Geo-Sentiment Analysis of Public Opinion of X Users towards the Documentary Film Dirty Vote using the Bidirectional Long Short-Term Memory Method - Dalam bentuk buku karya ilmiah
SYIFA SALSABILA

Informasi Umum

Kode

25.04.1198

Klasifikasi

000 - General Works

Jenis

Karya Ilmiah - Skripsi (S1) - Reference

Subjek

Data Science

Dilihat

149 kali

Informasi Lainnya

Abstraksi

<div>Presidential elections held every five years, often generates significant public discourse. The 2024 presidential </div>

<div>election saw the release of the documentary Dirty Vote, which raised allegations of electoral fraud and sparked </div>

<div>polarized opinions on social media, especially on X. This study aims to analyze public sentiment toward Dirty Vote </div>

<div>using geo-sentiment analysis and the Bidirectional Long Short-Term Memory (Bi-LSTM) model. Data were collected </div>

<div>from geotagged tweets, with sentiment classified as positive, negative, or neutral. The research explored various data </div>

<div>processing techniques, including TF-IDF for feature extraction, FastText for feature expansion, and balancing </div>

<div>methods like SMOTE and class weighting to address data imbalance. Results showed that the baseline Bi-LSTM </div>

<div>model achieved an accuracy of 71.57% and an F1-Score of 74.05%. When enhanced with TF-IDF and FastText, </div>

<div>accuracy increased to 77.07%, though the F1-Score dropped slightly to 72.95%. Applying SMOTE resulted in a </div>

<div>decrease in accuracy to 76.45%, but significantly improved the F1-Score to 74.93%. Exploratory data analysis </div>

<div>revealed that negative sentiment was most concentrated in Java Island, particularly Jakarta, and peaked during </div>

<div>February 2024, coinciding with the documentary's release and the election period. This study significantly contributes </div>

<div>to understanding how geographic locations influence public opinion on sensitive political issues. A lack of </div>

<div>understanding of geographically-based sentiment patterns can hinder identifying regional needs, leading to poorly </div>

<div>targeted policies. By integrating data analysis methods with geographical approaches, this research provides deep </div>

<div>insights for designing more effective, data-driven public intervention strategies and supports policymaking that is </div>

<div>more responsive to the dynamics of public opinion.</div>

• CII-454 - TUGAS AKHIR
• CII454 - TUGAS AKHIR

Koleksi & Sirkulasi

Tersedia 1 dari total 1 Koleksi

Pengarang

Penerbit

Sirkulasi

Download / Flippingbook