文献类型：期刊文献

英文题名：RETRACTED: Collaborative Filtering Recommendation Algorithm Based on Knowledge Graph (Retracted article. See vol. 2019, 2019)

作者：Mu, Ruihui[1,2];Zeng, Xiaoqin[1]

第一作者：穆瑞辉;Mu, Ruihui

通讯作者：Mu, RH[1];Mu, RH[2]

机构：[1]Hohai Univ, Coll Comp & Informat, Nanjing 210098, Jiangsu, Peoples R China;[2]Xinxiang Univ, Coll Comp & Informat Engn, Xinxiang 453003, Peoples R China

第一机构：Hohai Univ, Coll Comp & Informat, Nanjing 210098, Jiangsu, Peoples R China

通讯机构：[1]corresponding author), Hohai Univ, Coll Comp & Informat, Nanjing 210098, Jiangsu, Peoples R China;[2]corresponding author), Xinxiang Univ, Coll Comp & Informat Engn, Xinxiang 453003, Peoples R China.|[1107118]新乡学院计算机与信息工程学院;[11071]新乡学院;

年份：2018

卷号：2018

外文期刊名：MATHEMATICAL PROBLEMS IN ENGINEERING

收录：;WOS:【SCI-EXPANDED(收录号:WOS:000441544000001)】；

基金：This research was partially supported by the National Key Research and Development Plan Key Projects of China under Grant no. 2017YFC0405800, the National Natural Science Foundation of China Grant (Grant nos. 60971088, 60571048, 61432008, and 61375121), and the Natural Science Foundation of the Colleges and Universities in Jiangsu Province of China, no. 17KJB520022.

语种：英文

摘要：To solve the problem that collaborative filtering algorithm only uses the user-item rating matrix and does not consider semantic information, we proposed a novel collaborative filtering recommendation algorithm based on knowledge graph. Using the knowledge graph representation learning method, this method embeds the existing semantic data into a low-dimensional vector space. It integrates the semantic information of items into the collaborative filtering recommendation by calculating the semantic similarity between items. The shortcoming of collaborative filtering algorithm which does not consider the semantic information of items is overcome, and therefore the effect of collaborative filtering recommendation is improved on the semantic level. Experimental results show that the proposed algorithm can get higher values on precision, recall, and F-measure for collaborative filtering recommendation.