Predicting user personality with social interactions in Weibo

Yuting Jiang, Shengli Deng*, Hongxiu Li, Yong Liu

*Corresponding author for this work

Research output: Contribution to journalArticleScientificpeer-review

9 Citations (Scopus)


Purpose: The purposes of this paper are to (1) explore how personality traits pertaining to the dominance influence steadiness compliance model manifest themselves in terms of user interaction behavior on social media and (2) examine whether social interaction data on social media platforms can predict user personality. Design/methodology/approach: Social interaction data was collected from 198 users of Sina Weibo, a popular social media platform in China. Their personality traits were also measured via questionnaire. Machine learning techniques were applied to predict the personality traits based on the social interaction data. Findings: The results demonstrated that the proposed classifiers had high prediction accuracy, indicating that our approach is reliable and can be used with social interaction data on social media platforms to predict user personality. “Reposting,” “being reposted,” “commenting” and “being commented on” were found to be the key interaction features that reflected Weibo users' personalities, whereas “liking” was not found to be a key feature. Originality/value: The findings of this study are expected to enrich personality prediction research based on social media data and to provide insights into the potential of employing social media data for the purpose of personality prediction in the context of the Weibo social media platform in China.

Original languageEnglish
Pages (from-to)839-864
Number of pages26
JournalAslib Journal of Information Management
Issue number6
Early online date1 Sept 2021
Publication statusPublished - 13 Oct 2021
MoE publication typeA1 Journal article-refereed


  • DISC
  • Personality
  • Social interaction
  • Social media
  • Weibo


Dive into the research topics of 'Predicting user personality with social interactions in Weibo'. Together they form a unique fingerprint.

Cite this