BCMM: A novel post-based augmentation representation for early rumour detection on social media

Abstract

Online social media (OSM) has become a hotbed for the rapid dissemination of disinformation or rumour. Therefore, rumour detection, especially early rumour detection (ERD), is very challenging given the limited, incomplete and noisy information. Although there are some researches on earlier rumour detection, most of their studies require a larger dataset or a longer detection time span, i.e., the rumour detection efficiency needs to be improved. In this paper, we focus on a shorter detection time span which also means fewer online posts to achieve the task of ERD. We proposed a novel post-based augmentation representation approach to process post content of rumour events in the early stages of their dissemination, i.e., backward compression mapping mechanism (BCMM). In addition, we combine BCMM with gated recurrent unit (GRU) to represent post content, topology network of posts and metadata extracted from post datasets. We apply a three-layers GRU to enhance the representation of dataset within one hour after the occurrence of a social media event, i.e., BCMM-GRU. The steps are as follows: (1) we input the first-hour data into the first layer; (2) the first 40 min of data are channelled into the second layer with the output of the first layer making a full mapping to the second layer simultaneously; (3) the first 20 min of data are sent to the third layer while the output of the second layer applies a full mapping to the third layer simultaneously. The evaluation of BCMM-GRU’s performance entails applying k-fold cross-validation (CV) set-up on four available real-life rumour event datasets. The experimental results are superior to the baselines and model variants and achieve a high accuracy of 80.09% and F1-score of 80.18%.