Abstract
The proceedings contain 49 papers. The special focus in this conference is on User modeling, adaptation, and personalization. The topics include: modelling long term goals; a personalization method based on human factors for improving usability of user authentication tasks; the magic barrier of recommender systems - no magic, just ratings; toward fully automated person-independent detection of mind wandering; hybrid recommendation in heterogeneous networks; recommendation based on contextual opinions; user partitioning hybrid for tag recommendation; predicting user locations and trajectories; a two-stage item recommendation method using probabilistic ranking with reconstructed tensor model; time-sensitive user profile for optimizing search ersonlization; a computational model for mood recognition; privacy and user trust in context-aware systems; hoeffding-CF: neighbourhood-based recommendations on reliably similar users; toward a personalized approach for combining document relevance estimates; adaptive support versus alternating worked examples and tutored problems: which leads to better learning?; te,te,hi,hi: eye gaze sequence analysis for informing user-adaptive information visualizations; text-based user-knn: measuring user similarity based on text reviews; using DBpedia as a knowledge source for culture-related user modelling questionnaires; eye tracking to understand user differences in visualization processing with highlighting interventions; evil twins: modeling power users in attacks on recommender systems; personality profiling from text: introducing part-of-speech N-grams; collaborative compound critiquing; sparrows and owls: characterisation of expert behaviour in stackoverflow; generalizability of goal recognition models in narrative-centered learning environments and extending log-based affect detection to a multi-user virtual environment for science.