<![CDATA[Social media platforms like Instagram play a significant role in the daily lives of many individuals. To understand user experiences with social media, we can read reviews and ratings provided by users. However, these ratings often may not accurately reflect the content of their reviews. Therefore, it is important to analyze these responses to understand the common complaints users have. This study aims to develop an accurate sentiment analysis method for Instagram user reviews by combining Naïve Bayes with a lexicon-based approach to address the discrepancy between star ratings and the content of reviews. The main issue addressed is how to accurately analyze Instagram user sentiment, given the potential discrepancies. To tackle this problem, the study employs a Naïve Bayes method combined with a lexicon-based approach to determine positive and negative sentiments towards user reviews. The testing results show an accuracy of 92%, with a precision of 84%, recall of 91%, and an F1-Score of 87%.]]>
Copyrights © 2024
