Table of contents XvII Modeling Individualization in a Bayesian Networks Implementation of Knowledge Tracing Zachary A. Pardos and Neil T. Heffernan Detecting Gaming the System in Constraint-Based Tutors 267 Ryan S.J.d. Baker, Antonia Mitrovic, and Moffat Mathews Bayesian Credibility Modeling for Personalized Recommendation in Participatory Media Aaditeshwar Seth, Jie Zhang, and Robin Cohen A Study on User Perception of Personality-Based Recommender System Rong Hu and Pearl Pu Compass to Locate the User Model I Need: Building the bridge between Researchers and Practitioners in User modeling 303 Armelle Brun, Anne Boyer, and Liana razmerita Industry Papers my COMAND Automotive User Interface: Personalized Interaction with Multimedia Content Based on Fuzzy Preference Modeling 315 Philipp Fischer and Andreas Nurnberger User Modeling for Telecommunication Applications: Experiences and Practical Implications Heath Hohwald, Enrique Frias-Martinez, and Nuria Oliver Mobile Web Profiling: A Study of off-Portal Surfing Habits of Mobile Daniel Olmedilla, Enrique Frias-Martinez, and Ruben lara Personalized Implicit Learning in a Music Recommender System Suzana Kordumova, Ivana Kostadinouska, Mauro barbieri Verus Pronk, and Jan Korst Short Research Papers Personalised Pathway Prediction 363 Fabian Bohnert and Ingrid Zukerman Towards a Customization of Rating Scales in Adaptive Systems Federica Cena, Fabiana verner, and Cristina Gena Eye-Tracking Study of User Behavior in Recommender Interfaces Li chen and pearl p
Table of Contents XVII Modeling Individualization in a Bayesian Networks Implementation of Knowledge Tracing ............................................... 255 Zachary A. Pardos and Neil T. Heffernan Detecting Gaming the System in Constraint-Based Tutors............. 267 Ryan S.J.d. Baker, Antonija Mitrovi´c, and Moffat Mathews Bayesian Credibility Modeling for Personalized Recommendation in Participatory Media .............................................. 279 Aaditeshwar Seth, Jie Zhang, and Robin Cohen A Study on User Perception of Personality-Based Recommender Systems ........................................................ 291 Rong Hu and Pearl Pu Compass to Locate the User Model I Need: Building the Bridge between Researchers and Practitioners in User Modeling .............. 303 Armelle Brun, Anne Boyer, and Liana Razmerita Industry Papers myCOMAND Automotive User Interface: Personalized Interaction with Multimedia Content Based on Fuzzy Preference Modeling ............. 315 Philipp Fischer and Andreas N¨urnberger User Modeling for Telecommunication Applications: Experiences and Practical Implications ............................................ 327 Heath Hohwald, Enrique Fr´ıas-Mart´ınez, and Nuria Oliver Mobile Web Profiling: A Study of Off-Portal Surfing Habits of Mobile Users ........................................................... 339 Daniel Olmedilla, Enrique Fr´ıas-Mart´ınez, and Rub´en Lara Personalized Implicit Learning in a Music Recommender System ....... 351 Suzana Kordumova, Ivana Kostadinovska, Mauro Barbieri, Verus Pronk, and Jan Korst Short Research Papers Personalised Pathway Prediction ................................... 363 Fabian Bohnert and Ingrid Zukerman Towards a Customization of Rating Scales in Adaptive Systems ........ 369 Federica Cena, Fabiana Vernero, and Cristina Gena Eye-Tracking Study of User Behavior in Recommender Interfaces ...... 375 Li Chen and Pearl Pu
XVIII Table of Contents Recommending Food: Reasoning on Recipes and Ingredients Jill Freyme and Shlomo Berkousky Disambiguating Search by Leveraging a Social Context Based on the Stream of User's Activity Tomas Kramar. Michal barla and maria bielikova Features of an Independent Open Learner Model Influencing Uptake by University Students Susan bull Doctoral Consortium Papers Recognizing and Predicting the Impact on Human Emotion(Affect) Using Computing Systems David G. Cooper Utilising User Texts to Improve Recommendations 403 Yanir seroussi Semantically-Enhanced Ubiquitous User Modelin Till Plumbum User Modeling Based on Emergent Domain Semantics 411 Marian simko and maria bielikova "Biographic Spaces": A Personalized Smoking Cessation Intervention in Second life 415 Ana Boa- Ventura and Luis Saboga-Nunes Task-Based User Modelling for Knowledge Work 419 Charlie Abela, Chris Staff, and Siegfried Handschuh Enhancing User Interaction in Virtual Environments through Adaptive Personalized 3D Interaction Techniques Johanna Renny Octavia, Karin Coninz, and Chris Raymaekers Author index
XVIII Table of Contents Recommending Food: Reasoning on Recipes and Ingredients........... 381 Jill Freyne and Shlomo Berkovsky Disambiguating Search by Leveraging a Social Context Based on the Stream of User’s Activity ......................................... 387 Tom´aˇs Kram´ar, Michal Barla, and M´aria Bielikov´a Features of an Independent Open Learner Model Influencing Uptake by University Students ........................................... 393 Susan Bull Doctoral Consortium Papers Recognizing and Predicting the Impact on Human Emotion (Affect) Using Computing Systems ........................................ 399 David G. Cooper Utilising User Texts to Improve Recommendations ................... 403 Yanir Seroussi Semantically-Enhanced Ubiquitous User Modeling ................... 407 Till Plumbaum User Modeling Based on Emergent Domain Semantics ................ 411 Mari´an Simko and M´ ˇ aria Bielikov´a “Biographic Spaces”: A Personalized Smoking Cessation Intervention in Second Life ................................................... 415 Ana Boa-Ventura and Lu´ıs Saboga-Nunes Task-Based User Modelling for Knowledge Work Support ............. 419 Charlie Abela, Chris Staff, and Siegfried Handschuh Enhancing User Interaction in Virtual Environments through Adaptive Personalized 3D Interaction Techniques ............................. 423 Johanna Renny Octavia, Karin Coninx, and Chris Raymaekers Author Index .................................................. 427
