Drawing openness to experience from user generated contents: An interpretable data-driven topic modeling approach

作者：

Highlights：

• Predicting users’ openness from text using a topic-emotion-openness mixture model.

• Predicting openness in a data-driven manner via Maximum-A-Posteriori estimation.

• Topic and emotional intensity are identified from text for openness prediction.

摘要

•Predicting users’ openness from text using a topic-emotion-openness mixture model.•Predicting openness in a data-driven manner via Maximum-A-Posteriori estimation.•Topic and emotional intensity are identified from text for openness prediction.

论文关键词：Openness to experience,Interpretability,Topic modeling,Maximum-A-Posteriori estimation,Data-driven

论文评审过程：Received 21 January 2019, Revised 13 October 2019, Accepted 2 November 2019, Available online 4 November 2019, Version of Record 12 November 2019.

论文官网地址：https://doi.org/10.1016/j.eswa.2019.113073