Two half-day tutorials will be presented at UMAP'2016. 

T1: Semantics-Aware Techniques for Social Media Analysis, User Modeling, and Recommender Systems

Pasquale Lops and Cataldo Musto (University of Bari Aldo Moro, Italy) 

Since the creation of the World Wide Web and with the advent of the Social Web - where almost any user can create and share content of different types – there was an exponential growth of the online information which gave new life to the research in the area of user modelling and recommender systems. Many information about user preferences can be also obtained by mining data gathered from many heterogeneous sources, such as the content posted by people on social networks and microblogs, in order to unveil latent information about their interests, automatically extract people personality traits, build preference models on the ground of textual reviews, and so on. At the same time, the recent phenomenon of (Linked) Open Data fueled this research line by making available a huge amount of machine-readable textual data.
However, a complete exploitation of such textual data requires a comprehension of the information conveyed by people and in turn, this requires a deep understanding of the language, which is not Hence, novel research works have introduced semantic techniques able to deal with the classical problems of simple keyword-based approaches by means of concept-based representations of items. The goal of this tutorial is to provide a broad overview of semantic techniques for enhanced content representations, some of which having their roots in NLP foundations, to build a new generation of semantics-aware services for user modeling, personalization and recommendation.

Intended audience: This tutorial will benefit researchers and practitioners with broad interest in user modeling and recommender systems, who are willing to have a whole picture of advanced semantics-aware techniques for building advanced and intelligent services for user modeling and recommender systems. The technical level of the tutorial will be intermediate.

Pasquale Lops is Assistant Professor at the Department of Computer Science, University of Bari Aldo Moro, Italy. He received the Ph.D. in Computer Science from the University of Bari in 2005 with a dissertation on “Hybrid Recommendation Techniques based on User Profiles”. His research interests include recommender systems, machine learning and user modelling. He authored over 120 articles published in international journals, international collections, proceedings of national and international conferences and workshops, and book chapters. He participated in more than 20 funded research projects. He is Area Chair of User Modelling for Recommender Systems at the International Conference on User Modeling, Adaptation and Personalization 2016, and Senior Program Committee member of the ACM Conference on Recommender Systems since 2014. He co-organized several workshops related to user modeling and recommender systems.

Personal web site: http://www.di.uniba.it/~swap/lops.html   Google Scholar profile: http://scholar.google.com/citations?user=1MHRACkAAAAJ

Cataldo Musto is Assistant Professor at the Department of Computer Science, University of Bari Aldo Moro, Italy. He completed his Ph.D. in 2012 with a dissertation on “Enhanced Vector Space Models for Content-based Recommender Systems”. His research focuses on the adoption of machine learning and natural language processing techniques for semantic content representation in recommender system, user modeling, and intelligent adaptive platforms. He was an invited speaker at the workshop on Semantic Adaptive and Social Web (SASWeb) at UMAP 2012 and at the first workshop on Financial Recommender Systems (FINREC 2015). He has published over 50 papers and served as reviewer or co-reviewer in the Program Committee of several conferences in the area as ACM Recommender Systems, ECIR, UMAP and WWW.

Personal web site: http://www.di.uniba.it/~swap/musto   Google Scholar profile: https://scholar.google.com/citations?user=pauGgdYAAAAJ&hl=it

T2: Games, gamification and personalization

Amon Rapp (University of Torino, Italy)

Games largely impact on players’ experience through their designs, by retaining them in the game world, modifying their habits and involving so that they can become addicted to them. For these reasons games have been largely used for behavior change interventions in the health, sustainability and wellness domains. One of the key for producing an engaging player experience in games is personalization: games are personalized on the basis of the players’ personalities, play styles, skills, and so on. This fundamental factor in games, however, is still not widely exploited in one of the most recent and popular techniques that uses game elements for behavior change purposes. Gamification, a design method that employs game elements in non-game contexts, aims at reproducing the effects of games even in non-game applications and services. Aim of this tutorial is providing an overview on how games implement personalized features and how they impact on players’ experience. Then, we will outline how games can be used for behavior change purposes. Among these opportunities we will focus on gamification, as a novel design technique able to affect users’ motivation and behavior. We will illustrate how gamification works, grounding it in behavior change theories. Finally, we will explore how gamification can implement personalization in its designs.

Learning objectives.

- to learn about personalization in games

- to be aware of the most important work in the state of the art and the evolution in the field of games used for behavior change

- to learn about gamification and its potentialities for design

- to experiment with some design techniques for producing personalized gamified services

Amon Rapp is a research fellow at the Computer Science Department at University of Torino, where he is a member of the Smart Interactive Objects and Systems group. He is currently the head of the Smart Personal Technology Lab at ICxT (Center for Innovation for Society and Territory). His main research interests are related to behavior change technologies, gamification and game design, and personal informatics. His research activity resulted in the organization of different workshops: “LinkQS” at Hypertext 2014 and “"New Frontiers of Quantified Self" at UBICOMP 2015. He teaches as an adjunct professor the Psychology of Human-Technology Interaction course at the Psychology Master Degree in the University of Torino. He served as a program committee member for several conferences and workshops in the field and was Session Chair at IEEE CIVEMSA Conference 2014 (Brain-Computer Interfaces Session), COIOTE Cognitive Internet of Things Technologies Conference (Affordances in Internet of Things Session) 2016, and HCI International 2016 (Quantified Self & Personal Informatics parallel session).