基于文档向量和回归模型的评分预测框架

A rating prediction framework based on distributed representation of document and regression model

个性化推荐系统可以帮助用户在海量的项目集合中找到他们喜爱的项目,其被广泛地应用于岗位推荐系统、电子商务网站以及社交网络平台中。文章提出了一个基于文档向量和回归模型的评分预测框架,它利用文档向量表示模型将非结构化的评论文本用相同维度的向量表示,进而构造出刻画用户和产品的特征向量,最终融合多个回归模型进行评分预测。在基于真实的数据集上的实验表明,与基准模型相比,其显著改善了数据稀疏情况下评分预测的准确性。

Recommender systems typically produce a list of recommendations to precisely predict the user＇s preference for the items. It is widely used in post recommendation systems, e-commerce websites and social network platforms. This paper proposes a rating prediction framework based on distributed representation of document and regression model. The framework takes advantage of distributed representation of document to map the unstructured review texts into the same vector space, and furthermore constructs the feature vector of users and items. The framework trains several regression models to predict ratings. The extensive experiments on real-world datasets demonstrate that it performs better than the benchmark and alleviates the cold-start problem to some extent.