HCI Bibliography Home | HCI Conferences | UMAP Archive | Detailed Records | RefWorks | EndNote | Hide Abstracts
UMAP Tables of Contents: 00010203040506070809101112131415

Proceedings of the 2015 Conference on User Modeling, Adaptation and Personalization

Fullname:UMAP 2015: 23rd International Conference on User Modeling, Adaptation, and Personalization
Editors:Francesco Ricci; Kalina Bontcheva; Owen Conlan; Séamus Lawless
Location:Dublin, Ireland
Dates:2015-Jun-29 to 2015-Jul-03
Publisher:Springer International Publishing
Series:Lecture Notes in Computer Science 9146
Standard No:DOI: 10.1007/978-3-319-20267-9 hcibib: UMAP15; ISBN: 978-3-319-20266-2 (print), 978-3-319-20267-9 (online)
Papers:37
Pages:404
Links:Online Proceedings | Conference Website
  1. Long Presentations
  2. Short Presentations
  3. Doctoral Consortium

Long Presentations

Exploring the Potential of User Modeling Based on Mind Maps BIBAKFull-Text 3-17
  Joeran Beel; Stefan Langer; Georgia Kapitsaki; Corinna Breitinger; Bela Gipp
Mind maps have not received much attention in the user modeling and recommender system community, although mind maps contain rich information that could be valuable for user-modeling and recommender systems. In this paper, we explored the effectiveness of standard user-modeling approaches applied to mind maps. Additionally, we develop novel user modeling approaches that consider the unique characteristics of mind maps. The approaches are applied and evaluated using our mind mapping and reference-management software Docear. Docear displayed 430,893 research paper recommendations, based on 4,700 user mind maps, from March 2013 to August 2014. The evaluation shows that standard user modeling approaches are reasonably effective when applied to mind maps, with click-through rates (CTR) between 1.16% and 3.92%. However, when adjusting user modeling to the unique characteristics of mind maps, a higher CTR of 7.20% could be achieved. A user study confirmed the high effectiveness of the mind map specific approach with an average rating of 3.23 (out of 5), compared to a rating of 2.53 for the best baseline. Our research shows that mind map-specific user modeling has a high potential, and we hope that our results initiate a discussion that encourages researchers to pursue research in this field and developers to integrate recommender systems into their mind mapping tools.
Keywords: Mind map; User modeling; Recommender systems
Modeling Motivation in a Social Network Game Using Player-Centric Traits and Personality Traits BIBAKFull-Text 18-30
  Max V. Birk; Dereck Toker; Regan L. Mandryk; Cristina Conati
People are drawn to play different types of videogames and find enjoyment in a range of gameplay experiences. Envisaging a representative game player or persona allows game designers to personalize game content; however, there are many ways to characterize players and little guidance on which approaches best model player behavior and preference. To provide knowledge about how player characteristics contribute to game experience, we investigate how personality traits as well as player styles from the BrianHex model moderate the prediction of player motivation with a social network game. Our results show that several player characteristics impact motivation, expressed in terms of enjoyment and effort. We also show that player enjoyment and effort, as predicted by our models, impact players' in-game behaviors, illustrating both the predictive power and practical utility of our models for guiding user adaptation.
Keywords: User modeling; Personality; Player experience; Social network game; Linear regression; Moderation; Motivation
Automatic Gaze-Based Detection of Mind Wandering with Metacognitive Awareness BIBAKFull-Text 31-43
  Robert Bixler; Sidney D'Mello
Mind wandering (MW) is a ubiquitous phenomenon where attention involuntarily shifts from task-related processing to task-unrelated thoughts. There is a need for adaptive systems that can reorient attention when MW is detected due to its detrimental effects on performance and productivity. This paper proposes an automated gaze-based detector of self-caught MW (i.e., when users become consciously aware that they are MW). Eye gaze data and self-reports of MW were collected as 178 users read four instructional texts from a computer interface. Supervised machine learning models trained on features extracted from users' gaze fixations were used to detect pages where users caught themselves MW. The best performing model achieved a user-independent kappa of .45 (accuracy of 74% compared to a chance accuracy of 52%); the first ever demonstration of a self-caught MW detector. An analysis of the features revealed that during MW, users made more regression fixations, had longer saccades that crossed lines more often, and had more uniform fixation durations, indicating a violation from normal reading patterns. Applications of the MW detector are discussed.
