Elamur Research⌕
☰
home / papers / 2023 / Guiding Computational Stance Detection with Expanded Stance Triangle Framework

Guiding Computational Stance Detection with Expanded Stance Triangle Framework

Summary

Target-aware stance detection classifies whether a text's author supports, opposes, or is neutral toward a given target. It is hard because social media posts often refer to targets only indirectly. Models trained on small, single-domain corpora also tend to latch onto surface cues, such as sentiment words, and largely ignore the target itself. The authors approach this from linguistics. They take Du Bois's "stance triangle" (subject, object, other subjects, linked by evaluation, positioning, and alignment) and extend it to model how explicitly mentioned objects relate to implicit targets. The extension describes two inference paths a human reader might follow. Using this framework, they add new annotations to one existing training corpus. Each tweet gets extra targets that are not mentioned in the text, labelled according to how their stance aligns with the explicit object. Models trained on the enriched data generalize significantly better to out-of-domain and cross-target evaluation. This suggests that linguistically motivated data enrichment pushes models toward more domain-invariant features.

Key points

  • The extended framework annotates each tweet with an explicit object and its stance. It then adds implicit targets marked with a label alignment value: 1 (same stance), -1 (opposite stance), or 0 (unrelated, labelled None).
  • Two stancetaking inference paths are outlined, with worked examples. These include tweets that express stance through quotations, such as a Bible verse or a Mother Teresa quote.
  • A motivating failure case is a baseline that predicts Favor even for an irrelevant target ("CD Disk"). This shows that strong models can ignore the specified target.
  • The enrichment was evaluated with several models: an LSTM attention-based target-specific model, BERTweet, and the de-biasing Product-of-Expert (PoE) method. Most metrics improved substantially.
  • Limitations: all data are English, and applying the approach to other languages would require new data or multilingual backbones. The enriched corpora are restricted to academic use.

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

Cite

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.18653/v1/2023.acl-long.220 · arXiv 2305.19845

@inproceedings{liu2023guiding,
  title = {{Guiding Computational Stance Detection with Expanded Stance Triangle Framework}},
  author = {Liu, Zhengyuan and Yap, Yong Keong and Chieu, Hai Leong and Chen, Nancy},
  booktitle = {Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},
  year = {2023},
  doi = {10.18653/v1/2023.acl-long.220},
  eprint = {2305.19845},
  archivePrefix = {arXiv},
  url = {https://doi.org/10.18653/v1/2023.acl-long.220}
}

