TY - GEN
T1 - Modeling Evolution of Message Interaction for Rumor Resolution
AU - Chen, Lei
AU - Wei, Zhongyu
AU - Li, Jing
AU - Zhou, Baohua
AU - Zhang, Qi
AU - Huang, Xuanjing
PY - 2020/12/8
Y1 - 2020/12/8
N2 - Previous work for rumor resolution concentrates on exploiting time-series characteristics or modeling topology structure separately. However, how local interactive pattern affects global information assemblage has not been explored. In this paper, we attempt to address the problem by learning evolution of message interaction. We model confrontation and reciprocity between message pairs via discrete variational autoencoders which effectively reflects the diversified opinion interactivity. Moreover, we capture the variation of message interaction using a hierarchical framework to better integrate information flow of a rumor cascade. Experiments on PHEME dataset demonstrate our proposed model achieves higher accuracy than existing methods.
AB - Previous work for rumor resolution concentrates on exploiting time-series characteristics or modeling topology structure separately. However, how local interactive pattern affects global information assemblage has not been explored. In this paper, we attempt to address the problem by learning evolution of message interaction. We model confrontation and reciprocity between message pairs via discrete variational autoencoders which effectively reflects the diversified opinion interactivity. Moreover, we capture the variation of message interaction using a hierarchical framework to better integrate information flow of a rumor cascade. Experiments on PHEME dataset demonstrate our proposed model achieves higher accuracy than existing methods.
U2 - 10.18653/v1/2020.coling-main.561
DO - 10.18653/v1/2020.coling-main.561
M3 - Conference article published in proceeding or book
SP - 6377
EP - 6387
BT - The 28th International Conference on Computational Linguistics
ER -