Tutorials will take place on Sunday, July 9, 2017.
T 10. SEMANTICS-AWARE TECHNIQUES FOR SOCIAL MEDIA ANALYSIS, USER MODELLING, AND RECOMMENDER SYSTEMS
Pasquale Lops, Cataldo Musto
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 fuelled this research line by making available a huge amount of machine-readable textual data.
A complete exploitation of such data requires a comprehension of the information conveyed by people and in turn, this requires a deep understanding of the language, which is not trivial. 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 and user profiles.
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.
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.
Google Scholar profile:
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 was 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.
Google Scholar profile:
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.
T 11. Designing Cross-Space Learning Analytics and Personalised Support
Roberto Martinez-Maldonado, Abelardo Pardo and Davinia Hernandez-Leo
In this tutorial, participants will explore the challenges of designing data-intensive solutions to support students in blended learning scenarios through collaborative prototyping. We recognise that student’s learning happens where the learner is, rather than being constrained to a single physical or digital environment. In fact, students commonly interact at diverse physical spaces and with a variety of educational tools.
Specifically, this tutorial explores a number of issues such as defining the short-term future vision of ubiquitous and pervasive learning support, dealing with heterogeneous data, collecting multimodal sources of student’s data beyond clickstreams andacknowledging potential ethical issues that may arise. By bringing together researchers, practitioners, designers and makers in an intense but reflective half a day of prototyping cross-space learning analytics and personalisation experiences, we believe this tutorial will advance the development of a vision of the kind of work that needs to be done to make real progress in this critical area of learning support across spaces.
We will conduct a half a day tutorial with at most 20 participants from the sub-community of UMAP researchers interested in ubiquitous, mobile and/or face-to-face learning analytics, and learning scientists and researchers from other communities who have explored the perspective of learning across spaces.
This tutorial is associated with similar workshops organised by Davinia Hernandez-Leo in 2011 (AcrossSpaces held in at ECTEL 2011), Roberto Martinez-Maldonado in 2012 (DECL 2012 held at ICLS 2012) and by all the co-authors in LAK 2016 and 2017 (CrossLAK).
Roberto Martinez-Maldonado is an Educational Data Science Research Fellow in the Connected Intelligence Centre at University of Technology Sydney, Australia. He has done research grounded on principles of HCI, CSCL, Educational Data Mining and Learning Analytics. He has co-organised five international research workshops at ICLS 2012, CSCL 2013, ITS 2014 and AIED 2015.
Personal web site:
Davinia Hernandez-Leo is Associate Professor, and head of her Teaching Support Unit at the Universitat Pompeu Fabra, Spain. Her research lies at the intersection of network and computer applications, HCI, and the learning sciences, with a special focus on CSCL, learning design and learning architectures.
Abelardo Pardo is Associate Professor in the Faculty of Engineering and IT at The University of Sydney, Australia . His areas of research are learning analytics, software tools for collaboration and personalized learning, and systems to improve teaching practice and student experience.