Acta Scientiarum Naturalium Universitatis Pekinensis ›› 2016, Vol. 52 ›› Issue (1): 165-170.DOI: 10.13209/j.0479-8023.2016.011

Previous Articles     Next Articles

Personalized Model for Rating Prediction Based on Review Analysis

MA Chunping1,2, CHEN Wenliang1,2   

  1. 1. School of Computer Science and Technology, Soochow University, Suzhou 215006
    2. Collaborative Innovation Center of Novel Software Technology and Industrialization, Suzhou 215006
  • Received:2015-06-07 Online:2016-01-20 Published:2016-01-20
  • Contact: CHEN Wenliang, E-mail: wlchen(at)suda.edu.cn

基于评论主题的个性化评分预测模型

马春平1,2, 陈文亮1,2   

  1. 1. 苏州大学计算机科学与技术学院, 苏州 215006
    2. 软件新技术与产业化协同创新中心, 苏州 215006
  • 通讯作者: 陈文亮, E-mail: wlchen(at)suda.edu.cn
  • 基金资助:
    国家自然科学基金(61203314, 61373095)资助

Abstract:

Existing recommender systems do not take full advantage of personalization. To address this problem, a novel approach is proposed to mine the opinions and preference of users to build a personalized model for each user or item. Experimental results generated from a real data set show that the proposed approach can improve the accuracy of rating prediction.

Key words: personalized recommendation, recommender system, rating prediction, review comment

摘要:

针对现有基于评论分析的推荐算法没有充分考虑个性化的问题, 通过对评论进行主题分析, 挖掘用户的喜好, 分别建立基于用户和物品的个性化评分预测模型。在真实数据集上进行实验验证, 结果表明该模型有效地提高了推荐系统的评分预测性能。

关键词: 个性化推荐, 推荐系统, 评分预测, 评论信息

CLC Number: