This is the authors' abstract. We don't add key points for this paper.
One crucial part of the success of any Community Question Answering (CQA) websites is getting a timely reply on a user's question. And this can be achieved by finding top users who are potential experts in that domain and can provide an answer. In this paper, we experiment and suggest different techniques to recommend top-k users to a newly posted question in the system. We start off by using TF-IDF, LSA, LDA along with LambdaRank. We further propose Hybrid Matrix Factorization for this task which performs better than the rest. In the crux of this technique lies combining feature co-occurrences from content-based method and user-actions on questions from the collaborative methodology.
Answers are grounded in this paper and cite their sources.
No takes yet. Share an insight, caveat, or question.
Choudhary et al. (2018) studied this question.
Synapse has enriched 8 closely related papers on similar clinical questions. Consider them for comparative context: