Asis, M (2025) Penerapan Algoritma Naive Bayes Untuk Klasifikasi Sentimen Masyarakat Terhadap Hastag #Pilgub Pada Instagram Dan Facebook. Other thesis, Universitas Islam Riau.

Text skripsi_203510573_watermark.pdf - Submitted Version Restricted to Registered users only Download (8MB) | Request a copy

Abstract

Social media has become a major platform for the public to express their opinions on various issues, including political events such as the Gubernatorial Election (PILGUB). This study aims to classify public sentiment toward the hashtag #PILGUB found on Instagram and Facebook using the Naive Bayes algorithm. A total of 4,372 public opinion data points were collected from both platforms and processed through several stages including preprocessing, manual labeling, and feature extraction using the TF-IDF method. The data distribution reveals a dominance of negative sentiment at 74.43%, followed by positive sentiment at 24.11%, and neutral sentiment at 1.46%. To evaluate model performance, data splitting was applied with various ratios (90:10, 80:20, 70:30). The results indicate that the Naive Bayes algorithm is capable of classifying sentiment effectively, despite the presence of class imbalance. This research is expected to contribute to a better understanding of public opinion on social media and support decisionmaking in political communication strategies.

Actions (login required)

View Item