Compressed Sensing Classification in Online Social Networks

Abstract : In this technical report we introduce a novel low dimensional method to perform topic detection and classification in Twitter. The proposed method first employs Joint Complexity to perform topic detection. Then, based on the nature of the data, we apply the theory of Compressive Sensing to perform topic classification by recovering an indicator vector, while reducing significantly the amount of information from tweets. We exploit datasets in various languages collected by using the Twitter streaming API, and achieve increased classification accuracy when comparing to state-of-the-art methods based on bag-of-words, along with several reconstruction techniques.
Type de document :
Pré-publication, Document de travail
Columbia University, New York. 2014
Liste complète des métadonnées

https://hal-polytechnique.archives-ouvertes.fr/hal-01299628
Contributeur : Dimitrios Milioris <>
Soumis le : vendredi 8 avril 2016 - 04:04:09
Dernière modification le : jeudi 9 février 2017 - 15:17:16
Document(s) archivé(s) le : lundi 14 novembre 2016 - 22:14:06

Fichier

Tech_Report_Columbia_Universit...
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-01299628, version 1

Collections

Citation

Dimitrios Milioris. Compressed Sensing Classification in Online Social Networks. Columbia University, New York. 2014. <hal-01299628>

Partager

Métriques

Consultations de
la notice

108

Téléchargements du document

111