KLASIFIKASI SENTIMEN NETIZEN X MENGGUNAKAN METODE NAIVE BAYES DAN LINEAR DISCRIMINANT ANALYSIS (LDA) (STUDI KASUS: SENTIMEN NETIZEN TERKAIT AKSI DEMONSTRASI PADA TANGGAL 1 AGUSTUS - 30 SEPTEMBER 2025)

Bunga Wanda Nurhalisa, NIM.: 22106010027 (2026) KLASIFIKASI SENTIMEN NETIZEN X MENGGUNAKAN METODE NAIVE BAYES DAN LINEAR DISCRIMINANT ANALYSIS (LDA) (STUDI KASUS: SENTIMEN NETIZEN TERKAIT AKSI DEMONSTRASI PADA TANGGAL 1 AGUSTUS - 30 SEPTEMBER 2025). Skripsi thesis, UIN SUNAN KALIJAGA YOGYAKARTA.

Preview	Text (KLASIFIKASI SENTIMEN NETIZEN X MENGGUNAKAN METODE NAÏVE BAYES DAN LINEAR DISCRIMINANT ANALYSIS (LDA) (STUDI KASUS: SENTIMEN NETIZEN TERKAIT AKSI DEMONSTRASI PADA TANGGAL 1 AGUSTUS - 30 SEPTEMBER 2025)) 22106010027_BAB-I_IV-atau-V_DAFTAR-PUSTAKA.pdf - Published Version Download (7MB) | Preview
	Text (KLASIFIKASI SENTIMEN NETIZEN X MENGGUNAKAN METODE NAÏVE BAYES DAN LINEAR DISCRIMINANT ANALYSIS (LDA) (STUDI KASUS: SENTIMEN NETIZEN TERKAIT AKSI DEMONSTRASI PADA TANGGAL 1 AGUSTUS - 30 SEPTEMBER 2025)) 22106010027_BAB-II_sampai_SEBELUM-BAB-TERAKHIR.pdf - Published Version Restricted to Registered users only Download (15MB) | Request a copy

Abstract

Demonstrations are a form of public political participation that not only take place in physical spaces but also trigger the formation of public opinion on social media. Netizen’s opinions regarding demonstration movements are generally expressed through comments or posts on the social media platform X, containing various sentiments. This study aims to compare the performance of the Naïve Bayes and Linear Discriminant Analysis (LDA) methods in sentiment classification related to the DPR RI demonstration movement on social media X. The dataset was obtained through a data scraping technique on social media X within the period of August 1 to September 30, 2025, resulting in 8.702 data entries. The sentiment data were classified into three categories: positive, negative, and neutral. The research stages included preprocessing, TF-IDF weighting, and sentiment classification using the Naïve Bayes and LDA methods. Model evaluation was conducted using a confusion matrix with accuracy, precision, and F1-score metrics. The results showed that the LDA method achieved better performance than Naïve Bayes, with an accuracy of 79,21%, while Naïve Bayes obtained an accuracy of 74,01%. These findings indicate that the LDA method is more effective in classifying sentiment in unstructured and high-dimensional socal media text data.

Share this knowledge with your friends :

Actions (login required)

View Item