Keywords: Gaze tracking; Mind wandering; Affect detection; User modeling
The Value of Social: Comparing Open Student Modeling and Open Social Student Modeling BIBAKFull-Text 44-55
  Peter Brusilovsky; Sibel Somyürek; Julio Guerra; Roya Hosseini; Vladimir Zadorozhny
Open Student Modeling (OSM) is a popular technology that makes traditionally hidden student models available to the learners for exploration. OSM is known for its ability to increase student engagement, motivation, and knowledge reflection. A recent extension of OSM known as Open Social Student Modeling (OSSM) attempts to enhance cognitive aspects of OSM with social aspects by allowing students to explore models of peer students or the whole class. In this paper, we introduce MasteryGrids, a scalable OSSM interface and report the results of a large-scale classroom study that explored the value of adding social dimension to OSM. The results of the study reveal a remarkable engaging potential of OSSM as well as its impact on learning effectiveness and user attitude.
Keywords: Open student modeling; Open social student modeling; Social visualization
MENTOR: A Physiologically Controlled Tutoring System BIBAKFull-Text 56-67
  Maher Chaouachi; Imène Jraidi; Claude Frasson
In this paper we present a tutoring system that automatically sequences the learning content according to the learners' mental states. The system draws on techniques from Brain Computer Interface and educational psychology to automatically adapt to changes in the learners' mental states such as attention and workload using electroencephalogram (EEG) signals. The objective of this system is to maintain the learner in a positive mental state throughout the tutoring session by selecting the next pedagogical activity that fits the best to his current state. An experimental evaluation of our approach involving two groups of learners showed that the group who interacted with the mental state-based adaptive version of the system obtained higher learning outcomes and had a better learning experience than the group who interacted with a non-adaptive version.
Keywords: Intelligent tutoring system; Engagement; Workload; Real-time adaptive system; EEG; Machine learning; Experience and affect
Context-Aware User Modeling Strategies for Journey Plan Recommendation BIBAKFull-Text 68-79
  Victor Codina; Jose Mena; Luis Oliva
Popular journey planning systems, like Google Maps or Yahoo! Maps, usually ignore user's preferences and context. This paper shows how we applied context-aware recommendation technologies in an existing journey planning mobile application to provide personalized and context-dependent recommendations to users. We describe two different strategies for context-aware user modeling in the journey planning domain. We present an extensive performance comparison of the proposed strategies by conducting a user-centric study in addition to a traditional offline evaluation method.
Keywords: Recommender systems; Context-awareness; Personalized journey planning; User-centric evaluation
MOOClm: User Modelling for MOOCs BIBAKFull-Text 80-91
  Ronny Cook; Judy Kay; Bob Kummerfeld
Emerging MOOC platforms capture huge amounts of learner data. This paper presents our MOOClm platform, for transforming data from MOOCs into independent learner models that can drive personalisation and support reuse of the learner model, for example in an Open Learner Model (OLM). We describe the MOOClm architecture and demonstrate how we have used it to build OLMs.
Keywords: MOOCs; Learner modelling; Open Learner Modelling (OLM); Learner model server
Dynamic Approaches to Modeling Student Affect and its Changing Role in Learning and Performance BIBAKFull-Text 92-103
  Seth Corrigan; Tiffany Barkley; Zachary Pardos
We investigate the relation between students' affect, learning and performance in the context of the ASSISTments online math tutoring system. Moment-by-moment estimates of students' affective states derived from a series of affect detectors accompany each student response within the tutoring system. By applying a series modified factorial hidden Markov models that account for students' affective state at the time of the given response and comparing the models' performance to the standard Bayesian Knowledge Tracing (BKT) approach, we evaluate the impact of affect on estimates of students' guess and slip behavior. The investigation suggests a model based approach to improving student models in the context of online tutoring systems.
