Entrepôts, Représentation et Ingénierie des Connaissances
Publications du laboratoire

Recherche approfondie

par Année
par Auteur
par Thème
par Type
- CATS: Collection and Analysis of Tweets Made Simple doi link

Auteur(s): Truică C.-O., Guille A., Gauthier Michael

Conference: ACM CSCW 2016 (San Francisco, US, 2016-02-26)
Actes de conférence: Proceedings of the 19th ACM Conference on Computer Supported Cooperative Work and Social Computing Companion, vol. p.41-44 ()

Ref HAL: hal-01442850_v1
DOI: 10.1145/2818052.2874320

Twitter presents an unparalleled opportunity for researchers from various fields to gather valuable and genuine textual data from millions of people. However, the collection pro-cess, as well as the analysis of these data require different kinds of skills (e.g. programing, data mining) which can be an obstacle for people who do not have this background. In this paper we present CATS, an open source, scalable, Web application designed to support researchers who want to carry out studies based on tweets. The purpose of CATS is twofold: (i) allow people to collect tweets (ii) enable them to analyze these tweets thanks to efficient tools (e.g. event detection, named-entity recognition, topic modeling, word-clouds). What is more, CATS relies on a distributed imple-mentation which can deal with massive data streams.