Skip to main content

Improving Implicit Stance Classification in Tweets Using Word and Sentence Embeddings

Part of the Lecture Notes in Computer Science book series (LNAI,volume 11793)

Abstract

Argumentation Mining aims at finding components of arguments, as well as relations between them, in text. One of the largely unsolved problems is implicitness, where the text invites the reader to infer a missing component, such as the claim or a supporting statement. In the work of Wojatzki and Zesch (2016), an interesting implicitness problem is addressed on a Twitter data set. They showed that implicit stances toward a claim can be found with some success using just token and character n-grams. Using the same dataset, we show that results for this task can be improved using word and sentence embeddings, but that not all embedding variants perform alike. Specifically, we compare fastText, GloVe, and Universal Sentence Encoder (USE); and we find that, to our knowledge, USE yields state-of-the-art results for this task.

Keywords

  • Argumentation mining
  • Social media
  • Stance classification

This is a preview of subscription content, access via your institution.

Buying options

Chapter
USD   29.95
Price excludes VAT (USA)
  • DOI: 10.1007/978-3-030-30179-8_26
  • Chapter length: 9 pages
  • Instant PDF download
  • Readable on all devices
  • Own it forever
  • Exclusive offer for individuals only
  • Tax calculation will be finalised during checkout
eBook
USD   59.99
Price excludes VAT (USA)
  • ISBN: 978-3-030-30179-8
  • Instant PDF download
  • Readable on all devices
  • Own it forever
  • Exclusive offer for individuals only
  • Tax calculation will be finalised during checkout
Softcover Book
USD   79.99
Price excludes VAT (USA)

Notes

  1. 1.

    The code can be downloaded from https://github.com/RobinSchaefer/tweet-stance-classification.

  2. 2.

    Note that WZ16 apply the DKPro Core [6] and DKPro TC frameworks [8].

  3. 3.

    Note that during punctuation removal #’s are ignored in order to maintain hashtags, which we assume to be meaningful for our task.

  4. 4.

    The Snowball Stemmer is implemented using NLTK [13].

  5. 5.

    As the USE model has been trained exclusively for 512-dimensional vectors [7], we are unable to create 300-dimensional vectors that would have been more directly comparable to the fastText and GloVe vectors.

References

  1. Abadi, M., et al.: TensorFlow: large-scale machine learning on heterogeneous systems (2015). http://tensorflow.org/

  2. Boltužić, F., Šnajder, J.: Back up your stance: recognizing arguments in online discussions. In: Proceedings of the First Workshop on Argumentation Mining, Baltimore, Maryland, pp. 49–58. Association for Computational Linguistics, June 2014. https://doi.org/10.3115/v1/W14-2107

  3. Bosc, T., Cabrio, E., Villata, S.: DART: a dataset of arguments and their relations on twitter. In: Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC 2016), Portorož, Slovenia, pp. 1258–1263. European Language Resources Association (ELRA), May 2016

    Google Scholar 

  4. Bosc, T., Cabrio, E., Villata, S.: Tweeties squabbling: positive and negative results in applying argument mining on social media. In: Proceedings of the 6th International Conference on Computational Models of Argument, Potsdam, Germany, September 2016

    Google Scholar 

  5. Cabrio, E., Villata, S.: Combining textual entailment and argumentation theory for supporting online debates interactions. In: Proceedings of the 50th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), Jeju Island, Korea, pp. 208–212. Association for Computational Linguistics, July 2012

    Google Scholar 

  6. de Castilho, R.E., Gurevych, I.: A broad-coverage collection of portable NLP components for building shareable analysis pipelines. In: Proceedings of the Workshop on Open Infrastructures and Analysis Frameworks for HLT, Dublin, Ireland, pp. 1–11. Association for Computational Linguistics and Dublin City University, August 2014. https://doi.org/10.3115/v1/W14-5201

  7. Chidambaram, M., et al.: Learning cross-lingual sentence representations via a multi-task dual-encoder model. CoRR abs/1810.12836 (2018)

    Google Scholar 

  8. Daxenberger, J., Ferschke, O., Gurevych, I., Zesch, T.: DKPro TC: a Java-based framework for supervised learning experiments on textual data. In: Proceedings of 52nd Annual Meeting of the Association for Computational Linguistics: System Demonstrations, Baltimore, Maryland, pp. 61–66. Association for Computational Linguistics, June 2014. https://doi.org/10.3115/v1/P14-5011

