Ensembles of Recurrent Networks for Classifying the Relationship of Fake News Titles

Nowadays, everyone can create and publish news and information anonymously online. However, the credibility of such news and information are not guaranteed. To differentiate fake news from genuine news, one can compare a recent news with earlier posted ones. Identified suspicious news can be debunked to stop the fake news from spreading further. In this paper, we investigate the advantages of recurrent neural networks-based language representations (e.g., BERT, BiLSTM) in order to build ensemble classifiers that can accurately predict if one news title is related to, and, additionally disagrees with an earlier news title. Our experiments, on a dataset of 321k news titles created for the WSDM 2019 challenge, show that the BERT-based models significantly outperform BiLSTM, which in-turn significantly outperforms a simpler embedding-based representation. Furthermore, even the state-of-the-art BERT approach can be enhanced when combined with a simple BM25 feature.

[1]  Geoffrey E. Hinton,et al.  Rectified Linear Units Improve Restricted Boltzmann Machines , 2010, ICML.

[2]  Xiaoli Z. Fern,et al.  DR-BiLSTM: Dependent Reading Bidirectional LSTM for Natural Language Inference , 2018, NAACL.

[3]  W. Bruce Croft,et al.  Neural Ranking Models with Weak Supervision , 2017, SIGIR.

[4]  Wei Gao,et al.  Detecting Rumors from Microblogs with Recurrent Neural Networks , 2016, IJCAI.

[5]  Jonas Mueller,et al.  Siamese Recurrent Architectures for Learning Sentence Similarity , 2016, AAAI.

[6]  Stephen E. Robertson,et al.  Okapi at TREC-3 , 1994, TREC.

[7]  Kyumin Lee,et al.  The Rise of Guardians: Fact-checking URL Recommendation to Combat Fake News , 2018, SIGIR.

[8]  Mona T. Diab,et al.  Rumor Identification and Belief Investigation on Twitter , 2016, WASSA@NAACL-HLT.

[9]  Yonghui Wu,et al.  Exploring the Limits of Language Modeling , 2016, ArXiv.

[10]  Ming-Wei Chang,et al.  BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding , 2019, NAACL.

[11]  Bowen Zhou,et al.  LSTM-based Deep Learning Models for non-factoid answer selection , 2015, ArXiv.

[12]  Jimmy J. Lin,et al.  End-to-End Open-Domain Question Answering with BERTserini , 2019, NAACL.

[13]  Jin-Hyuk Hong,et al.  Semantic Sentence Matching with Densely-connected Recurrent and Co-attentive Information , 2018, AAAI.

[14]  Tadao Kasami,et al.  An Efficient Recognition and Syntax-Analysis Algorithm for Context-Free Languages , 1965 .

[15]  Jeffrey Dean,et al.  Efficient Estimation of Word Representations in Vector Space , 2013, ICLR.

[16]  Yejin Choi,et al.  Syntactic Stylometry for Deception Detection , 2012, ACL.

[17]  Xiang Ji,et al.  MatchZoo: A Learning, Practicing, and Developing System for Neural Text Matching , 2019, SIGIR.