Keywords: Knowledge tracing; Emotion; Affect; Learning; Performance; Hidden Markov models; Factorial hidden Markov models; Automated tutoring systems
Analyzing and Predicting Privacy Settings in the Social Web BIBAKFull-Text 104-117
  Kaweh Djafari Naini; Ismail Sengor Altingovde; Ricardo Kawase; Eelco Herder; Claudia Niederée
Social networks provide a platform for people to connect and share information and moments of their lives. With the increasing engagement of users in such platforms, the volume of personal information that is exposed online grows accordingly. Due to carelessness, unawareness or difficulties in defining adequate privacy settings, private or sensitive information may be exposed to a wider audience than intended or advisable, potentially with serious problems in the private and professional life of a user. Although these causes usually receive public attention when it involves companies' higher managing staff, athletes, politicians or artists, the general public is also subject to these issues. To address this problem, we envision a mechanism that can suggest users the appropriate privacy setting for their posts taking into account their profiles. In this paper, we present a thorough analysis of privacy settings in Facebook posts and evaluate prediction models that can anticipate the desired privacy settings with high accuracy, making use of the users' previous posts and preferences.
Keywords: Facebook; Privacy; Social networks
Counteracting Anchoring Effects in Group Decision Making BIBAKFull-Text 118-130
  Martin Stettinger; Alexander Felfernig; Gerhard Leitner; Stefan Reiterer
Similar to single user decisions, group decisions can be affected by decision biases. In this paper we analyze anchoring effects as a specific type of decision bias in the context of group decision scenarios. On the basis of the results of a user study in the domain of software requirements prioritization we discuss results regarding the optimal time when preference information of other users should be disclosed to the current user. Furthermore, we show that explanations can increase the satisfaction of group members with various aspects of a group decision process (e.g., satisfaction with the decision and decision support quality).
Keywords: Group decision making; Recommender systems; Decision biases; Anchoring effects
Note: James Chen Best Student Paper Award
Gifting as a Novel Mechanism for Personalized Museum and Gallery Interpretation BIBAKFull-Text 131-142
  Lesley Fosh; Steve Benford; Boriana Koleva; Katharina Lorenz
The designers of mobile guides for museums and galleries are increasingly concerned with delivering rich interpretation that can be personalized to meet the diverse needs of individual visitors. However, increased personalization can mean that the sociality of museum visits is overlooked. We present a new approach to resolving the tension between the personal and the social that invites visitors themselves to personalize and gift interpretations to others in their social groups. We tested the approach in two different museum settings and with different types of small group, to investigate how visitors personalized experiences for one another, how the personalized experiences were received by visitors, and how they worked as part of a social visit. We reveal how visitors designed highly personal interpretations for one another by drawing inspiration from both the exhibits themselves and their interpersonal knowledge of one another. Our findings suggest that the deep level of personalization generated by our approach can create rich, engaging and socially coherent visits that allow visitors to achieve a balance of goals. We conclude by discussing the broader implications of our findings for personalization.
Keywords: Museums; Galleries; Personalization; Interpretation; Collaboration
Supporting Cross-Device Web Search with Social Navigation-Based Mobile Touch Interactions BIBAKFull-Text 143-155
  Shuguang Han; Daqing He; Zhen Yue; Peter Brusilovsky
The wide adoption of smartphones eliminates the time and location barriers for people's daily information access, but also limits users' information exploration activities due to the small mobile screen size. Thus, cross-device web search, where people initialize information needs on one device but complete them on another device, is frequently observed in modern search engines, especially for exploratory information needs. This paper aims to support the cross-device web search, on top of the commonly used context-sensitive retrieval framework, for exploratory tasks. To better model users' search context, our method not only utilizes the search history (query history and click-through) but also employs the mobile touch interactions (MTI) on mobile devices. To be more specific, we combine MTI's ability of locating relevant subdocument content [10] with the idea of social navigation that aggregates MTIs from other users who visit the same page. To demonstrate the effectiveness of our proposed approach, we designed a user study to collect cross-device web search logs on three different types of tasks from 24 participants and then compared our approach with two baselines: a traditional full text based relevance feedback approach and a self-MTI based subdocument relevance feedback approach. Our results show that the social navigation-based MTIs outperformed both baselines. A further analysis shows that the performance improvements are related to several factors, including the quality and quantity of click-through documents, task types and users' search conditions.
