Skripsi
ANALISIS SENTIMEN KOMENTAR PADA INSTAGRAM BADAN EKSEKUTIF MAHASISWA UNIVERSITAS SRIWIJAYA PERIODE 2024-2025 MENGGUNAKAN METODE NAIVE BAYES
This study aims to analyze the sentiment of Instagram user comments on the account of the Student Executive Board of Sriwijaya University (BEM Unsri) for the 2024–2025 period. The background of this research is based on the increasing use of social media as a public communication platform that reflects students’ perceptions of student organization performance. This study employs a quantitative approach using data mining techniques, implementing the Multinomial Naive Bayes algorithm combined with Term Frequency–Inverse Document Frequency (TF-IDF) for feature weighting. The data used consists of Instagram user comments that have undergone preprocessing, labeling using the InSet Lexicon, and data balancing. The results show that the model achieved an accuracy of 0.75, indicating that most of the test data were classified correctly. The sentiment distribution reveals that negative sentiment dominates with 378 comments (74.1%), followed by neutral sentiment with 84 comments (16.5%), and positive sentiment with 48 comments (9.4%). These findings indicate that the Instagram comment section is predominantly used as a medium for expressing criticism and evaluation of the organization’s performance. Therefore, it can be concluded that sentiment analysis using the Naive Bayes algorithm is capable of providing a fairly accurate overview of public perception and can be utilized as an evaluation tool to improve the organization’s digital communication strategy.