Article
Authors: Dawid Motyka and Maciej Piasecki
Computational Science – ICCS 2024: 24th International Conference, Malaga, Spain, July 2–4, 2024, Proceedings, Part II
July 2024
Pages 34 - 49
Published: 02 July 2024 Publication History
- 0citation
- 0
- Downloads
Metrics
Total Citations0Total Downloads0Last 12 Months0
Last 6 weeks0
New Citation Alert added!
This alert has been successfully added and will be sent to:
You will be notified whenever a record that you have chosen has been cited.
To manage your alert preferences, click on the button below.
Manage my Alerts
New Citation Alert!
Please log in to your account
- View Options
- References
- Media
- Tables
- Share
Abstract
Stance detection, i.e. recognition of utterances in favor, against or neutral in relation to some targets is important for text analysis. However, different approaches were tested on different datasets, often interpreted in different ways. We propose a unified overview of the state-of-the-art stance detection methods in which targets are expressed by short phrases. Special attention is given to zero-shot learning settings. An overview of the available multiple target datasets is presented that reveals several problems with the sets and their proper interpretation. Wherever possible, methods were re-run or even re-implemented to facilitate reliable comparison. A novel modification of a prompt-based approach to training encoder transformers for stance detection is proposed. It showed comparable results to those obtained with large language models, but at the cost of an order of magnitude fewer parameters. Our work tries to reliably show where do we stand in stance detection and where should we go, especially in terms of datasets and experimental settings.
References
[1]
Addawood, A., Schneider, J., Bashir, M.: Stance classification of twitter debates. In: Processing of the 8th International Conference on Social Media. ACM Press, pp .1–10 (2017)
[2]
Allaway, E., McKeown, K.: Zero-Shot Stance Detection: a dataset and model using generalized topic representations. In: Proc. of the 2020 EMNLP, pp. 8913–8931. ACL, Online (Nov 2020)
[3]
Allaway E and McKeown K Zero-shot stance detection: paradigms and challenges Front. Artif. Intell. 2023 5 1070429
[4]
Allaway, E., Srikanth, M., McKeown, K.: Adversarial learning for zero-shot stance detection on social media. In: Proc. of the 2021 NAACL: Human Language Technologies, pp. 4756–4767. ACL, Online (Jun 2021)
[5]
Barbieri, F., Camacho-Collados, J., EspinosaAnke, L., Neves, L.: TweetEval: Unified benchmark and comparative evaluation for tweet classification. In: Findings of the ACL: EMNLP 2020, pp. 1644–1650. ACL, Online (Nov 2020)
[6]
Brown, T., et al.: Language models are few-shot learners. In: Larochelle, H., Ranzato, M., Hadsell, R., Balcan, M., Lin, H. (eds.) Advances in Neural Information Processing Systems. vol.33, pp. 1877–1901. Curran Associates, Inc. (2020)
[7]
Derczynski, L., Bontcheva, K., Liakata, M., Procter, R., Wong SakHoi, G., Zubiaga, A.: SemEval-2017 task 8: RumourEval: Determining rumour veracity and support for rumours. In: Proc. of the 11th (SemEval-2017), pp. 69–76. ACL, Vancouver, Canada (Aug 2017)
[8]
Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: Pre-training of deep bidirectional transformers for language understanding. In: Proc. of the 2019 NAACL: Human Language Technologies, pp. 4171–4186. ACL, Minneapolis, Minnesota (Jun 2019)
[9]
Fan, L., White, M., Sharma, E., Su, R., Choubey, P.K., Huang, R., Wang, L.: In plain sight: Media bias through the lens of factual reporting. In: Proc. of the 2019 EMNLP-IJCNLP. pp. 6343–6349. ACL, Hong Kong, China (Nov 2019)
[10]
Gao, T., Fisch, A., Chen, D.: Making pre-trained language models better few-shot learners. In: Proceeding of the 59th ACL and the 11th IJCNLP, pp. 3816–3830. ACL, Online (Aug (2021)
[11]
