Enhancing Collaborative Filtering Recommender with Prompt-Based Sentiment Analysis

TL;DR

This paper explores enhancing collaborative filtering recommenders by integrating sentiment analysis using advanced NLP models like BERT and RoBERTa, showing significant performance improvements with fine-tuned models but limited gains from prompt-based learning.

Contribution

It demonstrates that fine-tuning RoBERTa for sentiment analysis significantly improves CF recommender performance, while prompt-based learning offers no additional benefit.

Findings

RoBERTa-based sentiment ratings improve recommendation accuracy by 30.7%.

Fine-tuning surpasses prompt-based learning in sentiment analysis for this task.

Prompt-based learning does not further enhance CF recommender performance.

Abstract

Collaborative Filtering(CF) recommender is a crucial application in the online market and ecommerce. However, CF recommender has been proven to suffer from persistent problems related to sparsity of the user rating that will further lead to a cold-start issue. Existing methods address the data sparsity issue by applying token-level sentiment analysis that translate text review into sentiment scores as a complement of the user rating. In this paper, we attempt to optimize the sentiment analysis with advanced NLP models including BERT and RoBERTa, and experiment on whether the CF recommender has been further enhanced. We build the recommenders on the Amazon US Reviews dataset, and tune the pretrained BERT and RoBERTa with the traditional fine-tuned paradigm as well as the new prompt-based learning paradigm. Experimental result shows that the recommender enhanced with the sentiment ratings predicted by the fine-tuned RoBERTa has the best performance, and achieved 30.7% overall gain by comparing MAP, NDCG and precision at K to the baseline recommender. Prompt-based learning paradigm, although superior to traditional fine-tune paradigm in pure sentiment analysis, fail to further improve the CF recommender.