Early Detection of Potential Experts in Question Answering Communities

Abstract

Abstract. Question answering communities (QA) are sustained by a handful of experts who provide a large number of high quality answers. Identifying these experts during the first few weeks of their joining the community can be beneficial as it would allow community managers to take steps to develop and retain these potential experts. In this paper, we explore approaches to identify potential experts as early as within the first two weeks of their association with the QA. We look at users' behavior and estimate their motivation and ability to help others. These qualities enable us to build classification and ranking models to identify users who are likely to become experts in the future. Our results indicate that the current experts can be effectively identified from their early behavior. We asked community managers to evaluate the potential experts identified by our algorithm and their analysis revealed that quite a few of these users were already experts or on the path of becoming experts. Our retrospective analysis shows that some of these potential experts had already left the community, highlighting the value of early identification and engagement.

"Leadership in Action: How Top Hackers Behave" A Big-Data Approach with Text-Mining and Sentiment Analysis

“…We observe that the dataset is imbalanced regarding class distribution. Other CQA services such as TurboTax Live Community (TTLC) and StackOverflow.com also demonstrate such behavior [51]. Super users in TTLC constitute 0.01 percent of overall users [52].…”

Adaptive notifications to support knowledge sharing in close-knit virtual communities

“…Identifying Expertise: Different tools and algorithms have been developed to support people in locating expertise on a specific subject inside groups or VCs (Shami et al, 2007;Zhang et al, 2007;Pal et al, 2011). Our work contributes to this research stream.…”

Beginning Teacher Support in Australia: Towards an Online Community to Augment Current Support

“…Over 92% of questions that are asked get answered, and the median time for having a question answered on the site is 11 minutes (Mamykina, Manoim, Mittal, Hripcsak, & Hartmann, 2011). This success can be attributed in part to having developed an active corps of experts, all of whom are volunteers who answer the majority of questions on the site (Pal, Chang, & Konstan, 2012).…”