Recommender System Through Sentiment Analysis

Abstract : —Customer product reviews play an important role in the customer's decision to purchase a product or use a service. Customer preferences and opinions are affected by other customers' reviews online, on blogs or over social networking platforms. We propose a multilingual recommender system based on sentiment analysis to help Algerian users decide on products, restaurants, movies and other services using online product reviews. The main goal of this work is to combine both recommendation system and sentiment analysis in order to generate the most accurate recommendations for users. Because both domains suffer from the lack of labeled data, to overcome that, this paper detects the opinions polarity score using the semi-supervised SVM. The experimental results suggested very high precision and a recall of 100%. The results analysis evaluation provides interesting findings on the impact of integrating sentiment analysis into a recommendation technique based on collaborative filtering.
Document type :
Conference papers
Liste complète des métadonnées
Contributor : Didier Schwab <>
Submitted on : Saturday, January 13, 2018 - 9:01:57 PM
Last modification on : Tuesday, February 12, 2019 - 1:31:18 AM
Document(s) archivé(s) le : Monday, May 7, 2018 - 12:45:00 AM


Files produced by the author(s)


  • HAL Id : hal-01683511, version 1



Amel Ziani, Nabiha Azizi, Didier Schwab, Monther Aldwairi, Nassira Chekkai, et al.. Recommender System Through Sentiment Analysis. 2nd International Conference on Automatic Control, Telecommunications and Signals, Dec 2017, Annaba, Algeria. ⟨hal-01683511⟩



Record views


Files downloads