Information Retrieval (IR) is finding content of an unstructured nature with respect to an information need. A retrieval system typically uses a retrieval model to rank the available content by their estimated relevance to an information need. For decades, state-of-the-art retrieval models have used the assumption that terms appear independently in text documents. Chapter 1 of this thesis describes how the relevance likelihood of a document changes by the observed distance between co-occurring query terms in its text. Nowadays, news is abundantly available online, allowing users to discover and follow news events. However, online news is often very redundant; most sources basing their stories on previously published works and add only limited new information. Thus, a user often ends up spending significant amount of effort re-reading the same parts of a story before finding relevant and novel information. In Chapter 2 and Chapter 3, we present a novel approach to construct an online news summary for a given topic. Salient sentences are identified by clustering the sentences in the news stream based on the relative proximity of the sentences and the temporal proximity of their publication times. To improve the coherence of a long summary that describes a news topic, we propose to automatically cluster sentences by subtopics in Chapter 4. In Chapter 5, we show how new topics can be detected in the news stream using the same clustering technique. In real-life decision making, people are often faced with an overload of choices. A recommender system aids the user by reducing the available choices to a shortlist of items that are of interest to the user. In Chapter 6, we learn high-dimensional representations for movies that allow to effectively recommend movies based on a user’s most recently rated movies.@en

This thesis carried out two major investigations on how the geographical information generated by users in social media can be used to model and predict human behaviours. The first investigation regards the mobility patterns of social media users, which utilizes the relations between geographical information and other sources of information, e.g., textual information and temporal information (Chapter 3) as well as users' trajectory patterns, in predicting the locations of users' future visits (Chapter 4). The experimental results confirm the predictability of human movement and the proposed methods for predicting users' locations are demonstrated to outperform the state-of-the-art via evaluations with the data collected from social media platforms (Twitter and Foursquare). The second investigation regards the geo-knowledge that users may gain from physical visits to locations (Chapter 5). The thesis first presented a discussion on how such knowledge can be modelled from users' check-in posts on social media and then approached this problem from both theoretical and practical points of view. Probabilistic models were built and tested via a configurable system on which all the models were implemented. To evaluate the proposed models, a data set of ground truth was collected by annotation from two different sources (i.e., a crowdsourcing platform and university students/staff). The evaluation show that the proposed models outperform the approaches from related research.@en