Team QCRI-MIT at SemEval-2019 Task 4: Propaganda Analysis Meets Hyperpartisan News Detection
This work addresses the problem of identifying biased news for media analysis, but it is incremental as it applies existing propaganda features to a new task.
The paper tackled hyperpartisan news detection by adapting propaganda analysis features, achieving 72.9% accuracy on manually annotated test data and 60.8% on distantly supervised data.
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.