Fernando Samuel Peregrino

Every move you make I'll be watching you: geographical focus detection on Twitter

On-line Social Networks have increased their popularity rapidly since their creation, providing a huge amount of data which can be leverage to extract useful information related to commercial and social human behaviours. One of the most useful information that can be extracted is the geographical one. This paper shows an approach to detect the geographical focus of Twitter users at city level based on the text of the tweets that users have sent and external information from Wikipedia. The main goal of this work is to show how important could be external formal text resources such as Wikipedia when it comes to resolve the geographical focus in short pieces of informal natural language text. In order to accomplish this objective, we have assessed our system with a language model system, comparing the results using only the informal pieces of text (tweets) and merging it with formal text coming from Wikipedia. In our experiments, we found that the aid of formal pieces of text, such as those obtained from the Wikipedia articles and links, could be useful when the existing amount of data is rather limited.

Question answering and multi-search engines in geo-temporal information retrieval

In this paper we present a complete system for the treatment of both geographical and temporal dimensions in text and its application to information retrieval. This system has been evaluated in both the GeoTime task of the 8th and 9th NTCIR workshop in the years 2010 and 2011 respectively, making it possible to compare the system to contemporary approaches to the topic. In order to participate in this task we have added the temporal dimension to our GIR system. The system proposed here has a modular architecture in order to add or modify features. In the development of this system, we have followed a QA-based approach as well as multi-search engines to improve the system performance.