Finding The Potential Accepted Answer On Stack Overflow: a Text Mining Approach

Stack Overflow has been the first website developers look at to find their answers. Many questions asked on Stack Overflow have several answers but don’t have an accepted answer. It confuses users and causes people with the same question to doubt the existing answers and spend more time searching online for the solution. We aim to improve Stack Overflow by detecting the potential solution to questions with no accepted answers. Specifically, our proposed method investigates all submitted answers and proposes one as the potential solution to help the questioner and Stack Overflow find the best answer. In this paper, we use text mining to extract ۱۳ different features from ۱۵۴۶۴ questions, ۳۷۲۷۵ answers, and ۷۲۰۲۵ comments on Stack Overflow posts and then pass them to machine learning models to predict the best answer. This paper only uses English texts. Our proposed method achieved ۷۱% accuracy and ۷۰% F۱-score.

کلیدواژه ها:

Stack Overflow ، Data Mining ، Text Mining ، Machine-Learning ، Sentiment Analysis