Mining Tweet Data - Statistic and semantic information for political tweet classification

Tisserant Guillaume, Roche Mathieu, Prince Violaine. 2014. Mining Tweet Data - Statistic and semantic information for political tweet classification. In : Proceedings of the 6th International Conference on Knowledge Discovery and Information Retrieval : KDIR 2014, Rome, Italy, 21-24 October, 2014. s.l. : s.n., 523-529. International Conference on Knowledge Discovery and Information Retrieval. 6, Rome, Italie, 21 Octobre 2014/24 Octobre 2014.

Résumé : This paper deals with the quality of textual features in messages in order to classify tweets. The aim of our study is to show how improving the representation of textual data affects the performance of learning algorithms. We will first introduce our method GENDESC. It generalizes less relevant words for tweet classification. Secondly, we compare and discuss the types of textual features given by different approaches. More precisely we discuss the semantic specificity of textual features, e.g. Named Entities, HashTags.

Classification Agris : C30 - Documentation et information
U10 - Informatique, mathématiques et statistiques
000 - Autres thèmes

Auteurs et affiliations

• Tisserant Guillaume, LIRMM (FRA)
• Roche Mathieu, CIRAD-ES-UMR TETIS (FRA) ORCID: 0000-0003-3272-8568
• Prince Violaine, LIRMM (FRA)

Source : Cirad - Agritrop (https://agritrop.cirad.fr/575281/)

Métriques

[ Page générée et mise en cache le 2022-04-28 ]