Glandt, K., Khanal, S., Li, Y., Caragea, D., Caragea, C.: Stance detection in COVID-19 tweets. In: Proceeding of the 59th ACL and the 11th Inter. Joint Conference on Natural Language Processing, pp. 1596–1611. ACL, Online (Aug 2021)
[12]
Hardalov, M., Arora, A., Nakov, P., Augenstein, I.: Cross-domain label-adaptive stance detection. In: Proceeding of the 2021 EMNLP, pp. 9011–9028. ACL, Online and Punta Cana, Dominican Republic (Nov 2021)
[13]
He, Z., Mokhberian, N., Lerman, K.: Infusing knowledge from Wikipedia to enhance stance detection. In: Proceeding of the 12th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis, pp. 71–77. ACL, Dublin, Ireland (May 2022)
[14]
Jiang Y, Gao J, Shen H, and Cheng X Zero-shot stance detection via multi-perspective contrastive learning with unlabeled data Inf. Process. Manage. 2023 60 4
Digital Library
[15]
Kocoń, J., Cichecki, I., Kaszyca, O., Kochanek, M., Szydło, D., Baran, J., etal.: ChatGPT: Jack of all trades, master of none. Inf. Fusion 99, 101861 (Nov 2023). 10.1016/j.inffus.2023.101861
[16]
Lewis, M., et al.: BART: Denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension. In: Proceeding of the 58th ACL, pp. 7871–7880. ACL, Online (Jul 2020)
[17]
Li, Y., Sosea, T., Sawant, A., Nair, A.J., Inkpen, D., Caragea, C.: P-stance: A large dataset for stance detection in political domain. In: Findings of the ACL: ACL-IJCNLP 2021, pp. 2355–2365. ACL, Online (Aug 2021)
[18]
Li, Y., Zhao, C., Caragea, C.: Tts: A target-based teacher-student framework for zero-shot stance detection. In: Proceeding of the ACM Web Conference. 2023, pp . 1500-1509. WWW ’23, ACM, New York, NY, USA (2023)
[19]
Liang, B., Chen, Z., Gui, L., He, Y., Yang, M., Xu, R.: Zero-shot stance detection via contrastive learning. In: Proceeding of the ACM Web Conference. 2022, pp. 2738-2747. WWW ’22, ACM, New York, NY, USA (2022)
[20]
Liang, B., et al.: JointCL: A joint contrastive learning framework for zero-shot stance detection. In: Proceeding of the 60th ACL, pp. 81–91. ACL, Dublin, Ireland (May 2022)
[21]
Liu, R., Lin, Z., Fu, P., Liu, Y., Wang, W.: Connecting targets via latent topics and contrastive learning: A unified framework for robust zero-shot and few-shot stance detection. In: ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 7812–7816 (2022)
[22]
Liu, R., Lin, Z., Tan, Y., Wang, W.: Enhancing zero-shot and few-shot stance detection with commonsense knowledge graph. In: Findings of the ACL: ACL-IJCNLP 2021, pp. 3152–3157. ACL, Online (Aug 2021)
[23]
Liu, Y., et al.: Roberta: a robustly optimized BERT pretraining approach. CoRR abs/1907.11692 (2019)
[24]
Liu, Y., Zhang, X.F., Wegsman, D., Beauchamp, N., Wang, L.: POLITICS: Pretraining with same-story article comparison for ideology prediction and stance detection. In: Findings of the ACL: NAACL 2022, pp. 1354–1374. ACL, Seattle, United States (Jul 2022)
[25]
Longpre, S., et al.: The flan collection: designing data and methods for effective instruction tuning, pp. 22631– 22648 (2023)
[26]
Luo, Y., Liu, Z., Shi, Y., Li, S.Z., Zhang, Y.: Exploiting sentiment and common sense for zero-shot stance detection. In: Proceeding of the 29th COLING, pp. 7112–7123. International Committee on Computational Linguistics, Gyeongju, Republic of Korea (Oct 2022)
[27]
Mohammad, S., Kiritchenko, S., Sobhani, P., Zhu, X., Cherry, C.: SemEval-2016 task 6: Detecting stance in tweets. In: Proceeding of the 10th (SemEval-2016), pp. 31–41. ACL, San Diego, California (Jun 2016)
[28]
Schick, T., Schütze, H.: Exploiting cloze-questions for few-shot text classification and natural language inference. In: Proceeding of the 16th Conference of EACL, pp. 255–269. ACL, Online (Apr 2021)
[29]
Schick, T., Schütze, H.: It’s not just size that matters: Small language models are also few-shot learners. In: Proceeding of the 2021 NAACL: Human Language Technologies, pp. 2339–2352. ACL, Online (Jun 2021)
