papers AI Learner
The Github is limit! Click to go to the new site.

Team QCRI-MIT at SemEval-2019 Task 4: Propaganda Analysis Meets Hyperpartisan News Detection

2019-04-06
Abdelrhman Saleh (1), Ramy Baly (2), Alberto Barrón-Cedeño (3), Giovanni Da San Martino (3), Mitra Mohtarami (2), Preslav Nakov (3), James Glass (2) ((1) Harvard University, MA, USA, (2) MIT Computer Science and Artificial Intelligence Laboratory, MA, USA, (3) Qatar Computing Research Institute, HBKU, Qatar)

Abstract

In this paper, we describe our submission to SemEval-2019 Task 4 on Hyperpartisan News Detection. Our system relies on a variety of engineered features originally used to detect propaganda. This is based on the assumption that biased messages are propagandistic in the sense that they promote a particular political cause or viewpoint. We trained a logistic regression model with features ranging from simple bag-of-words to vocabulary richness and text readability features. Our system achieved 72.9% accuracy on the test data that is annotated manually and 60.8% on the test data that is annotated with distant supervision. Additional experiments showed that significant performance improvements can be achieved with better feature pre-processing.

Abstract (translated by Google)
URL

http://arxiv.org/abs/1904.03513

PDF

http://arxiv.org/pdf/1904.03513


Similar Posts

Comments