Elamur Research⌕
☰
home / papers / 2020 / Multilingual Stance Detection in Tweets: The Catalonia Independence Corpus

Multilingual Stance Detection in Tweets: The Catalonia Independence Corpus

Summary

Automatic stance detection, which classifies whether a text supports or opposes a given target, has mostly been studied in English because labelled data in other languages is scarce. The earlier Catalan/Spanish resource from IberEval 2018, the TW-10 Referendum Dataset, has a heavily skewed label distribution, especially in its Catalan portion. This makes cross-language comparisons of systems unreliable. To fix this, the authors built the Catalonia Independence Corpus (CIC), a class-balanced set of Catalan and Spanish tweets labelled for stance on Catalan independence. Instead of labelling every tweet by hand, they used a semi-automatic procedure that assigns labels based on a categorization of Twitter users. Both corpora were used to benchmark four supervised systems, ranging from linear SVMs to neural text classifiers, with shared normalization and dictionary-based lemmatization. The comparison shows the value of balanced data for multilingual and cross-lingual stance research. The authors also report new state-of-the-art scores on TW-10 for both languages. All data and code are publicly released.

Key points

  • Resource: CIC covers Catalan and Spanish tweets with a single target, the independence of Catalonia. It is released with code at github.com/ixa-ehu/catalonia-independence-corpus.
  • Annotation: Tweet labels are derived semi-automatically from a categorization of Twitter users, which reduces manual tweet-by-tweet labelling.
  • Systems tested:
    • SVM + TF-IDF
    • SVM over fastText embeddings
    • the fastText classifier
    • Flair (an RNN with static and contextual string embeddings)
  • Preprocessing: Removal of mentions, URLs and numbers, spelling normalization, diacritic stripping, dictionary-lookup lemmatization and stopword removal.
  • Prior TW-10 bests: uc3m reached 28.02 macro-F1 for Spanish with TF-IDF bag-of-words. CriCa reached 30.68 for Catalan by merging both languages and applying stemming. The provided extract omits CIC's size and the new TW-10 scores; see the full paper for these figures.

Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.

Fields: Linguistics & languages

Cited by

26 papers of our library cite it (of the 140673 whose bibliographies we read); 4 of them have a page here, 22 not yet.

Cite

The paper itself, not this page. BibTeX from the library's record of the work.

@inproceedings{zotova2020multilingual,
  title = {{Multilingual Stance Detection in Tweets: The Catalonia Independence Corpus}},
  author = {Zotova, Elena and Agerri, Rodrigo and Nuñez, Manuel and Rigau, German},
  booktitle = {Proceedings of the Twelfth Language Resources and Evaluation Conference},
  year = {2020},
  url = {https://aclanthology.org/2020.lrec-1.171/}
}

