Geert-Jan Houben

Analyzing user modeling on twitter for personalized news recommendations

How can micro-blogging activities on Twitter be leveraged for user modeling and personalization? In this paper we investigate this question and introduce a framework for user modeling on Twitter which enriches the semantics of Twitter messages (tweets) and identifies topics and entities (e.g. persons, events, products) mentioned in tweets. We analyze 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 personalized news recommendation system. Our results reveal how semantic enrichment enhances the variety and quality of the generated user profiles. Further, we see how the different user modeling strategies impact personalization and discover that the consideration of temporal profile patterns can improve recommendation quality.

User Modeling, Adaptation, and Personalization

Interactive technologies pervade every aspect of modern life. Web sites, mobile devices, household gadgets, automotive controls, aircraft flight decks; everywhere you look, people are interacting with technologies. This trend is set to continue as we move towards a world comprising Smart Cities built around the Internet of Things. Unfortunately, much of the rhetoric surrounding this dawning age of ubiquitous and embedded computing fails to appropriately consider the people at the centre of it. These people are embodied social agents with motivations, emotions, capabilities, capacities, proclivities and predilections. Technological imaginings around the Internet of Things are often steeped in generalities or idealised scenarios of use. Such imaginings typically forget that design is always about meeting particular peoples’ needs in particular contexts. From concept to ideation to prototype and evaluation, the design of interactive technologies and systems that are intended for people should start with some understanding of who the users will be, what tasks and experiences they are aiming for, and what the circumstances, conditions or context(s) are at play. In this talk, I will discuss a simple people-centric framework devised with my colleagues and coauthors to inform the way we think about design, the ABCS of designing interactive systems. A descriptive guide rather than a prescriptive checklist, the framework draws on basic research in ergonomics, psychology and user modeling. It is intended to focus design thinking about people as the users of interactive, computational systems. It is intended to support us as the designers of interactive technologies as we scope, draft and iterate on the design space of imagined interactive experiences. Using examples from my own work, I will illustrate how this framework has been explicitly and/or tacitly applied in the design, development and evaluation of interactive, multimedia systems. In particular, I will consider how this framework is currently being applied to rethinking the concept of personalization.

Semantic enrichment of twitter posts for user profile construction on the social web

As the most popular microblogging platform, the vast amount of content on Twitter is constantly growing so that the retrieval of relevant information (streams) is becoming more and more difficult every day. Representing the semantics of individual Twitter activities and modeling the interests of Twitter users would allow for personalization and therewith countervail the information overload. Given the variety and recency of topics people discuss on Twitter, semantic user profiles generated from Twitter posts moreover promise to be beneficial for other applications on the Social Web as well. However, automatically inferring the semantic meaning of Twitter posts is a non-trivial problem. In this paper we investigate semantic user modeling based on Twitter posts. We introduce and analyze methods for linking Twitter posts with related news articles in order to contextualize Twitter activities. We then propose and compare strategies that exploit the semantics extracted from both tweets and related news articles to represent individual Twitter activities in a semantically meaningful way. A large-scale evaluation validates the benefits of our approach and shows that our methods relate tweets to news articles with high precision and coverage, enrich the semantics of tweets clearly and have strong impact on the construction of semantic user profiles for the Social Web.

A comparative study of users' microblogging behavior on sina weibo and twitter

In this article, we analyze and compare user behavior on two different microblogging platforms: (1) Sina Weibo which is the most popular microblogging service in China and (2) Twitter. Such a comparison has not been done before at this scale and is therefore essential for understanding user behavior on microblogging services. In our study, we analyze more than 40 million microblogging activities and investigate microblogging behavior from different angles. We (i) analyze how people access microblogs and (ii) compare the writing style of Sina Weibo and Twitter users by analyzing textual features of microposts. Based on semantics and sentiments that our user modeling framework extracts from English and Chinese posts, we study and compare (iii) the topics and (iv) sentiment polarities of posts on Sina Weibo and Twitter. Furthermore, (v) we investigate the temporal dynamics of the microblogging behavior such as the drift of user interests over time. Our results reveal significant differences in the microblogging behavior on Sina Weibo and Twitter and deliver valuable insights for multilingual and culture-aware user modeling based on microblogging data. We also explore the correlation between some of these differences and cultural models from social science research.

