM AUTHOR]

A rapidly growing number of user and student modeling systems have employed numerical techniques for uncertainty management. The three major paradigms are those of Bayesian networks, the Dempster-Shafer theory of evidence, and fuzzy logic. In this overview, each of the first three main sections focuses on one of these paradigms. It first introduces the basic concepts by showing how they can be applied to a relatively simple user modeling problem. It then surveys systems that have applied techniques from the paradigm to user or student modeling, characterizing each system within a common framework. The final main section discusses several aspects of the usability of these techniques for user or student modeling, such as their knowledge engineering requirements, their need for computational resources, and the communicability of their results. [ABSTRACT FROM AUTHOR]

This paper is concerned with information-seeking dialogues in a restricted domain (we consider a consultation system for a Computer Science Department, delivering information about the various tasks that the users may want to perform: for example, how to access the library, get information about the courses of the Department, etc.) and presents a framework where a plan recognition and a user modeling component are integrated to cooperate in the task of identifying the user's plans and goals. The focus of the paper is centered on the techniques used for building the user model and exploiting it in the determination of the user's intentions. For this task, we use stereotypes and we propose some inference rules for expanding the user model by inferring the user's beliefs from both the sentences s/he utters and the information stored in the plan library of the system, that describes the actions in the domain. Moreover, we introduce some disambiguation rules that are applied to the information in the user model for restricting the set of ambiguous hypotheses on the user's plans and goals to the most plausible ones. This also simplifies a further clarification dialogue if it is necessary for a precise identification of the user's intentions. [ABSTRACT FROM AUTHOR]

There has been a great deal of research on specific issues of user modeling (e.g., generation of explanations (Paris 88), implicit knowledge acquisition (Kass, Finin 87), exploitation of user feedback to compensate for the unreliability of user models (Moore, Paris 92), but to our knowledge no work has been done on how to integrate this work into a single system. In TECHDOC-I we combine a number of ideas and work from various areas in a single system, add some unique features (e.g., application of a double-stereotype mechanism to plan representation), and apply them to a new domain (instructions for car maintenance). TECHDOC-I provides support to a user in the area of car maintenance. All maintenance activities are represented by plans, which consist of plan steps. The dialogue between user and system is based on these plans. A user model ensures that the system adapts the content of the output to the user. The commands and explanations are given in natural language that is generated by a (multilingual) text generator. [ABSTRACT FROM AUTHOR]

The paper is concerned with the question of whether and under what conditions active help systems with plan recognition components that have been developed in the environment of artificial intelligence research are able to prove their value in the real context of commercial application programs. The question is investigated using the development of the COMFOHELP intelligent help system as an example. COMFOHELP supports the COMFOTEX graphical text processing program and has been developed by the Linguistic Information Science Group at the University of Regensburg since 1988. The system recognizes erroneous and suboptimal plans pursued by the user by analyzing the dialog history and comparing them with the correct plan for achieving the user's goal. Section 2 discusses the research situation and elaborates on those problems which up to now prevented research concepts for plan recognition and intelligent help systems from being practically applied. Testing error situations empirically is a first prerequisite since potential erroneous plans can only be established in real-world tests. The second prerequisite is a special system architecture which counteracts the problem of ambiguities in plan recognition. Section 3 introduces a first still restricted prototype version of COMFOHELP whose efficiency was verified in a statistical hypothesis test. The users performing their text processing tasks with the support of COMFOHELP came off significantly better than members of a reference group working without the intelligent help. Section 4 shows that the proposed COMFOHELP system architecture is reconfirmed by the results of extensive empirical investigations (with more than 100 users) of erroneous plans when using a more complex version of COMFOTEX. The architecture still proves to be worthwhile even when functionality is increased by a factor of three to four. [ABSTRACT FROM AUTHOR]

Natural Language is a powerful medium for interacting with users, and sophisticated computer systems using natural language are becoming more prevalent. Just as human speakers show an essential, inbuilt responsiveness to their hearers, computer systems must 'tailor' their utterances to users. Recognizing this, researchers devised user models and strategies for exploiting them in order to enable systems to produce the 'best' answer for a particular user. Because these efforts were largely devoted to investigating how a user model could be exploited to produce better responses, systems employing them typically assumed that a detailed and correct model of the user was available a priori, and that the information needed to generate appropriate responses was included in that model. However, in practice, the completeness and accuracy of a user model cannot be guaranteed. Thus, unless systems can compensate for incorrect or incomplete user models, the impracticality of building user models will prevent much of the work on tailoring from being successfully applied in real systems. In this paper, we argue that one way for a system to compensate for an unreliable user model is to be able to react to feedback from users about the suitability of the texts it produces. We also discuss how such a capability can actually alleviate some of the burden now placed on user modeling. Finally, we present a text generation system that employs whatever information is available in its user model in an attempt to produce satisfactory texts, but is also capable of responding to the user's follow-up questions about the texts it produces. [ABSTRACT FROM AUTHOR]

