A Joint Summarization and Pre-Trained Model for Review-Based Recommendation

Abstract

Currently, reviews on the Internet contain abundant information about users and products, and this information is of great value to recommendation systems. As a result, review-based recommendations have begun to show their effectiveness and research value. Due to the accumulation of a large number of reviews, it has become very important to extract useful information from reviews. Automatic summarization can capture important information from a set of documents and present it in the form of a brief summary. Therefore, integrating automatic summarization into recommendation systems is a potential approach for solving this problem. Based on this idea, we propose a joint summarization and pre-trained recommendation model for review-based rate prediction. Through automatic summarization and a pre-trained language model, the overall recommendation model learns a fine-grained summary representation of the key content as well as the relationships between words and sentences in each review. The review summary representations of users and items are finally incorporated into a neural collaborative filtering (CF) framework with interactive attention mechanisms to predict the rating scores. We perform experiments on the Amazon dataset and compare our method with several competitive baselines. Experimental results show that the performance of the proposed model is obviously better than that of the baselines. Relative to the current best results, the average improvements obtained on four sub-datasets randomly selected from the Amazon dataset are approximately 3.29%.

Analyzing Social Media Data Using Sentiment Mining and Bigram Analysis for the Recommendation of YouTube Videos

“…For an example of sentiment analysis using the R package sentimentr on Twitter posts, see Figure 7. The posts are identified by a number (1)(2)(3)(4)(5)(6)(7)(8)(9)(10). They are ranked as either positive (green), neutral (gray), or negative (red), and each has a number denoting the strength of the sentiment.…”

“…Unfortunately, CF has a number of limitations such as the cold-start problem, i.e., generating reliable recommendations for those with few ratings or items. However, this issue can be alleviated to some extent by reusing pre-trained deep learning models and/or using contextual information [2]. Since CF is generally an open process, they can be vulnerable to biased information or fake information [3,4].…”