Predicting self-monitoring skills using textual posts on Facebook
作者：
Highlights：
• We explore the relationship between posts on Facebook and self-monitoring skills.
• An IRT model is introduced to validate the responses collected via the Internet.
• Posts on Facebook Wall can partially predict the users’ self-monitoring skills.
• Emoticons and Internet slangs are robust to classify high and low self-monitors.
• Expressions related to family topics are more likely used by low self-monitors.
摘要
•We explore the relationship between posts on Facebook and self-monitoring skills.•An IRT model is introduced to validate the responses collected via the Internet.•Posts on Facebook Wall can partially predict the users’ self-monitoring skills.•Emoticons and Internet slangs are robust to classify high and low self-monitors.•Expressions related to family topics are more likely used by low self-monitors.
论文关键词：Facebook,Self-monitoring,Text mining,Item response theory,Data validation,Natural language processing
论文评审过程：Available online 23 January 2014.
论文官网地址：https://doi.org/10.1016/j.chb.2013.12.026
