# Integrating Reviews into Personalized Ranking for Cold Start Recommendation

## TL;DR

This paper proposes two models that incorporate item reviews into Bayesian personalized ranking to improve recommendation accuracy, especially for cold-start items, by leveraging review text features and uncovering review-based user preferences.

## Contribution

The paper introduces novel models that integrate item reviews into Bayesian ranking, enhancing cold-start recommendation performance using text features and review dimensions.

## Key findings

- Leveraging item reviews improves ranking accuracy.
- Models outperform baseline methods on six datasets.
- Review-based features help mitigate cold-start issues.

## Abstract

Item recommendation task predicts a personalized ranking over a set of items for each individual user. One paradigm is the rating-based methods that concentrate on explicit feedbacks and hence face the difficulties in collecting them. Meanwhile, the ranking-based methods are presented with rated items and then rank the rated above the unrated. This paradigm takes advantage of widely available implicit feedback. It, however, usually ignores a kind of important information: item reviews. Item reviews not only justify the preferences of users, but also help alleviate the cold-start problem that fails the collaborative filtering. In this paper, we propose two novel and simple models to integrate item reviews into Bayesian personalized ranking. In each model, we make use of text features extracted from item reviews using word embeddings. On top of text features we uncover the review dimensions that explain the variation in users' feedback and these review factors represent a prior preference of users. Experiments on six real-world data sets show the benefits of leveraging item reviews on ranking prediction. We also conduct analyses to understand the proposed models.