Hybrid Deep Learning with GloVe and Genetic Algorithm for Sentiment Analysis on X : 2024 election - Dalam bentuk pengganti sidang - Artikel Jurnal
MAHRUNISSA AZMIMA FITRIA

Informasi Umum

Kode

24.04.5368

Klasifikasi

000 - General Works

Jenis

Karya Ilmiah - Skripsi (S1) - Reference

Subjek

Data Science

Dilihat

129 kali

Informasi Lainnya

Abstraksi

Abstract. <br /> Purpose: This research analyzes sentiment on the 2024 Indonesian Presidential Election using X data, employing a <br /> hybrid CNN-GRU model optimized with a Genetic Algorithm (GA) to improve accuracy and efficiency. It also explores <br /> GloVe feature expansion for enhanced sentiment classification, aiming for deeper insights into public opinion through <br /> advanced deep learning and optimization techniques. <br /> Methods: This research employs a deep learning approach that integrates Convolutional Neural Network (CNN) and <br /> Gated Recurrent Unit (GRU) models, Term Frequency-Inverse Document Frequency (TF-IDF), Global Vectors <br /> (GloVe), and GA. The dataset comprises 62.955 Indonesian tweets focusing on the 2024 General Election using various <br /> keywords. <br /> Result: The results indicated that the Genetic Algorithm significantly improved model accuracy. The CNN-GRU + <br /> GA model achieved 84.72% accuracy for the Top 10 ranking, a 1.94% increase from the base model. In comparison, <br /> the GRU-CNN + GA model achieved 84.69% accuracy for the Top 5 ranking, a 2.76% increase from the base model, <br /> demonstrating enhanced performance with GA across configurations. <br /> Novelty: This research uses a hybrid CNN-GRU model to introduce a novel sentiment analysis approach for the 2024 <br /> Indonesian Presidential Election. The model enhances accuracy by combining CNN's spatial feature extraction with <br /> GRU's temporal context capture and GloVe's word semantics. Genetic Algorithm optimization further refines <br /> performance. Comprehensive pre-processing ensures high-quality data, and focusing on election-specific keywords <br /> adds relevance. This study advances sentiment analysis through its innovative hybrid model, feature expansion, and <br /> optimization techniques. 

• CII4E4 - TUGAS AKHIR

Koleksi & Sirkulasi

Tersedia 1 dari total 1 Koleksi

Pengarang

Penerbit

Sirkulasi

Download / Flippingbook