Document embeddings for Arabic Sentiment Analysis - Archive ouverte HAL Access content directly
Conference Papers Year : 2017

Document embeddings for Arabic Sentiment Analysis


Research and industry are more and more focusing in finding automatically the polarity of an opinion regarding a specific subject or entity. Paragraph vector has been recently proposed to learn embeddings which are leveraged for English sentiment analysis. This paper focuses on Arabic sentiment analysis and investigates the use of paragraph vector within a machine learning techniques to determine the polarity of a given text. We tested some preprocessing method, and we show that light stemming enhance the performance of classification.
Fichier principal
Vignette du fichier
LPKM2017_paper_6.pdf (119.89 Ko) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

hal-02042060 , version 1 (20-02-2019)


  • HAL Id : hal-02042060 , version 1


Amira Barhoumi, Yannick Estève, Chafik Aloulou, Lamia Belguith. Document embeddings for Arabic Sentiment Analysis. Conference on Language Processing and Knowledge Management, LPKM 2017, Sep 2017, Sfax, Tunisia. ⟨hal-02042060⟩
290 View
270 Download


Gmail Mastodon Facebook X LinkedIn More