Authors: Zhiwei Jin,Juan Cao,Han Guo,Yongdong Zhang
Where published:
Mountain View, CA, USA 2017 10
Document:
PDF
DOI
Abstract URL: https://dl.acm.org/citation.cfm?id=3123454
Microblogs have become popular media for news propagation
in recent years. Meanwhile, numerous rumors and fake news
also bloom and spread wildly on the open social media plat-
forms. Without verication, they could seriously jeopardize
the credibility of microblogs. We observe that an increasing
number of users are using images and videos to post news
in addition to texts. Tweets or microblogs are commonly
composed of text, image and social context. In this paper,
we propose a novel Recurrent Neural Network with an at-
tention mechanism (att-RNN) to fuse multimodal features
for eective rumor detection. In this end-to-end network,
image features are incorporated into the joint features of
text and social context, which are obtained with an LSTM
(Long-Short Term Memory) network, to produce a reliable
fused classication. The neural attention from the outputs
of the LSTM is utilized when fusing with the visual features.
Extensive experiments are conducted on two multimedia ru-
mor datasets collected from Weibo and Twitter. The results
demonstrate the eectiveness of the proposed end-to-end
att-RNN in detecting rumors with multimodal contents.