Authors:
Asma Chader
1
;
Dihia Lanasri
2
;
Leila Hamdad
1
;
Mohamed Chemes Eddine Belkheir
1
and
Wassim Hennoune
1
Affiliations:
1
Laboratoire de la Communication dans les Systèmes Informatiques (LCSI), Ecole Nationale Supérieure d’Informatique (ESI), BP 68M, 16309, Oued-Smar, Algiers and Algeria
;
2
Laboratoire de la Communication dans les Systèmes Informatiques (LCSI), Ecole Nationale Supérieure d’Informatique (ESI), BP 68M, 16309, Oued-Smar, Algiers, Algeria, Research & Development & Innovation Direction, Brandt, Algiers and Algeria
Keyword(s):
Sentiment Analysis, Algerian Dialect, Arabizi, Social Networks, Supervised Classification.
Related
Ontology
Subjects/Areas/Topics:
Artificial Intelligence
;
Business Analytics
;
Computational Intelligence
;
Data Analytics
;
Data Engineering
;
Evolutionary Computing
;
Knowledge Discovery and Information Retrieval
;
Knowledge-Based Systems
;
Machine Learning
;
Mining Text and Semi-Structured Data
;
Soft Computing
;
Symbolic Systems
;
Web Mining
Abstract:
Sentiment Analysis and its applications have spread to many languages and domains. With regard to Arabic and its dialects, we witness an increasing interest simultaneously with increase of Arabic texts volume in social media. However, the Algerian dialect had received little attention, and even less in Latin script (Arabizi). In this paper, we propose a supervised approach for sentiment analysis of Arabizi Algerian dialect using different classifiers such as Naive Bayes and Support Vector Machines. We investigate the impact of several preprocessing techniques, dealing with dialect specific aspects. Experimental evaluation on three manually annotated datasets shows promising performance where the approach yielded the highest classification accuracy using SVM algorithm. Moreover, our results emphasize the positive impact of proposed preprocessing techniques. The adding of vowels removal and transliteration, to overcome phonetic and orthographic varieties, allowed us to lift the F-score
of SVM from 76 % to 87 %, which is considerable.
(More)