![](bg8.png)
Using this method we scored better than the first win-
ner’s deep learning model.
We performed feature analysis by removing a fea-
ture at a time but also groups of features. Any removal
led to moderate performance drop. The significance
drop happened when the BoW feature was removed.
This feature contains uni-grams and bi-grams extrac-
ted from the article heading and article tail. As dis-
cussed both parts either introduce or summarize argu-
ments and are likely to capture what is said in the he-
adline. Overall every feature plays a role in the clas-
sification. We showed that some features play role in
the first step (distinguishing between related and unre-
lated pairs) and others play at discriminating between
agree, disagree and discuss classes.
Our immediate future work will be to use stance to
perform judgments about fake news. We will investi-
gate how stance can be integrate for the fake news
classification.
REFERENCES
Allen, K., Carenini, G., and Ng, R. (2014). Detecting dis-
agreement in conversations using pseudo-monologic
rhetorical structure. In Proceedings of the 2014 Con-
ference on Empirical Methods in Natural Language
Processing (EMNLP), pages 1169–1180.
Breiman, L. (2001). Random forests. Machine learning,
45(1):5–32.
Dungs, S., Aker, A., Fuhr, N., and Bontcheva, K. (2018). (in
press). can rumour stance alone predict veracity? In
Proceedings of COLING 2018, The 27th International
Conference on Computational Linguistics.
Enayet, O. and El-Beltagy, S. R. (2017). Niletmrg at
semeval-2017 task 8: Determining rumour and ver-
acity support for rumours on twitter. In Proceedings
of the 11th International Workshop on Semantic Eva-
luation (SemEval-2017), pages 470–474.
Fan, R.-E., Chang, K.-W., Hsieh, C.-J., Wang, X.-R., and
Lin, C.-J. (2008). Liblinear - a library for large linear
classification. The Weka classifier works with version
1.33 of LIBLINEAR.
Ferreira, W. and Vlachos, A. (2016). Emergent: a novel
data-set for stance classification. In Proceedings of
the 2016 Conference of the North American Chapter
of the Association for Computational Linguistics: Hu-
man Language Technologies. ACL.
Hall, M., Frank, E., Holmes, G., Pfahringer, B., Reute-
mann, P., and Witten, I. H. (2009). The WEKA data
mining software: an update. SIGKDD Explorations,
11(1):10–18.
Hardalov, M., Koychev, I., and Nakov, P. (2016). In se-
arch of credible news. In International Conference
on Artificial Intelligence: Methodology, Systems, and
Applications, pages 172–180. Springer.
Jin, Z., Cao, J., Zhang, Y., and Luo, J. (2016). News veri-
fication by exploiting conflicting social viewpoints in
microblogs. In AAAI, pages 2972–2978.
Jin, Z., Cao, J., Zhang, Y., Zhou, J., and Tian, Q. (2017).
Novel visual and statistical image features for micro-
blogs news verification. IEEE Transactions on Multi-
media, 19(3):598–608.
Kuhn, H. W. (1955). The hungarian method for the assign-
ment problem. Naval Research Logistics (NRL), 2(1-
2):83–97.
Manning, C. D., Surdeanu, M., Bauer, J., Finkel, J. R., Be-
thard, S., and McClosky, D. (2014). The stanford co-
renlp natural language processing toolkit. In ACL (Sy-
stem Demonstrations), pages 55–60.
Markowitz, D. M. and Hancock, J. T. (2014). Linguistic
traces of a scientific fraud: The case of diederik stapel.
PloS one, 9(8):e105937.
Mikolov, T., Chen, K., Corrado, G., and Dean, J. (2013).
Efficient estimation of word representations in vector
space. arXiv preprint arXiv:1301.3781.
Miller, G. A. (1995). Wordnet: A lexical database for eng-
lish. Commun. ACM, 38(11):39–41.
Munkres, J. (1957). Algorithms for the assignment and
transportation problems. Journal of the society for in-
dustrial and applied mathematics, 5(1):32–38.
Pavlick, E., Rastogi, P., Ganitkevitch, J., Van Durme, B.,
and Callison-Burch, C. (2015). Ppdb 2.0: Better
paraphrase ranking, fine-grained entailment relations,
word embeddings, and style classification. In Procee-
dings of the 53rd Annual Meeting of the Association
for Computational Linguistics and the 7th Internatio-
nal Joint Conference on Natural Language Processing
(Volume 2: Short Papers), volume 2, pages 425–430.
Popat, K., Mukherjee, S., Str
¨
otgen, J., and Weikum, G.
(2017). Where the truth lies: Explaining the credibi-
lity of emerging claims on the web and social media.
In Proceedings of the 26th International Conference
on World Wide Web Companion, pages 1003–1012.
International World Wide Web Conferences Steering
Committee.
Qazvinian, V., Rosengren, E., Radev, D. R., and Mei, Q.
(2011). Rumor has it: Identifying misinformation in
microblogs. In Proceedings of the Conference on Em-
pirical Methods in Natural Language Processing, pa-
ges 1589–1599. Association for Computational Lin-
guistics.
Recasens, M., Danescu-Niculescu-Mizil, C., and Jurafsky,
D. (2013). Linguistic models for analyzing and de-
tecting biased language. In Proceedings of ACL.
Socher, R., Perelygin, A., Wu, J., Chuang, J., Manning,
C. D., Ng, A., and Potts, C. (2013). Recursive deep
models for semantic compositionality over a senti-
ment treebank. In Proceedings of the 2013 conference
on empirical methods in natural language processing,
pages 1631–1642.
Zubiaga, A., Aker, A., Bontcheva, K., Liakata, M., and
Procter, R. (2018). Detection and resolution of
rumours in social media: A survey. ACM Computing
Surveys (CSUR), 51(2):32.
The Fake News Challenge: Stance Detection using Traditional Machine Learning Approaches
135