References

42 references, 11 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Asif Agha. 2003. The social life of cultural value. Language & communication, 23(3-4):231–273. find
  2. Emily Allaway and Kathleen Mckeown. 2020. Zero-shot stance detection: A dataset and model using generalized topic representations. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 8913– 8931. find our card
  3. Isabelle Augenstein, Tim Rocktäschel, Andreas Vlachos, and Kalina Bontcheva. 2016. Stance detection with bidirectional conditional encoding. In Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, pages 876–885, Austin, Texas. Association for Computational Linguist… find our card
  4. Yejin Bang, Samuel Cahyawijaya, Nayeon Lee, Wenliang Dai, Dan Su, Bryan Wilie, Holy Lovenia, Ziwei Ji, Tiezheng Yu, Willy Chung, et al. 2023. A multi-task, multilingual, multimodal evaluation of chatgpt on reasoning, hallucination, and interactivity. arXiv preprint arXiv:2302.04023. find our card
  5. Douglas Biber and Edward Finegan. 1988. Adverbial stance types in english. Discourse processes, 11(1):1– 34. find
  6. Axel Bohmann and Wiebke Ahlers. 2022. Stance in narration: Finding structure in complex sociolinguistic variation. Journal of Sociolinguistics, 26(1):65–83. find
  7. Innocent Chiluwa and Presley Ifukor. 2015. ‘war against our children’: Stance and evaluation in\# bringbackourgirls campaign discourse on twitter and facebook. Discourse & Society, 26(3):267–296. find
  8. Christopher Clark, Mark Yatskar, and Luke Zettlemoyer. 2019. Don’t take the easy way out: Ensemble based methods for avoiding known dataset biases. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language… find
  9. John W Du Bois and Elise Kärkkäinen. 2012. Taking a stance on emotion: Affect, sequence, and intersubjectivity in dialogic interaction. Text & Talk, 32(4):433–451. find
  10. Ash Evans. 2016. Stance and identity in twitter hashtags. Language@ internet, 13(1). find
  11. Tianyu Gao, Xingcheng Yao, and Danqi Chen. 2021. Simcse: Simple contrastive learning of sentence embeddings. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 6894–6910. find our card
  12. Shalmoli Ghosh, Prajwal Singhania, Siddharth Singh, Koustav Rudra, and Saptarshi Ghosh. 2019. Stance detection in web and social media: a comparative study. In International Conference of the Cross-Language Evaluation Forum for European Languages, pages 75–87. Springer. find
  13. Kyle Glandt, Sarthak Khanal, Yingjie Li, Doina Caragea, and Cornelia Caragea. 2021. Stance detection in COVID-19 tweets. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Lo… find our card
  14. Pentti Haddington et al. 2004. Stance taking in news interviews. SKY Journal of Linguistics, 17:101–142. find
  15. Alexandra Jaffe et al. 2009. Stance: sociolinguistic perspectives. Oup Usa. find
  16. Rabeeh Karimi Mahabadi, Yonatan Belinkov, and James Henderson. 2020. End-to-end bias mitigation by modelling biases in corpora. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 8706–8716, Online. Association for Computational Linguistics. find
  17. Ayush Kaushal, Avirup Saha, and Niloy Ganguly. 2021. twt–wt: A dataset to assert the role of target entities for detecting stance of tweets. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 3879–3… find
  18. Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. BERT: Pre-training of deep bidirectional transformers for language understanding. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies,… find
  19. Scott F Kiesling. 2022. Stance and stancetaking. Annual Review of Linguistics, 8:409–426. find
  20. Jiachen Du, Ruifeng Xu, Yulan He, and Lin Gui. 2017. Stance classification with target-specific neural attention networks. International Joint Conferences on Artificial Intelligence. find
  21. Diederik P Kingma and Jimmy Ba. 2015. Adam: A method for stochastic optimization. In Proceedings of the 3rd International Conference for Learning Representations. find
  22. John W Du Bois. 2007. The stance triangle. Stancetaking in discourse: Subjectivity, evaluation, interaction, 164(3):139–182. find
  23. Dilek Küçük and Fazli Can. 2020. Stance detection: A survey. ACM Computing Surveys (CSUR), 53(1):1– 37. find
  24. Scott F. Kiesling, Umashanthi Pavalanathan, Jim Fitzpatrick, Xiaochuang Han, and Jacob Eisenstein. 2018. Interactional stancetaking in online forums. Computational Linguistics, 44(4):683–718. find
  25. Michael Lempert. 2008. The poetics of stance: Text-metricality, epistemicity, interaction. Language in Society, 37(4):569–592. find
  26. Yingjie Li and Cornelia Caragea. 2021. Target-aware data augmentation for stance detection. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 1850–1860. find our card
  27. Yingjie Li, Tiberiu Sosea, Aditya Sawant, Ajith Jayara-man Nair, Diana Inkpen, and Cornelia Caragea. 2021. P-stance: A large dataset for stance detection in political domain. In Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021, pages 2355–2365. find our card
  28. Yinhan Liu, Myle Ott, Naman Goyal, Jingfei Du, Mandar Joshi, Danqi Chen, Omer Levy, Mike Lewis, Luke Zettlemoyer, and Veselin Stoyanov. 2019. Roberta: A robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692. find
  29. Zhengyuan Liu and Jin-Cheon Na. 2018. Aspect-based sentiment analysis of nuclear energy tweets with attentive deep neural network. In ICADL 2018, Hamilton, New Zealand, November 19-22, 2018, Proceedings 20, pages 99–111. Springer. find
  30. Saif Mohammad, Svetlana Kiritchenko, Parinaz Sobhani, Xiaodan Zhu, and Colin Cherry. 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. Association for Computational Ling… find
  31. Yequan Wang, Minlie Huang, Xiaoyan Zhu, and Li Zhao. 2016. Attention-based lstm for aspect-level sentiment classification. In Proceedings of the 2016 conference on empirical methods in natural language processing, pages 606–615. find
  32. Nan Xi, Di Ma, Marcus Liou, Zachary C Steinert-Threlkeld, Jason Anastasopoulos, and Jungseock Joo. 2020. Understanding the political ideology of legislators from social media images. In Proceedings of the international aaai conference on web and social media, volume 14, pages 726–737. find
  33. Jianhua Yuan, Yanyan Zhao, Yanyue Lu, and Bing Qin. 2022. Ssr: Utilizing simplified stance reasoning process for robust stance detection. In Proceedings of the 29th International Conference on Computational Linguistics, pages 6846–6858. find our card
  34. Guido Zarrella and Amy Marsh. 2016. Mitre at semeval-2016 task 6: Transfer learning for stance detection. arXiv preprint arXiv:1606.03784. find our card
  35. Yiwei Zhou, Alexandra I Cristea, and Lei Shi. 2017. Connecting targets to tweets: Semantic attention-based model for target-specific stance detection. In International Conference on Web Information Systems Engineering, pages 18–32. Springer. find
  36. Caleb Ziems, William Held, Omar Shaikh, Jiaao Chen, Zhehao Zhang, and Diyi Yang. 2023. Can large language models transform computational social science? arXiv preprint arXiv:2305.03514. find our card
  37. Dat Quoc Nguyen, Thanh Vu, and Anh-Tuan Nguyen. 2020. Bertweet: A pre-trained language model for english tweets. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, pages 9–14. find our card
  38. Vasiliki Simaki, Panagiotis Simakis, Carita Paradis, and Andreas Kerren. 2018. Detection of stance-related characteristics in social media text. In Proceedings of the 10th Hellenic Conference on Artificial Intelligence, pages 1–7. find
  39. John S Uebersax. 1982. A generalized kappa coefficient. Educational and Psychological Measurement, 42(1):181–183. find
  40. Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Łukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. In Advances in Neural Information Processing Systems, pages 6000–6010. find
  41. Prashanth Vijayaraghavan, Ivan Sysoev, Soroush Vosoughi, and Deb Roy. 2016. Deepstance at semeval-2016 task 6: Detecting stance in tweets using character and word-level cnns. arXiv preprint arXiv:1606.05694. find
  42. Environment Details GPU Model Library Version Computational Cost Single Tesla A100 with 40 GB memory; CUDA version 10.1. Pytorch==1.8.1; Transformers==4.8.2. Average 1.5 hours training time for one round. Average 3 rounds for each reported result (calculating the mean of the result scores). Stance C… find

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/papers/liu-2023-guiding-computational-stance-detection-expanded/