Activity in Questions & Answers Websites

Millions of users on the Internet discuss a variety of topics on ‹estion and Answer (Q&A) instances. However, not all instances and topics receive the same amount of aŠention, as some thrive and achieve self-sustaining levels of activity while others fail to aŠract users and either never grow beyond being a small niche community or become inactive. Hence, it is imperative to not only beŠer understand but also to distill deciding factors and rules that de€ne and govern sustainable Q&A instances. We aim to empower community managers with quantitative methods for them to beŠer understand, control and foster their communities, and thus contribute to making the Web a more ecient place to exchange information. To that end, we extract, model and cluster user activity-based time series from 50 randomly selected Q&A instances from the StackExchange network to characterize user behavior. We €nd four distinct types of user activity temporal paŠerns, which vary primarily according to the users’ activity frequency. Finally, by breaking down total activity in our 50 Q&A instances by the previously identi€ed user activity pro€les, we classify those 50 Q&A instances into three di‚erent activity pro€les. Our categorization of Q&A instances aligns with the stage of development and maturity of the underlying communities, which can potentially help operators of such instances not only to quantitatively assess status and progress, but also allow them to optimize community building e‚orts.