Multitask Models for Supervised Protests Detection in Texts
This work addresses the need for automated political event coding in news analysis, though it is incremental due to building on existing multitask methods.
The authors tackled the problem of detecting political protests in news texts by applying multitask neural networks to three CLEF 2019 tasks, achieving performance near or above the reported state-of-the-art for automated political event coding.
The CLEF 2019 ProtestNews Lab tasks participants to identify text relating to political protests within larger corpora of news data. Three tasks include article classification, sentence detection, and event extraction. I apply multitask neural networks capable of producing predictions for two and three of these tasks simultaneously. The multitask framework allows the model to learn relevant features from the training data of all three tasks. This paper demonstrates performance near or above the reported state-of-the-art for automated political event coding though noted differences in research design make direct comparisons difficult.