Modeling emotion and Its Expression in virtual Humans Stacy Marsella Institute for Creative technologies Extended Abstract of Keynote Talk A growing body of work in psychology and the neurosciences has documented the functional, often adaptive role of emotions in human behavior. This has led to a signifi cant growth in research on computational models of human emotional processes, fueled both by their basic research potential as well as the promise that the function of emotion in human behavior can be exploited in a range of applications. Computational model transform theory construction by providing a framework for studying emotion processes that augments what is feasible in more traditional laboratory settings. Modern research in the psychological processes and neural underpinnings of emotion is also transform- ing the science of computation. In particular, findings on the role that emotions play in human behavior have motivated artificial intelligence and robotics research to explore whether modeling emotion processes can lead to more intelligent, fexible and capable systems. Further, as research has revealed the deep role that emotion and its expression play in human social interaction, researchers have proposed that more effective human computer interaction can be realized if the interaction is mediated both by a model of the user's emotional state as well as by the expression of emotions Our lab considers the computational modeling of emotions from the perspective of a particular application area, virtual humans. Virtual humans are autonomous virtual characters that are designed to act like humans and interact with them in shared virtual environments. much as humans interact with humans, as facsimiles of humans virtual humans can reason about the environment, simulate the understanding and expression of now use this technology, including education, health intervention and entertainment. They are also being used as virtual confederates for experiments in social psychology The computational modeling of emotions has emerged as a central challenge of vir- tual human architectures. In particular, researchers in virtual characters for gaming and teaching environments have sought to endow virtual characters with emotion-related capabilities so that they may interact more naturally with human users Pr Computational models of emotion used in virtual humans have largely been based appraisal theory, the predominant psychological theory of emotion. Appraisal theory argues that emotion arise from patterns of individual assessments concerning the rela- tionship between events and an individuals beliefs, desires and intentions, sometimes referred to as the person-environment relationship. These assessments, often called ap. praisal variables, characterize aspects of the personal significance of events(e.g, w P. De Bra, A Kobsa, and D Chin(Eds ) UMAP 2010, LNCS 6075, Pp. 1-2, 2010 C Springer-Verlag Berlin Heidelberg 2010
Modeling Emotion and Its Expression in Virtual Humans Stacy Marsella Institute for Creative Technologies University of Southern California Extended Abstract of Keynote Talk A growing body of work in psychology and the neurosciences has documented the functional, often adaptive role of emotions in human behavior. This has led to a signifi- cant growth in research on computational models of human emotional processes, fueled both by their basic research potential as well as the promise that the function of emotion in human behavior can be exploited in a range of applications. Computational models transform theory construction by providing a framework for studying emotion processes that augments what is feasible in more traditional laboratory settings. Modern research in the psychological processes and neural underpinnings of emotion is also transforming the science of computation. In particular, findings on the role that emotions play in human behavior have motivated artificial intelligence and robotics research to explore whether modeling emotion processes can lead to more intelligent, flexible and capable systems. Further, as research has revealed the deep role that emotion and its expression play in human social interaction, researchers have proposed that more effective human computer interaction can be realized if the interaction is mediated both by a model of the user’s emotional state as well as by the expression of emotions. Our lab considers the computational modeling of emotions from the perspective of a particular application area, virtual humans. Virtual humans are autonomous virtual characters that are designed to act like humans and interact with them in shared virtual environments, much as humans interact with humans. As facsimiles of humans, virtual humans can reason about the environment, simulate the understanding and expression of emotion, and communicate using speech and gesture. A range of application