This paper describes discourse processing in King Kong, a portable natural language interface. King Kong enables users to pose questions and issue commands to a back end system. The notion of a discourse is central to King Kong, and underlies much of the intelligent assistance that kong provides to its users. kong's approach to modeling discourse is based on the work of Grosz and Sidner (1986). We extend Grosz and Sidner's framework in several ways, principally to allow multiple independent discourse contexts to remain active at the same time. This paper also describes King Kong's method of intention recognition, which is similar to that described in Kautz and Allen (1986) and Carberry (1988). We demonstrate that a relatively simple intention recognition component can be exploited by many other discourserelated mechanisms, for example to disambiguate input and resolve anaphora. In particular, this paper describes in detail the mechanism in King Kong that uses information from the discourse model to form a range of cooperative extended responses to queries in an effort to aid the user in accomplishing her goals. [ABSTRACT FROM AUTHOR]

Intelligent computer-assisted instruction (ICAI) systems have continually sought increased flexibility to respond appropriately to the multi-faceted interests of students. Research on the Image student modeler of the Guidon2 ICAI system has developed a multiple-anticipation approach to plan generation and interpretation that directly meets a wide range of communication goals: providing information support, encouraging exploration with interesting elaborations, recognizing strategic mistakes in actions and plans, evaluating success in domain tasks, diagnosing misconceptions, and recommending improvements for mistakes. In order to meet pragmatic system constraints, Image must provide its full range of advice simultaneously, continually, and quickly. It drops many of the simplifying assumptions typically used by plan recognition user modelers, including assumptions of closed-world knowledge and of the user's correctness, cooperation, and unified goal. To maintain efficiency for dynamic plan recognition, Image relies instead on two assumptions of cognitive economy, contextual relevance and conceptual easiness, which are operational forms of Grice's maxims of relation and quantity. Its multiple-anticipation approach to plan management provides all of the requisite information together and allows incremental updating and relaxation methods of interpretation, even when students are shifting focus frequently. [ABSTRACT FROM AUTHOR]

User models play a critical role in robust plan recognition by controlling ambiguity. They allow an observer to prefer one plan explanation over another, and they provide a means of measuring the believability of misconceptions when the user's plan is flawed. This paper discusses the motivation for including a user model in robust plan recognition, and shows how a probabilistic interpretation offers a practical means of incorporating a user model into the plan recognition process. [ABSTRACT FROM AUTHOR]

User modeling research can benefit from formal automated reasoning tools. However existing formal tools may need to be modified to suit the needs of user modeling. Theorist is a simple framework for default reasoning. It can be used as a tool for building and maintaining a user model, and as a model of a user's default reasoning. To apply Theorist to both tasks, we develop Nested Theorist (NT), a simple tool based on Theorist that allows default reasoning on arbitrarily-many levels. We extend NT in two ways: we allow prioritized defaults, and we allow reasoning about agents with limited reasoning capabilities. This paper focusses on applications, and uses wide-ranging examples from user-modeling literature to illustrate the usefulness of the tools presented. [ABSTRACT FROM AUTHOR]

This article investigates the implications of active user model acquisition upon plan recognition, domain planning, and dialog planning in dialog architectures. A dialog system performs active user model acquisition by querying the user during the course of the dialog. Existing systems employ passive strategies that rely on inferences drawn from passive observation of the dialog. Though passive acquisition generally reduces unnecessary dialog, in some cases the system can effectively shorten the overall dialog length by selectively initiating subdialogs for acquiring information about the user. We propose a theory identifying conditions under which the dialog system should adopt active acquisition goals. Active acquisition imposes a set of rationality requirements not met by current dialog architectures. To ensure rational dialog decisions, we propose significant extensions to plan recognition, domain planning, and dialog planning models, incorporating decision-theoretic heuristics for expected utility. The most appropriate framework for active acquisition is a multi-attribute utility model wherein plans are compared along multiple dimensions of utility. We suggest a general architectural scheme, and present an example from a preliminary implementation. [ABSTRACT FROM AUTHOR]