Keywords: Mobile touch interaction; Cross-device web search; Social navigation
A Utility Model for Tailoring Sensor Networks to Users BIBAKFull-Text 156-168
  Masud Moshtaghi; Ingrid Zukerman
The proportion of people aged over 65 has significantly increased in recent times, with further increases expected. Multiple sensor-based monitoring solutions have been proposed to tackle the main concerns of elderly people and their carers, viz fall detection and safe movement in the house. At the same time, user studies have shown that cost is the most important factor when deciding whether to install a monitoring system. In this paper, we offer a utility-based approach for selecting a sensor configuration for a user on the basis of his/her behaviour patterns and preferences regarding false alerts and delay in the detection of mishaps, while taking into account his/her budget. Our evaluation on two real-life datasets shows that our utility function supports the selection of cost-effective sensor configurations.
Keywords: Older adults; Sensor selection; Monitoring systems; Inactivity detection
Towards a Recommender Engine for Personalized Visualizations BIBAKFull-Text 169-182
  Belgin Mutlu; Eduardo Veas; Christoph Trattner; Vedran Sabol
Visualizations have a distinctive advantage when dealing with the information overload problem: since they are grounded in basic visual cognition, many people understand them. However, creating them requires specific expertise of the domain and underlying data to determine the right representation. Although there are rules that help generate them, the results are too broad to account for varying user preferences. To tackle this issue, we propose a novel recommender system that suggests visualizations based on (i) a set of visual cognition rules and (ii) user preferences collected in Amazon-Mechanical Turk. The main contribution of this paper is the introduction and the evaluation of a novel approach called VizRec that can suggest an optimal list of top-n visualizations for heterogeneous data sources in a personalized manner.
Keywords: Personalized visualizations; Visualization recommender; Recommender systems; Collaborative filtering; Crowd-sourcing
Cross-System Transfer of Machine Learned and Knowledge Engineered Models of Gaming the System BIBAKFull-Text 183-194
  Luc Paquette; Ryan S. Baker; Adriana de Carvalho; Jaclyn Ocumpaugh
Replicable research on the behavior known as gaming the system, in which students try to succeed by exploiting the functionalities of a learning environment instead of learning the material, has shown it is negatively correlated with learning outcomes. As such, many have developed models that can automatically detect gaming behaviors, towards deploying them in online learning environments. Both machine learning and knowledge engineering approaches have been used to create models for a variety of software systems, but the development of these models is often quite time consuming. In this paper, we investigate how well different kinds of models generalize across learning environments, specifically studying how effectively four gaming models previously created for the Cognitive Tutor Algebra tutoring system function when applied to data from two alternate learning environments: the scatterplot lesson of Cognitive Tutor Middle School and ASSISTments. Our results suggest that the similarity between the systems our model are transferred between and the nature of the approach used to create the model impact transfer to new systems.
Keywords: Gaming the system; Cognitive tutors; ASSISTments; Machine learning; Cognitive modeling; Cross-system transfer
MobiScore: Towards Universal Credit Scoring from Mobile Phone Data BIBAFull-Text 195-207
  Jose San Pedro; Davide Proserpio; Nuria Oliver
Credit is a widely used tool to finance personal and corporate projects. The risk of default has motivated lenders to use a credit scoring system, which helps them make more efficient decisions about whom to extend credit. Credit scores serve as a financial user model, and have been traditionally computed from the user's past financial history. As a result, people without any prior financial history might be excluded from the credit system. In this paper we present MobiScore, an approach to build a model of the user's financial risk from mobile phone usage data, which previous work has shown to convey information about e.g. personality and socioeconomic status. MobiScore could replace traditional credit scores when no financial history is available, providing credit access to currently excluded population sectors, or be used as a complementary source of information to improve traditional finance-based scores. We validate the proposed approach using real data from a telecommunications operator and a financial institution in a Latin American country, resulting in an accurate model of default comparable to traditional credit scoring techniques.
Where to Next? A Comparison of Recommendation Strategies for Navigating a Learning Object Repository BIBAKFull-Text 208-215
  Jennifer Sabourin; Lucy Kosturko; Scott McQuiggan
This paper explores the initial investigation of six recommendation algorithms for deployment in SAS® Curriculum Pathways®, an online repository which houses over 1250 educational resources. The proposed approaches stem from three basic strategies: recommendations based on resource metadata, user behavior, and alignment to academic standards. An evaluation from subject experts suggests that usage-based recommendations are best aligned with teacher needs, though there are interesting domain interactions that suggest the need for continued investigation.
