基于情感权重的用户协同推荐模型

User Collaborative Recommendation Model Based on Emotional Weight

协同过滤推荐算法已经成为个性化推荐系统的关键技术,但由于项目空间上用户评分数据对项目描述的模糊性,导致基于评分数据的协同过滤推荐系统无法很好的表达用户对项目的偏好,以致在寻找相似性用户时存在不准确性.因此,本文通过引用情感计算这一概念,构建考虑权重的基于用户情感的协同过滤推荐算法,综合考虑用户的评分信息及情感评论信息,并通过调节用户的情感权重有效计算用户之间的相似性,从而寻找更符合自身偏好及情感的相似用户和推荐项目.实验结果表明,该算法有效提高了推荐系统中的用户真实感受及准确率.

Collaborative filtering recommendation algorithm has become the key technology of personalized recommendation system. However, due to the ambiguity of user rating data to the project description in the project space, the collaborative filtering recommendation system based on rating data cannot be very good to express user preferences of the project. So looking for similar users is inaccurate. Therefore,the concept of affective computing is referenced in this paper. This paper builds a collaborative filtering recommendation algorithm based on user emotion which considers the emotional weight. And it combines user ratings and emotional comments together by subject extraction and sentiment analysis in users＇ project reviews. And through effective regulation of emotional factors make the user computing recommendation system to find users and projects more in line with their own preferences and emotional user similarity and product recommendation. Experimental results show that the algorithm can effectively improve the recommendation system users really feel and accuracy.