[论文解读] Aspect-Aware Latent Factor Model: Rating Prediction with Ratings and Reviews

Zhiyong Cheng, Ying Ding+2 more|arXiv (Cornell University)|Feb 22, 2018

Recommender Systems and Techniques参考文献 43被引用 141

一句话总结

本论文提出了 ALFM，它将一个面向方面的主题模型（ATM）与一个面向方面的潜在因子模型相结合，利用评分和评论来预测评分，提升局部和冷启动性能以及可解释性。

ABSTRACT

Although latent factor models (e.g., matrix factorization) achieve good accuracy in rating prediction, they suffer from several problems including cold-start, non-transparency, and suboptimal recommendation for local users or items. In this paper, we employ textual review information with ratings to tackle these limitations. Firstly, we apply a proposed aspect-aware topic model (ATM) on the review text to model user preferences and item features from different aspects, and estimate the aspect importance of a user towards an item. The aspect importance is then integrated into a novel aspect-aware latent factor model (ALFM), which learns user's and item's latent factors based on ratings. In particular, ALFM introduces a weighted matrix to associate those latent factors with the same set of aspects discovered by ATM, such that the latent factors could be used to estimate aspect ratings. Finally, the overall rating is computed via a linear combination of the aspect ratings, which are weighted by the corresponding aspect importance. To this end, our model could alleviate the data sparsity problem and gain good interpretability for recommendation. Besides, an aspect rating is weighted by an aspect importance, which is dependent on the targeted user's preferences and targeted item's features. Therefore, it is expected that the proposed method can model a user's preferences on an item more accurately for each user-item pair locally. Comprehensive experimental studies have been conducted on 19 datasets from Amazon and Yelp 2017 Challenge dataset. Results show that our method achieves significant improvement compared with strong baseline methods, especially for users with only few ratings. Moreover, our model could interpret the recommendation results in depth.

研究动机与目标

• 利用评论文本在多个方面上建模用户偏好和项目特征。
• 为每个用户-项目对学习方面重要性，以改进局部评分预测。
• 通过权重矩阵将潜在因子与方面关联起来，以估计方面评分。
• 将总体评分计算为带有方面重要性的方面评分的加权和。
• 改善数据稀疏性处理并提升推荐的可解释性。

提出的方法

• 引入一个面向方面的主题模型（ATM），从评论中提取用户和项目的方面-主题分布。
• 使用权重矩阵 W 将潜在因子映射到方面，开发一个面向方面的潜在因子模型（ALFM），使之能够进行方面特定评分。
• 定义方面评分 r_{u,i,a} 为 r_{u,i,a}=s_{u,i,a} * (w_a ⊙ p_u)^T (w_a ⊙ q_i)。
• 通过 π_u、λ_u,a、λ_i,a 从用户与项目先验中计算方面重要性 ρ_{u,i,a}。
• 使用 ATM 输出估计 s_{u,i,a} 为 1 - JSD(θ_{u,a}, ψ_{i,a})。
• 使用在 MF 正则化与 L1/L2 惩罚结合的目标函数上进行 SGD 优化来预测评分。

实验结果

研究问题

• RQ1 ALFM 能否优于同时使用评分和评论的最新方法来进行评分预测？
• RQ2 将面向方面的表示融入是否能改进冷启动或评分稀疏的用户/项目的预测？
• RQ3 模型是否能够通过识别有影响力的方面来为其推荐提供可解释的解释？
• RQ4 关键超参数（例如主题数 K 和潜在因子数 f）如何影响性能？

主要发现

• ALFM 在 19 个真实世界的 Amazon 与 Yelp 数据集上显著超越强基线。
• ，该模型对少量评分的用户表现更好，解决了冷启动问题。
• ASPECT-aware weights enable local, per user-item adaptation improving rating prediction accuracy.
• ATM 提供可解释的方面提取，结合 ALFM 时，产生可解释的推荐。