ECNU at SemEval-2017 Task 8: Rumour Evaluation Using Effective Features and Supervised Ensemble Models

Abstract

This paper describes our submissions to task 8 in SemEval 2017, i.e., Determining rumour veracity and support for rumours. Given a rumoured tweet and a plethora of replied tweets, subtask A is to label whether these tweets are support, deny, query or comment, and subtask B aims to predict the veracity (i.e., true, false, and unverified) with a confidence (in range of 0-1) of the given rumoured tweet. For both subtasks, we adopted supervised machine learning methods incorporating rich features. Since the training data is imbalanced, we specifically designed a two-step classifier to address subtask A.