{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/qdee-question-difficulty-and-expertise","title":"QDEE: Question Difficulty and Expertise Estimation in Community Question Answering Sites","arxiv_id":"1804.00109","date":"2018-03-31","proceeding":null,"authors":["Jiankai Sun","Sobhan Moosavi","Rajiv Ramnath","Srinivasan Parthasarathy"],"abstract":"In this paper, we present a framework for Question Difficulty and Expertise\nEstimation (QDEE) in Community Question Answering sites (CQAs) such as Yahoo!\nAnswers and Stack Overflow, which tackles a fundamental challenge in\ncrowdsourcing: how to appropriately route and assign questions to users with\nthe suitable expertise. This problem domain has been the subject of much\nresearch and includes both language-agnostic as well as language conscious\nsolutions. We bring to bear a key language-agnostic insight: that users gain\nexpertise and therefore tend to ask as well as answer more difficult questions\nover time. We use this insight within the popular competition (directed) graph\nmodel to estimate question difficulty and user expertise by identifying key\nhierarchical structure within said model. An important and novel contribution\nhere is the application of \"social agony\" to this problem domain. Difficulty\nlevels of newly posted questions (the cold-start problem) are estimated by\nusing our QDEE framework and additional textual features. We also propose a\nmodel to route newly posted questions to appropriate users based on the\ndifficulty level of the question and the expertise of the user. Extensive\nexperiments on real world CQAs such as Yahoo! Answers and Stack Overflow data\ndemonstrate the improved efficacy of our approach over contemporary\nstate-of-the-art models. The QDEE framework also allows us to characterize user\nexpertise in novel ways by identifying interesting patterns and roles played by\ndifferent users in such CQAs.","url_abs":"http://arxiv.org/abs/1804.00109v2","url_pdf":"http://arxiv.org/pdf/1804.00109v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"qdee-question-difficulty-and-expertise","repo_url":"https://github.com/zhenv5/QDEE","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"community-question-answering","task_name":"Community Question Answering"},{"task_slug":"question-answering","task_name":"Question Answering"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}