Keywords: Recommender systems; Learning object repository; Technology enhanced learning
Diagrammatic Student Models: Modeling Student Drawing Performance with Deep Learning BIBAKFull-Text 216-227
  Andy Smith; Wookhee Min; Bradford W. Mott; James C. Lester
Recent years have seen a growing interest in the role that student drawing can play in learning. Because drawing has been shown to contribute to students' learning and increase their engagement, developing student models to dynamically support drawing holds significant promise. To this end, we introduce diagrammatic student models, which reason about students' drawing trajectories to generate a series of predictions about their conceptual knowledge based on their evolving sketches. The diagrammatic student modeling framework utilizes deep learning, a family of machine learning methods based on a deep neural network architecture, to reason about sequences of student drawing actions encoded with temporal and topological features. An evaluation of the deep-learning-based diagrammatic student models suggests that it can predict student performance more accurately and earlier than competitive baseline approaches.
Keywords: Student modeling; Intelligent tutoring systems; Deep learning
Lessons Learned -- 15 Years of Delivering Real-World Pedagogically Driven Courses Using Experimental Platforms BIBAKFull-Text 228-239
  Athanasios Staikopoulos; Ian O'Keeffe; Owen Conlan
Advancing research and developing innovative personalization platform whilst at the same time striving to evolve and improve learning experiences for learners, is a challenging prospect. This may be achieved through a longitudinal commitment to developing real-world educational offerings that are used in the daily delivery of learning experiences. This gives the opportunity to continuously apply methods, develop platforms and perform evaluations to realize improvements in the field of user modeling and personalization as well as improving the user experiences they support. In addition, there are specific requirements and obstacles that need to be considered like the robustness and reliability of the experimental platform in order to make this process viable and integrated both with the daily tasks of users and the core business activities of the institution. In this paper, we record our experiences in delivering real-world online courses using experimental platforms that advance personalization and user modeling techniques for over 15 years. We also describe how our research and technology, which is driven by solid pedagogical requirements, has evolved during that time in order to deliver richer learning experiences.
Keywords: Personalization platforms; Challenges using experimental platforms; Improving learning experiences; Pedagogical driven courses; User modelling
Smartphone Based Stress Prediction BIBAKFull-Text 240-251
  Thomas Stütz; Thomas Kowar; Michael Kager; Martin Tiefengrabner; Markus Stuppner; Jens Blechert; Frank H. Wilhelm; Simon Ginzinger
Smartphone usage has tremendously increased and most users keep their smartphones close throughout the day. Smartphones have a broad variety of sensors, that could automatically map and track the user's life and behaviour. In this work we investigate whether automatically collected smartphone usage and sensor data can be employed to predict the experienced stress levels of a user using a customized brief version of the Perceived Stress Scale (PSS). To that end we have conducted a user study in which smartphone data and stress (as measured by the PSS seven times a day) were recorded for two weeks. We found significant correlations between stress scores and smartphone usage as well as sensor data, pointing to innovative ways for automatic stress measurements via smartphone technology. Stress is a prevalent risk factor for multiple diseases. Thus accurate and efficient prediction of stress levels could provide means for targeted prevention and intervention.
Keywords: Stress; Prediction; Smartphone sensing; Data analysis; Field study; Observational study
Exploiting Implicit Item Relationships for Recommender Systems BIBAFull-Text 252-264
  Zhu Sun; Guibing Guo; Jie Zhang
Collaborative filtering inherently suffers from the data sparsity and cold start problems. Social networks have been shown useful to help alleviate these issues. However, social connections may not be available in many real systems, whereas implicit item relationships are lack of study. In this paper, we propose a novel matrix factorization model by taking into account implicit item relationships. Specifically, we employ an adapted association rule technique to reveal implicit item relationships in terms of item-to-item and group-to-item associations, which are then used to regularize the generation of low-rank user- and item-feature matrices. Experimental results on four real-world datasets demonstrate the superiority of our proposed approach against other counterparts.
