Applied Sciences (Aug 2021)

Expert Recommendation for Answering Questions on Social Media

  • Kyoungsoo Bok,
  • Heesub Song,
  • Dojin Choi,
  • Jongtae Lim,
  • Deukbae Park,
  • Jaesoo Yoo

DOI
https://doi.org/10.3390/app11167681
Journal volume & issue
Vol. 11, no. 16
p. 7681

Abstract

Read online

In this paper, we propose a method for recommending experts to appropriately answer questions based on social activity analysis on social media. By analyzing various social activities performed on social media, the user’s interests are identified. Through the human relation analysis of the users of a particular interest field and by considering the response speed and answer quality of the user, we determine the influence of a user. An expert group is matched by analyzing the content of queries by a user and using a hierarchical structure of words. For a user question, the accuracy of an expert recommendation is enhanced by incorporating the question content and sublevel words based on the hierarchical structure of words. Various evaluations have demonstrated that the performance of the proposed method is superior to existing methods.

Keywords