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.
@article{arxiv.2604.27439,
title = {Sentiment Analysis of AI Adoption in Indonesian Higher Education Using Machine Learning and Transformer-Based Models},
author = {Happy Syahrul Ramadhan and Ahmad Sahidin Akbar and Karin Yehezkiel Sinaga and Luluk Muthoharoh and Ardika Satria and Martin C. T. Manullang},
journal= {arXiv preprint arXiv:2604.27439},
year = {2026}
}
Comments
8 pages, 6 figures, 7 tables. The paper compares TF-IDF-based machine learning models and DistilBERT for Indonesian sentiment analysis on student opinions about AI adoption in higher education. The manuscript reports that DistilBERT achieves the best overall test performance, while SVM is the strongest classical baseline