Building Polar-Oriented Libyan Dialect Corpus Using Emoji-Based Lexicon

Abstract

The widespread use of social media platforms, such as Twitter, has given rise to research fields focused on analyzing platform content to extract knowledge for decision-making. This study employs natural language processing techniques to construct a Libyan dialect corpus with a focus on polarity, utilizing an emoji lexicon. Initially, tweets in the Libyan dialect were gathered from Twitter and filtered to retain only those containing emoji symbols. Subsequently, exploratory data analysis was conducted to scrutinize the collected tweets, generating a visual statistical interpretation to address various questions. Finally, the polarity of Libyan dialectal tweets was determined through an emoji lexicon-based approach. The results were then assessed by experts, with 80% expressing agreement with the corpus's polarity. The study concludes that emojis play a crucial role in analyzing the sentiment of Libyan youth on Twitter.