[30]
Sobhani, P., Inkpen, D., Zhu, X.: A dataset for multi-target stance detection. In: Proceeding of the 15th EACL, pp. 551–557. ACL, Valencia, Spain (Apr 2017)
[31]
Tay, Y., et al.: Unifying language learning paradigms. arXiv preprint arXiv:2205.05131 (2023)
[32]
Wen, H., Hauptmann, A.: Zero-shot and few-shot stance detection on varied topics via conditional generation. In: Proceeding of the 61st ACL, pp. 1491–1499. ACL, Toronto, Canada (Jul 2023)
[33]
Xu, H., Vucetic, S., Yin, W.: OpenStance: Real-world zero-shot stance detection. In: Proceeding of the 26th CoNLL, pp. 314–324. ACL, Abu Dhabi (Dec 2022)
[34]
Zhang, B., Ding, D., Jing, L.: How would stance detection techniques evolve after the launch of chatgpt? arXiv preprint arXiv:2212.14548 (2023)
[35]
Zhao, X., Zou, J., Zhang, Z., Xie, F., Zhou, B., Tian, L.:Feature enhanced zero-shot stance detection via contrastive learning, pp. 900–908 (2023)
[36]
Zhu, Q., Liang, B., Sun, J., Du, J., Zhou, L., Xu, R.: Enhancing zero-shot stance detection via targeted background knowledge. In: Proceeding of the 45th International ACM SIGIR Conference on Research and Development in IR, pp . 2070-2075. SIGIR ’22, ACM, New York, NY, USA (2022)
Recommendations
- Zero-shot stance detection via multi-perspective contrastive learning with unlabeled data
Abstract
Stance detection is to distinguish whether the text’s author supports, opposes, or maintains a neutral stance towards a given target. In most real-world scenarios, stance detection needs to work in a zero-shot manner, i.e., predicting ...
Highlights
- We use unlabeled texts of unseen targets in training for zero-shot stance detection.
Read More
- TTS: A Target-based Teacher-Student Framework for Zero-Shot Stance Detection
WWW '23: Proceedings of the ACM Web Conference 2023
The goal of zero-shot stance detection (ZSSD) is to identify the stance (in favor of, against, or neutral) of a text towards an unseen target in the inference stage. In this paper, we explore this problem from a novel angle by proposing a Target-based ...
Read More
- Task-Specific Data Augmentation for Zero-shot and Few-shot Stance Detection
WWW '23 Companion: Companion Proceedings of the ACM Web Conference 2023
Various targets keep coming up on social media, and most of them lack labeled data. In this paper, we focus on zero-shot and few-shot stance detection, which aims to identify stances with few or even no training instances. In order to solve the lack of ...
Read More
Comments
Information & Contributors
Information
Published In
Computational Science – ICCS 2024: 24th International Conference, Malaga, Spain, July 2–4, 2024, Proceedings, Part II
Jul 2024
421 pages
ISBN:978-3-031-63753-7
DOI:10.1007/978-3-031-63751-3
- Editors:
- Leonardo Franco
https://ror.org/036b2ww28University of Malaga, Malaga, Spain
, - Clélia de Mulatier
University of Amsterdam, Amsterdam, The Netherlands
, - Maciej Paszynski
AGH University of Science and Technology, Krakow, Poland
, - Valeria V. Krzhizhanovskaya
https://ror.org/04dkp9463University of Amsterdam, Amsterdam, The Netherlands
, - Jack J. Dongarra
University of Tennessee, Knoxville, TN, USA
, - Peter M. A. Sloot
University of Amsterdam, Amsterdam, The Netherlands
© The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.
Publisher
Springer-Verlag
Berlin, Heidelberg
Publication History
Published: 02 July 2024
Author Tags
- stance detection
- zero-shot learning
- prompt based learning for transformers
Qualifiers
- Article
Contributors
Other Metrics
View Article Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
Total Citations
Total Downloads
- Downloads (Last 12 months)0
- Downloads (Last 6 weeks)0
Other Metrics
View Author Metrics
Citations
View Options
View options
Get Access
Login options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign in
Full Access
Get this Publication
Media
Figures
Other
Tables
