Résumé

Les réseaux sociaux sont au centre des communications sur internet et une grande

Abstract

Social networks are central in nowadays internet communication and community exchanges. The emergence of Twitter led to the creation of a new tool for sharing information, where messages are bound to 140 characters. Publications on this social network are short and straightforward and often sent in real time from mobile phones, which make it difficult to appre- hend without some kind of context. We propose in this paper a method allowing to automatically contextualize Tweets by using information coming from Wikipedia. We treat this problem as an automatic summarization task, where the text to resume is composed of Wikipedia articles that discuss the various pieces of information appearing in a Tweet. We explore the influence of var- ious Tweet-related articles retrieval methods as well as several features for sentence extraction. We evaluate our approach using the test collection from the INEX 2012 Tweet Contextualization track and provide some insights on what makes a contextually important sentence.