Harnessing Diversity in User Generated Content to Empower Adaptation and Personalisation
- Speaker: Vania Dimitrova, Associate Professor at the School of Computing, the University of Leeds.
- Date: Wednesday, 25 March 2015 from 13:30
- Location: Room 151, Birkbeck Main Building
User-adaptive systems are intelligent interactive systems that can adapt themselves to the users by using some model of the user which is derived from analysing interaction data. These systems enable personalisation, i.e. creating unique interaction experiences tailored to individuals' specific needs and requirements. This talk will focus on a dimension of personalisation - awareness of the cultural diversity of users – which has been given little attention so far. As shown in numerous cases, cultural ignorance in business can result in big financial losses while it can lead to segregation and isolation in the public sphere. Yet, current user-adaptive systems are culturally ignorant, at most merely translating into different languages. Within the context of cultural diversity, I will discuss two well-known challenges to user modelling and personalisation, namely ‘cold start’ (the system has not yet gathered sufficient information about the user and cannot run proper adaptation) and ‘filter bubble’ (tendency to give users things they like or are familiar with). I will show how these challenges have been addressed at Leeds by exploiting semantic techniques and approaches to harness diversity in user generated content. The talk will be a reflection on the research journey of the recently finished EU project (ImREAL: www.imreal-project.eu), drawing lessons learnt and pointing at future directions for harnessing diversity to empower user-adaptive systems.
Vania Dimitrova is an Associate Professor at the School of Computing, the University of Leeds, UK. She is a member of the Artificial Intelligence Group where she leads the research activity on user-adaptive intelligent systems, focusing on knowledge-enriched user modelling and adaptation, crowdwisdom, interactive data exploration, knowledge capture and ontological modelling. She has co-authored more than 100 papers, many of which are presented at key conferences and journals in intelligent learning and user adaptive systems. She chaired the premier international conferences on user modelling (UMAP) and intelligent learning environments (AIED, ECTEL), as well as a series of international workshops on key topics related to user modelling, social systems, and intelligent data exploration. She is a member of the editorial boards of the personalisation journal (UMUAI) and the International Journal on Artificial Intelligence in Education (IJAIED). She was an associate editor of IEEE Transactions on Learning Technologies (IEEE-TLT) and served on the advisory board for the UK programme in technology-enhanced learning. She led the Leeds research activities in several interdisciplinary projects, and coordinated the recently completed EU project ImREAL (http://www.imreal-project.eu) which developed intelligent services to link experience in virtual learning environments with experience in the real world.