FWLSA-score: French and Wolof Lexicon-based for Sentiment Analysis

Abstract

With the advent of Internet, people actively express their opinions about products, services, events, political parties and other one in social media, blogs, and website comments. The amount of research work on sentiment analysis is growing explosively. However, the majority of research efforts are devoted to English language data, while a great share of information is available in other languages. It is a challenging task to identify sentiment polarity of reviews written in both Wolof and French languages because theirs spelling are usually incorrect or non-uniform. In this paper, we propose a novel framework that contains (i) an extended French lexicon [1] with a new words and expressions currently used in both languages; and (ii) a sentiment scoring algorithm that uses string (word) similarity algorithm to address the spelling problem. Our algorithm classifies reviews as positive or negative based on the polarity of the words or expressions. Our experimental results on a real corpus demonstrated the effectiveness of our proposal.