MULDASA: Multifactor Lexical Sentiment Analysis of Social-Media Content in Nonstandard Arabic Social Media

The semantically complicated Arabic natural vocabulary, and the shortage of available techniques skills to capture emotions from text hinder sentiment analysis (ASA). Evaluating idioms that do not follow a conventional linguistic framework, such as contemporary standard (MSA), complicates an incredibly difficult procedure. Here, we define novel lexical approach for studying language tweets (TTs) specialized digital media platforms. Many elements comprising emoji, intensifiers, negations, other nonstandard expressions supplications, proverbs, interjections are incorporated into MULDASA algorithm enhance precision opinion classifications. Root words in multidialectal LX associated with found content under study via simple stemming Furthermore, feature–sentiment correlation procedure is proposed technique exclude viewpoints expressed seem be irrelevant area concern. As part our research Saudi Arabian employability, compiled large sample TTs 6 different dialects. This shows this categorization method useful, using all characteristics listed earlier improves ability accurately classify people’s feelings. classification accuracy improved 83.84% 89.80%. Our also outperformed two existing projects employed