*** Apologies for cross postings *** ExUM Workshop @UMAP 2021 - SECOND CALL FOR PAPERS ---------------------------------------------------------------------- Workshop on Explainable User Models and Personalised Systems (ExUM@UMAP 2021) June 21-25, 2020 co-located with UMAP 2021 (https://www.um.org/umap2021/) - Online from Utrecht, the Netherlands Twitter: https://twitter.com/ExUM_Workshop Web: http://www.di.uniba.it/~swap/exum/ Submission: https://easychair.org/my/conference?conf=acmumap2021# (select "Workshop-ExUM") For any information: cataldo.musto@uniba.it<mailto:cataldo.musto@uniba.it>, marco.polignano@uniba.it<mailto:marco.polignano@uniba.it> ================ IMPORTANT DATES =============== * Full paper submission: March 26, 2021 * Paper notification: April 19, 2021 * Camera-ready paper: May 7, 2021 ======================== COVID-19 STATUS - UPDATE ======================== The 29th Conference on User Modeling, Adaptation and Personalization will be a virtual conference. We are still figuring out all the details, which we hope to announce bit by bit during the next couple of months. Stay tuned for further updates. ========= ABSTRACT ========= Adaptive and personalized systems have become pervasive technologies which are gradually playing an increasingly important role in our daily lives. Indeed, we are now used to interact every day with algorithms that help us in several scenarios, ranging from services that suggest us music to be listened to or movies to be watched, to personal assistants able to proactively support us in complex decision-making tasks. As the importance of such technologies in our everyday lives grows, it is fundamental that the internal mechanisms that guide these algorithms are as clear as possible. It is not by chance that the recent General Data Protection Regulation (GDPR) emphasized the users’ right to explanation when people face machine learning-based (or more in general - artificial intelligence-based) systems. Unfortunately, the current research tends to go in the opposite direction, since most of the approaches try to maximize the effectiveness of the personalization strategy (e.g., recommendation accuracy) at the expense of the explainability and the transparency of the model. The main research questions which arise from this scenario is simple and straightforward: how can we deal with such a dichotomy between the need for effective adaptive systems and the right to transparency and interpretability? Several research lines are triggered by this question: building scrutable user models and transparent al-gorithms, analyzing the impact of opaque algorithms on final users, studying the role of explanation strategies, investigating how to provide users with more control in the personalization and adaptation problems. The workshop aims to provide a forum for discussing such problems, challenges and innovative re-search approaches in the area, by investigating the role of transparency and explainability on the re-cent methodologies for building user models or for developing personalized and adaptive systems. ====== TOPICS ====== Topics of interests include but are not limited to: - TRANSPARENT AND EXPLAINABLE PERSONALIZATION STRATEGIES - Scrutable User Models - Transparent User Profiling and Personal Data Extraction - Explainable Personalization and Adaptation Methodologies - Novel strategies (e.g., conversational recommender systems) for building transparent algorithms - DESIGNING EXPLANATION ALGORITHMS - Explanation algorithms based on item description and item properties - Explanation algorithms based on user-generated content (e.g., reviews) - Explanation algorithms based on collaborative information - Building explanation algorithms for opaque personalization techniques (e.g., neural networks, matrix factorization) - DESIGNING TRANSPARENT AND EXPLAINABLE USER INTERFACES - Transparent User Interfaces - Designing Transparent Interaction methodologies - Novel paradigms (e.g. chatbots) for building transparent models - EVALUATING TRANSPARENCY AND EXPLAINABILITY - Evaluating Transparency in interaction or personalization - Evaluating Explainability of the algorithms - Designing User Studies for evaluating transparency and explainability - Novel metrics and experimental protocols - OPEN ISSUES IN TRANSPARENT AND EXPLAINABLE USER MODELS AND PERSONALIZED SYSTEMS - Ethical issues (Fairness and Biases) in User Models and Personalized Systems - Privacy management of Personal and Social data - Discussing Recent Regulations (GDPR) and future directions ============ SUBMISSIONS ============ We encourage the submission of original contributions, investigating novel methodologies to exploit heterogeneous personal data and approach to build transparent and scrutable user models. (A) Regular papers (max. 10 pages + references - single-column ACM format); (B) Demo and Position Papers (max. 5 pages + references - ACM format); Submission site: https://easychair.org/my/conference?conf=acmumap2021# (select "Workshop-ExUM") All submitted papers will be evaluated by at least two members of the program committee, based on originality, significance, relevance and technical quality. Note that the references do not count towards page limits. Submissions should be single blinded, i.e. authors names should be included in the submissions. Papers must be formatted according to the new workflow for ACM publications. The templates and instructions are available here: https://www.acm.org/publications/taps/word-template-workflow. Authors should submit their papers as single-column. The templates are available here (we strongly recommend the usage of LaTeX for the camera-ready papers to minimize the extent of reformatting): * LaTeX (use \documentclass[manuscript,review,anonymous]{acmart} in the sample-authordraft.tex file for single-column): https://www.acm.org/binaries/content/assets/publications/consolidated-tex-te... * Overleaf (use \documentclass[manuscript,review,anonymous]{acmart} for single-column): https://www.overleaf.com/latex/templates/acm-conference-proceedings-master-t... * MS Word: https://www.acm.org/binaries/content/assets/publications/taps/acm_submission... Submissions must be made through the EasyChair conference system prior the specified deadline (AoE). All accepted papers will be published by ACM as a joint volume of Extended UMAP 2021 Proceedings and will be available via the ACM Digital Library. At least one author of each accepted paper must register for the particular workshop and present the paper there. ============= ORGANIZATION ============= Cataldo Musto - University of Bari, Italy Nava Tintarev - Maastricht University, The Netherlands Oana Inel - Delft University of Technology, The Netherlands Marco Polignano - University of Bari, Italy Giovanni Semeraro - University of Bari, Italy Juergen Ziegler - University of Duisburg Essen