The Mars and Venus Effect: The Influence of User Gender on the Effectiveness of Adaptive Task Support BIBAKFull-Text 265-276
  Alexandria Katarina Vail; Kristy Elizabeth Boyer; Eric N. Wiebe; James C. Lester
Providing adaptive support to users engaged in learning tasks is the central focus of intelligent tutoring systems. There is evidence that female and male users may benefit differently from adaptive support, yet it is not understood how to most effectively adapt task support to gender. This paper reports on a study with four versions of an intelligent tutoring system for introductory computer programming offering different levels of cognitive (conceptual and problem-solving) and affective (motivational and engagement) support. The results show that female users reported significantly more engagement and less frustration with the affective support system than with other versions. In a human tutorial dialogue condition used for comparison, a consistent difference was observed between females and males. These results suggest the presence of the Mars and Venus Effect, a systematic difference in how female and male users benefit from cognitive and affective adaptive support. The findings point toward design principles to guide the development of gender-adaptive intelligent tutoring systems.
Keywords: Gender effects; Adaptive support; Intelligent tutoring systems; Affect; Engagement; Frustration
Note: Springer Best Paper Award
Quiet Eye Affects Action Detection from Gaze More Than Context Length BIBAKFull-Text 277-288
  Hana Vrzakova; Roman Bednarik
Every purposive interactive action begins with an intention to interact. In the domain of intelligent adaptive systems, behavioral signals linked to the actions are of great importance, and even though humans are good in such predictions, interactive systems are still falling behind. We explored mouse interaction and related eye-movement data from interactive problem solving situations and isolated sequences with high probability of interactive action. To establish whether one can predict the interactive action from gaze, we 1) analyzed gaze data using sliding fixation sequences of increasing length and 2) considered sequences several fixations prior to the action, either containing the last fixation before action (i.e. the quiet eye fixation) or not. Each fixation sequence was characterized by 54 gaze features and evaluated by an SVM-RBF classifier. The results of the systematic evaluation revealed importance of the quiet eye fixation and statistical differences of quiet eye fixation compared to other fixations prior to the action.
Keywords: Action; Intentions; Prediction; Eye-tracking; SVM; Mouse interaction; Problem solving
User Model in a Box: Cross-System User Model Transfer for Resolving Cold Start Problems BIBAKFull-Text 289-301
  Chirayu Wongchokprasitti; Jaakko Peltonen; Tuukka Ruotsalo; Payel Bandyopadhyay; Giulio Jacucci; Peter Brusilovsky
Recommender systems face difficulty in cold-start scenarios where a new user has provided only few ratings. Improving cold-start performance is of great interest. At the same time, the growing number of adaptive systems makes it ever more likely that a new user in one system has already been a user in another system in related domains. To what extent can a user model built by one adaptive system help address a cold start problem in another system? We compare methods of cross-system user model transfer across two large real-life systems: we transfer user models built for information seeking of scientific articles in the SciNet exploratory search system, operating over tens of millions of articles, to perform cold-start recommendation of scientific talks in the CoMeT talk management system, operating over hundreds of talks. Our user study focuses on transfer of novel explicit open user models curated by the user during information seeking. Results show strong improvement in cold-start talk recommendation by transferring open user models, and also reveal why explicit open models work better in cross-domain context than traditional hidden implicit models.
Keywords: Cross-system user modeling; Recommender systems
Implicit Acquisition of User Personality for Augmenting Movie Recommendations BIBAKFull-Text 302-314
  Wen Wu; Li Chen
In recent years, user personality has been recognized as valuable info to build more personalized recommender systems. However, the effort of explicitly acquiring users' personality traits via psychological questionnaire is unavoidably high, which may impede the application of personality-based recommenders in real life. In this paper, we focus on deriving users' personality from their implicit behavior in movie domain and hence enabling the generation of recommendations without involving users' efforts. Concretely, we identify a set of behavioral features through experimental validation, and develop inference model based on Gaussian Process to unify these features for determining users' big-five personality traits. We then test the model in a collaborative filtering based recommending framework on two real-life movie datasets, which demonstrates that our implicit personality based recommending algorithm significantly outperforms related methods in terms of both rating prediction and ranking accuracy. The experimental results point out an effective solution to boost the applicability of personality-based recommender systems in online environment.
