Sentiment Analysis of AI Adoption in Indonesian Higher Education Using Machine Learning and Transformer-Based Models

TL;DR

This paper compares machine learning and Transformer-based models for analyzing Indonesian students' opinions on AI in higher education, finding Transformer models outperform traditional methods in accuracy.

Contribution

It introduces a combined dataset and evaluates both traditional machine learning and Transformer models, demonstrating the superior performance of Transformer-based models for sentiment analysis.

Findings

DistilBERT achieves 84.78% accuracy and F1-score.

SVM achieves 82.14% accuracy, being a competitive alternative.

Transformer models better capture contextual sentiment information.

Abstract

This study analyzes Indonesian student opinions on the adoption of artificial intelligence in higher education using two approaches: TF-IDF-based machine learning and Transformer-based deep learning. The dataset consists of 2,295 labeled samples, combining 1,154 student opinions with additional lexical sentiment data. LightGBM, Random Forest, and Support Vector Machine (SVM) are evaluated as machine learning models, while DistilBERT is fine-tuned for binary sentiment classification. The results show that SVM achieves the best performance among the machine learning models with 82.14% test accuracy and F1-score, while DistilBERT performs best overall with 84.78% accuracy and 84.75% F1-score. These findings indicate that Transformer-based models better capture contextual information, although SVM remains a competitive and efficient alternative for sentiment classification.