References

24 references, 6 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Aggarwal, C. C. and Zhai, C. (2012). Mining Text Data. Kluwer Academic Publishers, Boston/Dordrecht/London. find
  2. Akbik, A., Blythe, D., and Vollgraf, R. (2018). Contextual string embeddings for sequence. In Proceedings of the 27th International Conference on Computational Linguistics, pages 1638–1649, Santa Fe, New Mexico, USA. find
  3. Akbik, A., Bergmann, T., Blythe, D., Rasul, K., Schweter, S., and Vollgraf, R. (2019). FLAIR: An easy-to-use framework for state-of-the-art NLP. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics (Demonstrations), pages 54–59, Minneap… find our card
  4. Blei, D. M., Ng, A. Y., and Jordan, M. I. (2003). Latent dirichlet allocation. J. Mach. Learn. Res., 3:993–1022, March. find our card
  5. Bøhler, H., Asla, P., Marsi, E., and Sætre, R. (2016). IDI@NTNU at SemEval-2016 task 6: Detecting stance in tweets using shallow features and GloVe vectors for word representation. In Proceedings of the 10th International Workshop on Semantic Evaluation (SemEval-2016), pages 445–450, San Diego, Cali… find
  6. Cover, T. M. and Thomas, J. A. (2006). Elements of Information Theory (Wiley Series in Telecommunications and Signal Processing). Wiley-Interscience, New York, NY, USA. Cuquerella, C. A. and Rodrı́guez, C. C. (2018). Crica team: Multimodal stance detection in tweets on catalan 1oct referendum (multi… find
  7. Derczynski, L., Bontcheva, K., Liakata, M., Procter, R., Wong Sak Hoi, G., and Zubiaga, A. (2017). SemEval-2017 task 8: RumourEval: Determining rumour veracity and support for rumours. In Proceedings of the 11th International Workshop on Semantic Evaluation (SemEval-2017), pages 69–76, Vancouver, Ca… find
  8. Du, J., Xu, R., He, Y., and Gui, L. (2017). Stance classification with target-specific neural attention networks. In Proceedings of the International Joint Conference on Artificial Intelligence, IJCAI 2017. find
  9. Grave, E., Bojanowski, P., Gupta, P., Joulin, A., and Mikolov, T. (2018). Learning word vectors for 157 languages. In Proceedings of the Eleventh International Conference on Language Resources and Evaluation, LREC 2018, Miyazaki, Japan, May 7-12, 2018. find our card
  10. Jones, K. S. (1972). A statistical interpretation of term specificity and its application in retrieval. Journal of Documentation, 28:11–21. find
  11. Joulin, A., Grave, E., Bojanowski, P., and Mikolov, T. (2017). Bag of tricks for efficient text classification. In Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 2, Short Papers, pages 427–431, Valencia, Spain. find
  12. Kenter, T., Borisov, A., and de Rijke, M. (2016). Siamese CBOW: optimizing word embeddings for sentence representations. In Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics, ACL 2016, August 7-12, 2016, Berlin, Germany, Volume 1: Long Papers. find
  13. McCallum, A. K. (2002). Mallet: A machine learning for language toolkit. http://mallet.cs.umass.edu. ↗
  14. Mikolov, T., Chen, K., Corrado, G., and Dean, J. (2013). Efficient estimation of word representations in vector space. In 1st International Conference on Learning Representations, ICLR 2013, Scottsdale, Arizona, USA, May 2-4, 2013, Workshop Track Proceedings. find
  15. Mohammad, S., Kiritchenko, S., Sobhani, P., Zhu, X., and Cherry, C. (2016). Semeval-2016 task 6: Detecting stance in tweets. In Proceedings of the 10th International Workshop on Semantic Evaluation (SemEval-2016), pages 31–41, San Diego, California. find
  16. Mohammad, S. M., Sobhani, P., and Kiritchenko, S. (2017). Stance and sentiment in tweets. ACM Trans. Internet Technol., 17(3):26:1–26:23, June. find
  17. Mohtarami, M., Glass, J., and Nakov, P. (2019). Contrastive language adaptation for cross-lingual stance detection. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), page… find
  18. Otte, E. and Rousseau, R. (2002). Social network analysis: a powerful strategy, also for the information sciences. Journal of Information Science, 28(6):441–453. find
  19. Peters, M. E., Neumann, M., Iyyer, M., Gardner, M., Clark, C., Lee, K., and Zettlemoyer, L. (2018). Deep contextualized word representations. In NAACL. find
  20. Rajadesingan, A. and Liu, H. (2014). Identifying users with opposing opinions in twitter debates. In Social Computing, Behavioral-Cultural Modeling and Prediction - 7th International Conference, SBP 2014, Washington, DC, USA, April 1-4, 2014. Proceedings, pages 153–160. find
  21. Segura-Bedmar, I. (2018). Labda’s early steps toward multimodal stance detection. In Proceedings of the Third Workshop on Evaluation of Human Language Technologies for Iberian Languages (IberEval 2018) co-located with 34th Conference of the Spanish Society for Natural Language Processing (SEPLN 2018… find
  22. Sun, Q., Wang, Z., Zhu, Q., and Zhou, G. (2018). Stance detection with hierarchical attention network. In Proceedings of the 27th International Conference on Computational Linguistics, pages 2399–2409, Santa Fe, New Mexico, USA. Taulé, M., Martı́, M. A., Rangel, F., Rosso, P., Bosco, C., , and Patt… find our card
  23. CEUR Workshop Proceedings. CEUR-WS.org, pages 149–166, Sevilla, Spain. Wei, W., Zhang, X., Liu, X., Chen, W., and Wang, T. (2016). pkudblab at SemEval-2016 task 6 : A specific convolutional neural network system for effective stance detection. In Proceedings of the 10th International Workshop on Sem… find our card
  24. Zarrella, G. and Marsh, A. (2016). MITRE at SemEval-2016 task 6: Transfer learning for stance detection. In Proceedings of the 10th International Workshop on Semantic Evaluation (SemEval-2016), pages 458–463, San Diego, California, June. Association for Computational Linguistics. find our card

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/papers/zotova-2020-multilingual-stance-detection-tweets-catalonia/