Article Per Year (5 Year)
p-Index From 2021 - 2026
0.23
P-Index
This Author published in this journals
All Journal Indonesian Journal of Statistics and Its Applications
Hari Wijayanto
School of Data Science, Mathematics, and Informatics, IPB University
Computer Science & IT Mathematics Other

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

Found 1 Documents
Search

 1 
A Two-Stage Framework for Unsupervised Sentiment Analysis with Model Selection and Semantic Similarity Evaluation Cici Suhaeni; Fani Fahira; Hari Wijayanto; La Ode Abdul Rahman; Hwan-Seung Yong
Indonesian Journal of Statistics and Applications Vol 10 No 1 (2026): Vol 10 Issue 1 June 2026
Publisher : Statistics and Data Science Program Study, SSMI, IPB University, in collaboration with the Forum Pendidikan Tinggi Statistika Indonesia (FORSTAT) and the Ikatan Statistisi Indonesia (ISI)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29244/ijsa.v10i1p01-22

Abstract

Sentiment analysis is widely used to extract user opinions from large-scale textual data. However, in practical settings, sentiment labels are often unavailable, making it difficult not only to perform sentiment classification but also to evaluate whether the predicted labels are reliable. This study proposes a two-stage framework for unsupervised sentiment analysis with model selection and semantic similarity evaluation. The dataset consists of Gemini app reviews, in which a labeled subset was used in the first stage to investigate the behavioral characteristics and predictive patterns of three sentiment analysis approaches: lexicon-based, transformer-based, and large language model (LLM)-based methods. The model with the most suitable performance was then selected and applied to predict sentiment labels for the remaining unlabeled data in the second stage. The predicted labels were further evaluated using embedding-based cosine similarity to assess semantic consistency within sentiment classes and separability between classes. The results show that the LLM-based method using Gemini 2.0 Flash achieved the best performance, with accuracy, balanced accuracy, and F1-score values above 0.91, followed by the transformer-based IndoBERT model, while the InSet lexicon-based method showed the weakest performance. In the second stage, semantic similarity evaluation revealed a high average intra-class similarity of 0.6699 and a low inter-class similarity of 0.1917, resulting in a similarity gap of 0.4783. These findings indicate that the proposed framework can support reliable sentiment prediction in largely unlabeled datasets by combining sample-based model selection with semantic validation.
Co-Authors Cici Suhaeni Fani Fahira Hwan-Seung Yong La Ode Abdul Rahman