This paper investigates sentiment classification of Steam game reviews using an attention-based Bidirectional Long Short-Term Memory (BiLSTM) model. Using a dataset of 50,000 reviews sampled from a larger Steam review corpus, the authors compare a traditional machine learning baseline based on TF-IDF and PyCaret AutoML with a deep learning approach implemented in PyTorch. The proposed BiLSTM+Attention model is trained with class-weighted cross-entropy to address class imbalance and achieves 83% accuracy and 85% weighted F1-score on the test set, with 90% recall for negative reviews. The paper also presents attention visualizations to show interpretability by highlighting sentiment-bearing words. The study concludes that the BiLSTM+Attention model is effective for analyzing user sentiment in Steam reviews and useful for helping developers understand player feedback.
@article{arxiv.2605.01315,
title = {Enhancing Game Review Sentiment Classification on Steam Platform with Attention-Based BiLSTM},
author = {Abit Ahmad Oktarian and Fadhil Fitra Wijaya and Dhafin Razaqa Luthfi and Luluk Muthoharoh and Ardika Satria and Martin Clinton Tosima Manullang},
journal= {arXiv preprint arXiv:2605.01315},
year = {2026}
}
Comments
7 pages, 4 figures, and 2 tables. The paper is a research manuscript on sentiment analysis of Steam game reviews, comparing TF-IDF-based machine learning methods with a BiLSTM+Attention deep learning model