areas now use this technology, including education, health intervention and entertainment. They are also being used as virtual confederates for experiments in social psychology. The computational modeling of emotions has emerged as a central challenge of virtual human architectures. In particular, researchers in virtual characters for gaming and teaching environments have sought to endow virtual characters with emotion-related capabilities so that they may interact more naturally with human users. Computational models of emotion used in virtual humans have largely been based on appraisal theory, the predominant psychological theory of emotion. Appraisal theory argues that emotion arise from patterns of individual assessments concerning the relationship between events and an individual’s beliefs, desires and intentions, sometimes referred to as the person-environment relationship. These assessments, often called appraisal variables, characterize aspects of the personal significance of events (e.g., was P. De Bra, A. Kobsa, and D. Chin (Eds.): UMAP 2010, LNCS 6075, pp. 1–2, 2010. c Springer-Verlag Berlin Heidelberg 2010
s. Marsella this event expected in terms of my prior beliefs? is this event congruent with my goals do I have the power to alter the consequences of this event? ) Patterns of appraisal are associated with specific emotional responses, including physiological and behav ioral reactions. In several versions of appraisal theory, appraisals also trigger cogni tive responses, often referred to as coping strategieseg, planning, procrastination or resignation--feeding back into a continual cycle of appraisal and re-appraisal In this talk, I will give an overview of virtual humans. I will then go into greater detail on how emotions is modeled computationally in virtual humans, including the heoretical basis of the models in appraisal theory, how we validate models against human data and how human data is also used to inform the animation of the virtual humans body
2 S. Marsella this event expected in terms of my prior beliefs? is this event congruent with my goals; do I have the power to alter the consequences of this event?). Patterns of appraisal are associated with specific emotional responses, including physiological and behavioral reactions. In several versions of appraisal theory, appraisals also trigger cognitive responses, often referred to as coping strategies—e.g., planning, procrastination or resignation—feeding back into a continual cycle of appraisal and re-appraisal. In this talk, I will give an overview of virtual humans. I will then go into greater detail on how emotions is modeled computationally in virtual humans, including the theoretical basis of the models in appraisal theory, how we validate models against human data and how human data is also used to inform the animation of the virtual human’s body
Adheat-An influence-Based Diffusion model for Propagating Hints to Personalize Social Ads Edward Y chang Abstract of Keynote Talk AdHeat is our newly developed social ad model considering user influence in add tion to relevance for matching ads. Traditionally, ad placement employs the relevance model. Such a model matches ads with Web page content, user interests, or both. We have observed however, on social networks that the relevance model suffers from two shortcomings. First, influential users(users who contribute opinions) seldom click ads that are highly relevant to their expertise. Second, because influential users'contents and activities are attractive to other users, hint words summarizing their expertise and activities may be widely preferred. Therefore, we propose AdHeat, which diffuses hint words of influential users to others and then matches ads for each user with aggregated hints. Our experimental results on a large-scale social network show that AdHeat out performs the relevance model on CTR(click through rate) by significant margins. In this talk, the algorithms employed by AdHeat and solutions to address scalability issues are prese P. De Bra, A Kobsa, and D Chin(Eds ) UMAP 2010, LNCS 6075, P 3, 2010 C Springer-Verlag Berlin Heidelberg 2010
AdHeat — An Influence-Based Diffusion Model for Propagating Hints to Personalize Social Ads Edward Y. Chang Director of Research Google Abstract of Keynote Talk AdHeat is our newly developed social ad model considering user influence in addition to relevance for matching ads. Traditionally, ad placement employs the relevance model. Such a model matches ads with Web page content, user interests, or both. We have observed, however, on social networks that the relevance model suffers from two shortcomings. First, influential users (users who contribute opinions) seldom click ads that are highly relevant to their expertise. Second, because influential users’ contents and activities are attractive to other users, hint words summarizing their expertise and activities may be widely preferred. Therefore, we propose AdHeat, which diffuses hint words of influential users to others and then matches ads for each user with aggregated hints. Our experimental results on a large-scale social network show that AdHeat outperforms the relevance model on CTR (click through rate) by significant margins. In this talk, the algorithms employed by AdHeat and solutions to address scalability issues are presented. P. De Bra, A. Kobsa, and D. Chin (Eds.): UMAP 2010, LNCS 6075, p. 3, 2010. c Springer-Verlag Berlin Heidelberg 2010