Topical affinity in short text microblogs

作者：

Highlights：

• Development of a character- based embedding framework for user-representative profiling.

• Profiles correlation with the user’s friendship network based on the homophily theory for affirmation.

• Framework tested on three generic and diverse topics of interest for validation.

• Experimentation on the design of user- representative profiles for group recommendations.

摘要

•Development of a character- based embedding framework for user-representative profiling.•Profiles correlation with the user’s friendship network based on the homophily theory for affirmation.•Framework tested on three generic and diverse topics of interest for validation.•Experimentation on the design of user- representative profiles for group recommendations.

论文关键词：Information retrieval,Short text mining,Taste profiling,Data mining,Neural networks,Social web

论文评审过程：Received 4 March 2020, Revised 12 August 2020, Accepted 10 October 2020, Available online 24 October 2020, Version of Record 6 November 2020.

论文官网地址：https://doi.org/10.1016/j.is.2020.101662