Item recommendation using tag emotion in social cataloging services

作者：

Highlights：

• We propose a tag-based recommendation method considering user’s emotions in tags.

• The tag weight is based on the rating and the emotion value of the tag.

• The emotion value of the tag is obtained using SenticNet.

• We apply a High-Order Singular Value Decomposition.

• The evaluation shows that user’s emotion plays an important role in recommendation.

摘要

•We propose a tag-based recommendation method considering user’s emotions in tags.•The tag weight is based on the rating and the emotion value of the tag.•The emotion value of the tag is obtained using SenticNet.•We apply a High-Order Singular Value Decomposition.•The evaluation shows that user’s emotion plays an important role in recommendation.

论文关键词：Recommendation,Tag,Emotion,Social cataloging service,High-Order Singular Value Decomposition (HOSVD)

论文评审过程：Received 9 February 2017, Revised 26 July 2017, Accepted 27 July 2017, Available online 27 July 2017, Version of Record 29 July 2017.

论文官网地址：https://doi.org/10.1016/j.eswa.2017.07.046