Prof. Geert-Jan Houben,TU Delft, The Netherlands
In this talk, we discuss how micro-blogging activities on Twitter can be leveraged for user modeling and personalisation. We investigate this challenge and introduce a framework for user modeling on Twitter which enriches the semantics of Twitter messages (tweets) and identies topics and entities (e.g. persons, events, products) mentioned in tweets. We analyse how strategies for constructing hashtag-based, entity-based or topic-based user profiles benefit from semantic enrichment and explore the temporal dynamics of those profiles. We further measure and compare the performance of the user modeling strategies in context of a personalised news recommendation system. Our results reveal how the different user modeling strategies impact personalization and discover that the consideration of temporal
profile patterns can improve recommendation quality. We also take a look at some applications that follow from this work, e.g. in the areas of crises management and culture-based adaptation. In the area of cultural differences we report on a study in which we analyse and compare user behaviour on two different microblogging platforms: (1) Sina Weibo which is the most popular microblogging service in China and (2) Twitter. We analyse more than 40 million microblogging activities and investigate microblogging behaviour from different angles. Our results reveal significant differences in the microblogging behaviour on Sina Weibo and Twitter and deliver valuable insights for multilingual and culture-aware user modelling based on microblogging data.
Local: Sala RDC511,
Data: 16/08 das 14 às 16horas