Enhancing Game Review Sentiment Classification on Steam Platform with Attention-Based BiLSTM

TL;DR

This paper presents an attention-based BiLSTM model that effectively classifies sentiment in Steam game reviews, outperforming traditional methods and providing interpretability through attention visualization.

Contribution

The study introduces a novel BiLSTM+Attention model for Steam review sentiment analysis, demonstrating improved accuracy and interpretability over baseline approaches.

Findings

Achieved 83% accuracy and 85% weighted F1-score on test data.

Model provides interpretability via attention visualizations highlighting sentiment words.

Outperforms traditional TF-IDF and AutoML baselines.

Abstract

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.