User recommendation in healthcare social media by assessing user similarity in heterogeneous network
作者：
Highlights：
• We proposed methods for representing the healthcare social media data as a heterogeneous healthcare information network.
• Then we introduced a local and a global structural approach to measure user similarity in the heterogeneous network.
• Experiment results showed that structural methods achieve better performance than content-based method for active users.
• Global approach can deal with sparse networks, capture the implicit similarity between two users, and performed better than local approach.
• Different approaches may capture different aspects of the similarity relationship between two users.
摘要
•We proposed methods for representing the healthcare social media data as a heterogeneous healthcare information network.•Then we introduced a local and a global structural approach to measure user similarity in the heterogeneous network.•Experiment results showed that structural methods achieve better performance than content-based method for active users.•Global approach can deal with sparse networks, capture the implicit similarity between two users, and performed better than local approach.•Different approaches may capture different aspects of the similarity relationship between two users.
论文关键词：Heterogeneous network mining,Similarity analysis,Healthcare informatics,Social media analytics,Recommendation systems
论文评审过程：Received 2 March 2017, Accepted 3 March 2017, Available online 18 March 2017, Version of Record 6 October 2017.
论文官网地址：https://doi.org/10.1016/j.artmed.2017.03.002