Cross-system user modeling and personalization on the Social Web

In order to adapt functionality to their individual users, systems need information about these users. The Social Web provides opportunities to gather user data from outside the system itself. Aggregated user data may be useful to address cold-start problems as well as sparse user profiles, but this depends on the nature of individual user profiles distributed on the Social Web. For example, does it make sense to re-use Flickr profiles to recommend bookmarks in Delicious? In this article, we study distributed form-based and tag-based user profiles, based on a large dataset aggregated from the Social Web. We analyze the completeness, consistency and replication of form-based profiles, which users explicitly create by filling out forms at Social Web systems such as Twitter, Facebook and LinkedIn. We also investigate tag-based profiles, which result from social tagging activities in systems such as Flickr, Delicious and StumbleUpon: to what extent do tag-based profiles overlap between different systems, what are the benefits of aggregating tag-based profiles. Based on these insights, we developed and evaluated the performance of several cross-system user modeling strategies in the context of recommender systems. The evaluation results show that the proposed methods solve the cold-start problem and improve recommendation quality significantly, even beyond the cold-start.

Twitcident: fighting fire with information from social web streams

In this paper, we present Twitcident, a framework and Web-based system for filtering, searching and analyzing information about real-world incidents or crises. Twitcident connects to emergency broadcasting services and automatically starts tracking and filtering information from Social Web streams (Twitter) when a new incident occurs. It enriches the semantics of streamed Twitter messages to profile incidents and to continuously improve and adapt the information filtering to the current temporal context. Faceted search and analytical tools allow users to retrieve particular information fragments and overview and analyze the current situation as reported on the Social Web. Demo: http://wis.ewi.tudelft.nl/twitcident/

Index structures and algorithms for querying distributed RDF repositories

A technical infrastructure for storing, querying and managing RDFdata is a key element in the current semantic web development. Systems like Jena, Sesame or the ICS-FORTH RDF Suite are widelyused for building semantic web applications. Currently, none ofthese systems supports the integrated querying of distributed RDF repositories. We consider this a major shortcoming since the semanticweb is distributed by nature. In this paper we present an architecture for querying distributed RDF repositories by extending the existing Sesame system. We discuss the implications of our architectureand propose an index structure as well as algorithms forquery processing and optimization in such a distributed context.

Analyzing temporal dynamics in Twitter profiles for personalized recommendations in the social web

Social Web describes a new culture of participation on the Web where more and more people actively participate in publishing and organizing Web content. As part of this culture, people leave a variety of traces when interacting with (other people via) Social Web systems. In this paper, we investigate user modeling strategies for inferring personal interest profiles from Social Web interactions. In particular, we analyze individual micro-blogging activities on Twitter. We compare different strategies for creating user profiles based on the Twitter messages a user has published and study how these profiles change over time. Moreover, we evaluate the quality of the user modeling strategies in the context of personalized recommender systems and show that those strategies which consider the temporal dynamics of the individual profiles allow for the best performance.

Semantics + filtering + search = twitcident. exploring information in social web streams

Automatically filtering relevant information about a real-world incident from Social Web streams and making the information accessible and findable in the given context of the incident are non-trivial scientific challenges. In this paper, we engineer and evaluate solutions that analyze the semantics of Social Web data streams to solve these challenges. We introduce Twitcident, a framework and Web-based system for filtering, searching and analyzing information about real-world incidents or crises. Given an incident, our framework automatically starts tracking and filtering information that is relevant for the incident from Social Web streams and Twitter particularly. It enriches the semantics of streamed messages to profile incidents and to continuously improve and adapt the information filtering to the current temporal context. Faceted search and analytical tools allow people and emergency services to retrieve particular information fragments and overview and analyze the current situation as reported on the Social Web. We put our Twitcident system into practice by connecting it to emergency broadcasting services in the Netherlands to allow for the retrieval of relevant information from Twitter streams for any incident that is reported by those services. We conduct large-scale experiments in which we evaluate (i) strategies for filtering relevant information for a given incident and (ii) search strategies for finding particular information pieces. Our results prove that the semantic enrichment offered by our framework leads to major and significant improvements of both the filtering and the search performance. A demonstration is available via: http://wis.ewi.tudelft.nl/twitcident/

Leveraging the semantics of tweets for adaptive faceted search on twitter

In the last few years, Twitter has become a powerful tool for publishing and discussing information. Yet, content exploration in Twitter requires substantial effort. Users often have to scan information streams by hand. In this paper, we approach this problem by means of faceted search. We propose strategies for inferring facets and facet values on Twitter by enriching the semantics of individual Twitter messages (tweets) and present different methods, including personalized and context-adaptive methods, for making faceted search on Twitter more effective. We conduct a large-scale evaluation of faceted search strategies, show significant improvements over keyword search and reveal significant benefits of those strategies that (i) further enrich the semantics of tweets by exploiting links posted in tweets, and that (ii) support users in selecting facet value pairs by adapting the faceted search interface to the specific needs and preferences of a user.