Keywords: Recommender systems; User personality; Implicit acquisition; Collaborative filtering
Note: James Chen Best Student Paper Award
Harnessing Engagement for Knowledge Creation Acceleration in Collaborative Q&A Systems BIBAFull-Text 315-327
  Jie Yang; Alessandro Bozzon; Geert-Jan Houben
Thanks to reputation and gamification mechanisms, collaborative question answering systems coordinate the process of topical knowledge creation of thousands of users. While successful, these systems face many challenges: on one hand, the volume of submitted questions overgrows the amount of new users willing, and capable, of answering them. On the other hand, existing users need to be retained and optimally allocated. Previous work demonstrates the positive effects that two important aspects, namely engagement and expertise valorisation, can have on user quality and quantity of participation. The magnitude of their effect can greatly vary across users and across topics. In this paper we advocate for a more in-depth study of the interplay that exists between user engagement factors in question answering systems. Our working hypothesis is that the process of knowledge creation can be accelerated by better understanding and exploiting the combined effects of the interests and expertise of users, with their intrinsic and extrinsic motivations. We perform a study over 6 years of data from the StackOverflow platform. By defining metrics of expertise and (intrinsic and extrinsic) motivations, we show how they distribute and correlate across platform's users and topics. By means of an off-line question routing experiment, we show how topic-specific combinations of motivations and expertise can help accelerating the knowledge creation process.

Short Presentations

News Recommender Based on Rich Feedback BIBAKFull-Text 331-336
  Liliana Ardissono; Giovanna Petrone; Francesco Vigliaturo
This paper proposes to exploit author-defined tags and social interaction data (commenting and sharing news items) in news recommendation. Moreover it presents a hybrid news recommender which suggest news items on the basis of the reader's short and long-term reading history, taking reading trends and short-term interests into account. The experimental results we carried out provided encouraging results about the accuracy of the recommendations.
Keywords: Hybrid news recommender; Tag-based news specification
News Recommenders: Real-Time, Real-Life Experiences BIBAKFull-Text 337-342
  Doychin Doychev; Rachael Rafter; Aonghus Lawlor; Barry Smyth
In this paper we share our experiences of working with a real-time news recommendation framework with real-world user and data.
Keywords: Real-life experiences; News Recommender Systems
On the Use of Cross-Domain User Preferences and Personality Traits in Collaborative Filtering BIBAKFull-Text 343-349
  Ignacio Fernández-Tobías; Iván Cantador
We present a study comparing collaborative filtering methods enhanced with user personality traits and cross-domain ratings in multiple domains on a relatively large dataset. We show that incorporating additional ratings from source domains allows improving the accuracy of recommendations in a different target domain, and that in certain cases, it is better to enrich user models with both cross-domain ratings and personality trait information.
Keywords: Collaborative filtering; Personality; Cross-domain recommendation
Understanding Real-Life Website Adaptations by Investigating the Relations Between User Behavior and User Experience BIBAKFull-Text 350-356
  Mark P. Graus; Martijn C. Willemsen; Kevin Swelsen
We study how a website adaptation based on segment predictions from click streams affects visitor behavior and user experience. Through statistical analysis we investigate how the adaptation changed actual behavior. Through structural equation modeling of subjective experience we answer why the change in behavior occurred. The study shows the value of using survey data for constructing and evaluating predictive models. It additionally shows how a website adaptation influences user experience and how this in turn influences visitor behavior.
Keywords: Online adaptation; Visitor behavior; User experience; Online behavior; Online segmentation; Structural equation modeling
Modelling the User Modelling Community (and Other Communities as Well) BIBAFull-Text 357-363
  Dario De Nart; Dante Degl'Innocenti; Andrea Pavan; Marco Basaldella; Carlo Tasso
Discovering and modelling research communities' activities is a task that can lead to a more effective scientific process and support the development of new technologies. Journals and conferences already offer an implicit clusterization of researchers and research topics, and social analysis techniques based on co-authorship relations can highlight hidden relationships among researchers, however, little work has been done on the actual content of publications. We claim that a content-based analysis on the full text of accepted papers may lead to a better modelling and understanding of communities' activities and their emerging trends. In this work we present an extensive case study of research community modelling based upon the analysis of over 450 events and 7000 papers.
