IRIT at TREC Microblog 2015

Abdelhamid Chellal (1) , Lamjed Ben Jabeur (1) , Laure Soulier (1) , Bilel Moulahi (1) , Thomas Palmer (1) , Mohand Boughanem (1, 2) , Karen Pinel-Sauvagnat (1) , Lynda Tamine (1) , Gilles Hubert (1)

1 IRIT-SIG - Systèmes d’Informations Généralisées
2 UT3 - Université Toulouse III - Paul Sabatier

This paper presents the participation of the IRIT laboratory (University of Toulouse) to the Microblog Track of TREC 2015. This track consists in a real-time filtering task aiming at monitoring a stream of social media posts in accordance to a user's interest profile. In this context, our team proposes three approaches: (a) a novel selective summarization approach based on a decision of selecting/ignoring tweets without the use of external knowledge and relying on novelty and redundancy factors, (b) a processing workflow enabling to index tweets in real-time and enhanced by a notification and digests method guided by diversity and user personalization, and (c) a step by step stream selection method focusing on rapidity, and taking into account tweet similarity as well as several features including content, entities and user-related aspects. For all these approaches, we discuss the obtained results during the experimental evaluation.

Mots clés: Clustering; User profile; Rapidity; Novelty; Filtering; Personalization; Entities; Redundancy; Social media; Real-time

Domaines: Théorie de l'information [cs.IT]; Recherche d'information [cs.IR]

Abdelhamid Chellal, Lamjed Ben Jabeur, Laure Soulier, Bilel Moulahi, Thomas Palmer, et al.. IRIT at TREC Microblog 2015. 34th Text REtrieval Conference (TREC 2015), Nov 2015, Gaithersburg, MD, United States. ⟨hal-01290136⟩