Paper: Modeling Factuality Judgments in Social Media Text

ACL ID P14-2068
Title Modeling Factuality Judgments in Social Media Text
Venue Annual Meeting of the Association of Computational Linguistics
Session Main Conference
Year 2014
Authors

How do journalists mark quoted content as certain or uncertain, and how do read- ers interpret these signals? Predicates such as thinks, claims, and admits offer a range of options for framing quoted content ac- cording to the author?s own perceptions of its credibility. We gather a new dataset of direct and indirect quotes from Twit- ter, and obtain annotations of the perceived certainty of the quoted statements. We then compare the ability of linguistic and extra-linguistic features to predict readers? assessment of the certainty of quoted con- tent. We see that readers are indeed influ- enced by such framing devices ? and we find no evidence that they consider other factors, such as the source, journalist, or the content itself. In addition, we examine the impact of specific framing dev...