Question identification on twitter

Abstract

In this paper, we investigate the novel problem of automatic question identification in the microblog environment. It contains two steps: detecting tweets that contain questions (we call them "interrogative tweets") and extracting the tweets which really seek information or ask for help (so called "qweets") from interrogative tweets. To detect interrogative tweets, both traditional rule-based approach and state-of-the-art learning-based method are employed. To extract qweets, context features like short urls and Tweetspecific features like Retweets are elaborately selected for classification. We conduct an empirical study with sampled one hour's English tweets and report our experimental results for question identification on Twitter.

Understanding and Predicting Question Subjectivity in Social Question and Answering

“…Jansen et al [1], in their work examining Twitter as a mechanism for wordof-mouth advertising, reported that 11.1% of the brandrelated tweets were information providing, while 18.1% were information seeking. Li et al [5] revealed that there were about 11% of general tweets containing questions and 6% of tweets having information needs. Going one step further, Efron and Winget [6] analyzed 100 question tweets on Twitter and proposed a taxonomy of questions asked on microblogging platforms.…”

“…There are only a few papers that touch on the problem of automatic question classification based on machine learning techniques. Li et al [5] proposed a cascade approach, which first detected interrogative tweets and then questions revealing real information needs (referred to as qweets in their paper). They relied on both rule-based (as proposed in [6]) and learning-based approaches for interrogative tweets detection and some Twitter-specific features, such as retweet, mentioned to extract qweets.…”

“…Given the high percentage of conversational questions on Twitter [5], [10], in order to collect as many informationseeking questions as possible, in this study, we collected question tweets from a site called Replyz. 2 Replyz is a very popular Twitter-based Q&A site, which searches through Twitter in real time looking for posts that contain questions based on their own algorithm.…”

A Community-Based Vietnamese Question Answering System

“…It is because that the task is under the key research problems of how to construct the database of question-answer pairs, how to analysis questions from users' queries, and how to produce a best answer. Regarding to these problems, some researches concern about question identification [5,16,6,15], question similarity [2], question generation [17], question analysis [10,9], answer summarization [3] and answer re-ranking [13].…”

Question identification on Turkish tweets

“…On the other they have some restrictions like 140-character constraint and tend to employ simple syntactic structure, which make processing it easy [9]. In the study at [10] authors detected questions in English tweets. They called tweets that contain any question as "interrogative tweets" and called tweets that really seek information or ask for help as "qweets".…”