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

arXiv cs.CL / 5/1/2026

📰 NewsIdeas & Deep AnalysisModels & Research

共有:

Key Points

The paper studies Indonesian students’ opinions about AI adoption in higher education using both classical ML and Transformer-based approaches.
It uses a labeled dataset of 2,295 samples (1,154 student opinions plus lexical sentiment data) to train and evaluate sentiment classification.
Among traditional models, Support Vector Machine (SVM) delivers the strongest machine-learning results with 82.14% test accuracy.
For Transformer-based deep learning, DistilBERT fine-tuned for binary sentiment classification achieves the best overall performance, with 84.78% accuracy and 84.75% F1-score.
The authors conclude that Transformers capture contextual information more effectively, while SVM remains a competitive, efficient baseline for sentiment analysis.

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.