Enhancing E-Commerce Recommender System Inputs Using Transformer-Based Aspect-Based Sentiment Analysis

Aspect-based sentiment analysis (ABSA) has become an important analytical technique in e-commerce research for understanding how customers perceive specific product features. Conventional sentiment analysis approaches typically treat a review as a single unit and assign an overall sentiment label, even though customers frequently express differing opinions about multiple product attributes within the same review. Such aggregation often obscures feature-level preferences and limits the usefulness of sentiment outputs for personalization and decision support. To address this limitation, this study proposes a transformer-based ABSA pipeline that integrates KeyBERT for unsupervised aspect extraction with Bidirectional Encoder Representations from Transformers (BERT) for contextual sentiment classification at the aspect level. The proposed approach is evaluated using a dataset of 10,000 Amazon product reviews obtained from publicly available open-source review data and is benchmarked against a widely used lexicon-based sentiment analysis method, Valence Aware Dictionary and Sentiment Reasoner (VADER). Model performance is assessed using precision, recall, and F1-score to capture both classification accuracy and balance across sentiment classes. Experimental results demonstrate that the transformer-based pipeline consistently outperforms the lexicon-based baseline, particularly in reviews containing mixed or contrasting sentiments across different product attributes. The findings show that contextual embeddings enable more accurate identification of sentiment polarity shifts and nuanced opinion expressions that are frequently missed by rule-based methods. Overall, the results indicate that transformer-based ABSA provides more reliable and interpretable sentiment representations, making it well suited for supporting personalized recommendations, feature-level analysis, and improved customer insight generation in e-commerce systems.