Extracting Rhetorical Question from Twitter

Abstract

Many types of content exist on SNSs. Sometimes authors' opinions are not properly communicated to the reader. The content might be inflammatory, known as flaming. We infer the importance of extracting passages in which the author's opinion is not communicated correctly when it is presented to the reader. This study particularly examines tweets, a popular message system of the Twitter SNS, and also specifically examines "rhetorical questions." Rhetorical questions are sometimes known as mandarin sentences. People might misunderstand them and might flame the author. We consider it important to extract rhetorical question tweets automatically and present them. This paper proposes a method to extract rhetorical question tweets. First, we propose two definitions of rhetorical question tweets by our preliminary experiment. Next we propose a method extracting rhetorical question tweets based on two definitions. Definition 1 is Including the author's opinion in a question. Definition 2 is Including an author's opinion sentence, commentary sentence, or sentiment reversal in a sentence. Specifically, we proposed a method of opinion sentence extraction, commentary sentence extraction, and sentiment reversal extraction. Furthermore, we conducted two experiments and measured the benefits of our proposed methods.