Marwa Naili ; Anja Chaibi ; Henda Ghézala - Arabic topic identification based on empirical studies of topic models

arima:3102 - Revue Africaine de Recherche en Informatique et Mathématiques Appliquées, August 3, 2017, Volume 27 - 2017 - Special issue CARI 2016 -
Arabic topic identification based on empirical studies of topic modelsArticle

Authors: Marwa Naili 1; Anja Chaibi 1; Henda Ghézala ORCID1

  • 1 Laboratoire de recherche en Génie Logiciel, Applications distribuées, Systèmes décisionnels et Imagerie intelligente [Manouba]

This paper focuses on the topic identification for the Arabic language based on topic models. We study the Latent Dirichlet Allocation (LDA) as an unsupervised method for the Arabic topic identification. Thus, a deep study of LDA is carried out at two levels: Stemming process and the choice of LDA hyper-parameters. For the first level, we study the effect of different Arabic stemmers on LDA. For the second level, we focus on LDA hyper-parameters α and β and their impact on the topic identification. This study shows that LDA is an efficient method for Arabic topic identification especially with the right choice of hyper-parameters. Another important result is the high impact of the stemming algorithm on topic identification.

Volume: Volume 27 - 2017 - Special issue CARI 2016
Published on: August 3, 2017
Accepted on: July 3, 2017
Submitted on: August 2, 2017
Keywords: Arabic stemmers,Latent Dirichlet Allocation,Topic identification,LDA hyper- parameters α and β,Identification thématique,Topic models,Allocation de Dirichlet Latente,hyper-paramètres α et β de LDA,lemmatiseurs Arabes,ACM : I.2.7.6,[INFO.INFO-TT] Computer Science [cs]/Document and Text Processing

5 Documents citing this article

Consultation statistics

This page has been seen 688 times.
This article's PDF has been downloaded 1282 times.