Sharoda A. Paul

Kyle Dent, Sharoda Paul

In a separate study, we were interested in understanding people's Q&A habits on Twitter. Finding questions within Twitter turned out to be a difficult challenge, so we considered applying some traditional NLP approaches to the problem. On the one hand, Twitter is full of idiosyncrasies, which make processing it difficult. On the other, it is very restricted in length and tends to employ simple syntactic constructions, which could help the performance of NLP processing. In order to find out the viability of NLP and Twitter, we built a pipeline of tools to work specifically with Twitter input for the task of finding questions in tweets. This work is still preliminary, but in this paper we discuss the techniques we used and the lessons we learned.

Sharoda A. Paul, Lichan Hong, Ed H. Chi

As social Q&A sites gain popularity, it is important to understand how users judge the authoritativeness of users and content, build reputation, and identify and promote high quality content. We conducted a study of emerging social Q&A site Quora. First, we describe user activity on Quora by analyzing data across 60 question topics and 3917 users. Then we provide a rich understanding of issues of authority, reputation, and quality from in-depth interviews with ten Quora users. Our results show that primary sources of information on Quora are judged authoritative. Also, users judge the reputation of other users based on their past contributions. Social voting helps users identify and promote good content but is prone to preferential attachment. Combining social voting with sophisticated algorithms for ranking content might enable users to better judge others' reputation and promote high quality content.