Personality Correlates for Digital Concert Program Notes BIBAKFull-Text 364-369
  Marko Tkalcic; Bruce Ferwerda; David Hauger; Markus Schedl
In classical music concerts, the concert program notes are distributed to the audience in order to provide background information on the composer, piece and performer. So far, these have been printed documents composed mostly of text. With some delay, mobile devices are making their way also in the world of classical concerts, hence offering additional options for digital program notes comprising not only text but also images, video and audio. Furthermore, these digital program notes can be personalized. In this paper, we present the results of a user study that relates personal characteristics (personality and background musical knowledge) to preferences for digital program notes.
Keywords: Classical music; Digital program notes; Personality
Integrating Context Similarity with Sparse Linear Recommendation Model BIBAKFull-Text 370-376
  Yong Zheng; Bamshad Mobasher; Robin Burke
Context-aware recommender systems extend traditional recommender systems by adapting their output to users' specific contextual situations. Most of the existing approaches to context-aware recommendation involve directly incorporating context into standard recommendation algorithms (e.g., collaborative filtering, matrix factorization). In this paper, we highlight the importance of context similarity and make the attempt to incorporate it into context-aware recommender. The underlying assumption behind is that the recommendation lists should be similar if their contextual situations are similar. We integrate context similarity with sparse linear recommendation model to build a similarity-learning model. Our experimental evaluation demonstrates that the proposed model is able to outperform several state-of-the-art context-aware recommendation algorithms for the top-N recommendation task.
Keywords: Context; Context-aware recommendation; Context similarity

Doctoral Consortium

Modeling Motivational States Through Interpreting Physical Activity Data for Adaptive Robot Companions BIBAFull-Text 379-384
  Elena Corina Grigore
This research aims to develop an adaptive human-robot interaction system that works with users over long periods of time to achieve a common goal that is beneficial to the user. The particular scenario I focus on is that of a robot companion interacting with adolescents, helping them succeed at achieving daily physical activity goals. To develop such a system, I propose a method of modeling the user's motivational state and employing this model in order to adapt motivational strategies best suited for each user. The proposed system uses both physical activity data obtained from wearable sensors (such as wristband devices) and information acquired by the robot from its interaction partners.
Privacy-Enhanced Personalisation of Web Search BIBAKFull-Text 385-390
  Anisha T. J. Fernando
In personalised search, user information needs captured through cookies and Web search history for example, make it possible to infer personal or sensitive information about a person. Although prior studies have established sources of privacy leakage on the Web, there is a need for identifying the sources of data leakage concerning personalised search, its impact on users and on the broader privacy laws and regulations. This research study firstly explores the significance of attributes impacting personalised search and considers whether the extensive collection of personal data is necessary for personalised search results through a series of experiments measuring the impact of personalisation and sources of data leakage. These findings will then be evaluated two-fold: through a qualitative study of users, and assessed for its applicability in the Australian context as per the Australian Privacy Principles. Further, the outcomes from the experimental and user studies will be used to develop a Privacy-Enhancing Technology (PET) that will provide users with options to control personal data leakage whilst searching on the Web and enable proactive protection of individual user privacy.
Keywords: Personalisation; Web search; Data leakage; Search query parameters; Experimental study; Privacy
From Artifact to Content Source: Using Multimodality in Video to Support Personalized Recomposition BIBAKFull-Text 391-396
  Fahim A. Salim
Video content is being produced in ever increasing quantities. It is practically impossible for any user to see every piece of video which could be useful to them. We need to look at video content differently. Videos are composed of a set of features, namely the moving video track, the audio track and other derived features, such as a transcription of the spoken words. These different features have the potential to be recomposed to create new video offerings. However, a key step in achieving such recomposition is the appropriate decomposition of those features into useful assets. Video artifacts can therefore be considered a type of multimodal source which may be used to support personalized and contextually aware recomposition. This work aims to propose and validate an approach which will convert a video from a single artifact into a diverse query-able content source.
Keywords: Personalization; Multimodality; Video analysis; Paralinguistic; User engagement
Exploiting Item and User Relationships for Recommender Systems BIBAFull-Text 397-402
  Zhu Sun
Recommender systems have become a prevalent tool to cope with the information overload problem. The most well-known recommendation technique is collaborative filtering (CF), whereby a user's preference can be predicted by her like-minded users. Data sparsity and cold start are two inherent and severe limitations of CF.