An Unsupervised Domain-Independent Framework for Automated Detection of Persuasion Tactics in Text
This addresses the need to identify exploitation in social media for users, though it appears incremental by building on prior work with a structural focus.
The paper tackles the problem of detecting persuasion tactics in text by proposing an unsupervised, domain-independent framework that exploits sentence structure, showing promising results compared to existing methods.
With the increasing growth of social media, people have started relying heavily on the information shared therein to form opinions and make decisions. While such a reliance is motivation for a variety of parties to promote information, it also makes people vulnerable to exploitation by slander, misinformation, terroristic and predatorial advances. In this work, we aim to understand and detect such attempts at persuasion. Existing works on detecting persuasion in text make use of lexical features for detecting persuasive tactics, without taking advantage of the possible structures inherent in the tactics used. We formulate the task as a multi-class classification problem and propose an unsupervised, domain-independent machine learning framework for detecting the type of persuasion used in text, which exploits the inherent sentence structure present in the different persuasion tactics. Our work shows promising results as compared to existing work.