Article Per Year (5 Year)
p-Index From 2019 - 2024
0.23
P-Index
This Author published in this journals
All Journal PIKSEL : Penelitian Ilmu Komputer Sistem Embedded and Logic
Nadya Aditama
Institut Teknologi Bandung
Computer Science & IT Decision Sciences, Operations Research & Management

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

 1 
Sentiment Analysis of Sentence-Level using Dependency Embedding and Pre-trained BERT Model Fariska Zakhralativa Ruskanda; Stefanus Stanley Yoga Setiawan; Nadya Aditama; Masayu Leylia Khodra
PIKSEL : Penelitian Ilmu Komputer Sistem Embedded and Logic Vol 11 No 1 (2023): March 2023
Publisher : LPPM Universitas Islam 45 Bekasi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33558/piksel.v11i1.6938

Abstract

Sentiment analysis is a valuable field of research in NLP with many applications. Dependency tree is one of the language features that can be utilized in this field. Dependency embedding, as one of the semantic representations of a sentence, has shown to provide more significant results compared to other embeddings, which makes it a potential way to improve the performance of sentiment analysis tasks. This study aimed to investigate the effect of dependency embedding on sentence-level sentiment analysis through experimental research. The study replaced the Vocabulary Graph embedding in the VGCN-BERT sentiment classification system architecture with several dependency embedding representations, including word vector, context vector, average of word and context vectors, weighting on word and context vectors, and merging of word and context vectors. The experiments were conducted on two datasets, SST-2 and CoLA, with more than 19 thousand labeled sentiment sentences. The results indicated that dependency embedding can enhance the performance of sentiment analysis at the sentence level.
Co-Authors Fariska Zakhralativa Ruskanda Masayu Leylia Khodra Stefanus Stanley Yoga Setiawan