  9. Dusmanu, M., Cabrio, E., Villata, S.: Argument mining on Twitter: arguments, facts and sources. In: Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, Copenhagen, Denmark, pp. 2317–2322. Association for Computational Linguistics, September 2017. https://doi.org/10.18653/v1/D17-1245

  10. Gimpel, K., et al.: Part-of-speech tagging for Twitter: annotation, features, and experiments. In: Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies, Portland, Oregon, USA, pp. 42–47. Association for Computational Linguistics, June 2011

    Google Scholar 

  11. Grave, E., Bojanowski, P., Gupta, P., Joulin, A., Mikolov, T.: Learning word vectors for 157 languages. In: Proceedings of the International Conference on Language Resources and Evaluation (LREC 2018) (2018)

    Google Scholar 

  12. Grosse, K., González, M.P., Chesñevar, C.I., Maguitman, A.G.: Integrating argumentation and sentiment analysis for mining opinions from twitter. AI Commun. 28(3), 387–401 (2015)

    MathSciNet  CrossRef  Google Scholar 

  13. Loper, E., Bird, S.: NLTK: the natural language toolkit. In: Proceedings of the ACL 2002 Workshop on Effective Tools and Methodologies for Teaching Natural Language Processing and Computational Linguistics, ETMTNLP 2002, Stroudsburg, PA, USA, vol. 1, pp. 63–70. Association for Computational Linguistics (2002). https://doi.org/10.3115/1118108.1118117

  14. Moens, M.F., Boiy, E., Palau, R.M., Reed, C.: Automatic detection of arguments in legal texts. In: Proceedings of the 11th International Conference on Artificial Intelligence and Law, ICAIL 2007, pp. 225–230. ACM, New York (2007). https://doi.org/10.1145/1276318.1276362

  15. Mohammad, S., Kiritchenko, S., Sobhani, P., Zhu, X., Cherry, C.: SemEval-2016 task 6: detecting stance in tweets. In: Proceedings of the 10th International Workshop on Semantic Evaluation (SemEval-2016), San Diego, California, pp. 31–41. Association for Computational Linguistics, June 2016. https://doi.org/10.18653/v1/S16-1003

  16. Pedregosa, F., et al.: Scikit-learn: machine learning in Python. J. Mach. Learn. Res. 12, 2825–2830 (2011)

    MathSciNet  MATH  Google Scholar 

  17. Pennington, J., Socher, R., Manning, C.D.: GloVe: global vectors for word representation. In: Empirical Methods in Natural Language Processing (EMNLP), pp. 1532–1543 (2014)

    Google Scholar 

  18. Snajder, J.: Social media argumentation mining: the quest for deliberateness in raucousness. CoRR abs/1701.00168 (2017)

    Google Scholar 

  19. Stab, C., Gurevych, I.: Identifying argumentative discourse structures in persuasive essays. In: Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), Doha, Qatar, pp. 46–56. Association for Computational Linguistics, October 2014. https://doi.org/10.3115/v1/D14-1006

  20. Wojatzki, M., Zesch, T.: Stance-based argument mining - modeling implicit argumentation using stance. In: Proceedings of the KONVENS, pp. 313–322 (2016)

    Google Scholar 

Download references

Acknowledgements

We would like to thank Michael Wojatzki for sharing further details about their implementation with us. We would further like to thank the anonymous reviewers for their helpful comments.

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Robin Schaefer .

Editor information

Editors and Affiliations

Rights and permissions

Reprints and Permissions

Copyright information

© 2019 Springer Nature Switzerland AG

About this paper

Verify currency and authenticity via CrossMark

Cite this paper

Schaefer, R., Stede, M. (2019). Improving Implicit Stance Classification in Tweets Using Word and Sentence Embeddings. In: Benzmüller, C., Stuckenschmidt, H. (eds) KI 2019: Advances in Artificial Intelligence. KI 2019. Lecture Notes in Computer Science(), vol 11793. Springer, Cham. https://doi.org/10.1007/978-3-030-30179-8_26

Download citation

  • DOI: https://doi.org/10.1007/978-3-030-30179-8_26

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-030-30178-1

  • Online ISBN: 978-3-030-30179-8

  • eBook Packages: Computer ScienceComputer Science (R0)