Interactive Topic Tagging in Community Question Answering Platforms

Radin Hamidi Rad, Silviu Cucerzan, Nirupama Chandrasekaran, Michael Gamon

Abstract: Community question-answering platforms offer new opportunities for users to share knowledge online. Such platforms allow building communities around areas of interest, and enable community members to post questions and have other members answer them. In this paper, we investigate a novel, interactive approach for tagging input questions with relevant topics, which are needed by community question-answering platforms for various tasks such as indexing and routing. Iteratively, we employ explicit feedback from the users who post questions to fine-tune further the tag suggestions for those questions. We show that our proposed method is able to suggest tags efficiently, and outperforms state-of-the-art methods applied to the tag suggestion task.

External IDs:doi:10.1007/978-3-031-56063-7_13