Diversifying contextual suggestions from location-based social networks

In this paper, we study the emerging Information Retrieval (IR) task of contextual suggestion in location-based social networks. The aim of this task is to make personalised recommendations of venues for entertainments or activities whilst visiting a city, by appropriately representing the context of the user, such as their location and personal interests. Instead of only representing the specific low-level interests of a user, our approach is driven by estimates of the high-level categories of venues that the user may be interested in. Moreover, we argue that an effective model for contextual suggestion should not only promote the categories that the user is interested in, but it should also be capable of eliminating redundancy by diversifying the recommended venues in the sense that they should cover various categories of interest to the given user. Therefore, we adapt web search result diversification approaches to the task of contextual suggestion. For categorising the venues, we use the category classifications employed by location-based social networks such as FourSquare, urban guides such as Yelp, and a large collection of web pages, the ClueWeb12 corpus, to build a textual classifier that is capable of predicting the category distribution for a certain venue given its web page. We thoroughly evaluate our approach using the TREC 2013 Contextual Suggestion track. We conduct a number of experiments where we consider venues from the closed environments of both FourSquare and Yelp, and the general web using the ClueWeb12 corpus. Our empirical results suggest that category diversification consistently improves the effectiveness of the recommendation model over a reasonable baseline that only considers the similarity between the user's profile and venue. The results also give insights on the effectiveness of our approach with different types of users.