Arabic dialect sentiment analysis with ZERO effort. Case study: Algerian dialect

Abstract

This paper presents an analytic study showing that it is entirely possible to analyze the Arabic dialect’s sentiment without constructing any resources. The idea of this work is to use the resources dedicated to a given dialect X for analyzing the sentiment of another dialect Y. The unique condition is to have X and Y in the same category of dialects. We apply this idea to the Algerian dialect, a Maghrebi Arabic dialect that suffers from limited available tools and other handling resources required for automatic sentiment analysis. To do this analysis, we rely on Maghrebi dialect resources and two manually annotated sentiment corpus for Tunisian and Moroccan dialect, respectively. We also use a large corpus for the Maghrebi dialect. We use a state-of-the-art system and propose a new deep learning architecture to classify the sentiment of the Algerian dialect automatically. Experimental results show that F1-score is up to 83%. It is achieved by Multilayer Perceptron (MLP) with Tunisian corpus and Long short-term memory (LSTM) with the combination of Tunisian and Moroccan. An improvement of 15% compared to its closest competitor was observed through this study. Ongoing work is aimed at manually constructing an annotated sentiment corpus for the Algerian dialect.