Document Type : Original/Review Paper

Authors

1 School of Computer Engineering, Iran University of Science and Technology, Tehran, Iran.

2 School of Computer engineering, Iran University of Science and Technology, Tehran, Iran.

3 School of Computer Engineering, Iran University of Science and Technology, Tehran, Iran

10.22044/jadm.2025.15250.2629

Abstract

Stance detection is the process of identifying and classifying an author's point of view or stance towards a specific target in a given text. Most of previous studies on stance detection neglect the contextual information hidden in the input data and as a result lead to less accurate results. In this paper, we propose a novel method called ConSPro, which uses decoder-only transformers to consider contextual input data in the process of stance detection. First, ConSPro applies zero-shot prompting of decoder only transformers to extract the context of target in the input data. Second, in addition to target and input text, ConSPro uses the extracted context as the third type of parameter for the ensemble method. We evaluate ConSPro on SemEval2016 and the empirical results indicate that ConSPro outperforms the non-contextual approaches methods, on average 9% with respect to f-measure. The findings of this study show the strong capabilities of zero-shot prompting for extracting the informative contextual information with significantly less effort comparing to previous methods on context extraction.

Keywords

Main Subjects

[1] D. Küçük and F. Can, "Stance Detection: A Survey," ACM Comput. Surv., vol. 53, no. 1, p. Article 12.
[2] D. Küçük and F. Can, "A Tutorial on Stance Detection," presented at the Proceedings of the Fifteenth ACM International Conference on Web Search and Data Mining, Virtual Event, AZ, USA, 2022.
[3] A. Aldayel and W. Magdy, "Stance detection on social media: State of the art and trends," Information Processing & Management, vol. 58, no. 4, p. 102597.
 
[4] D. Küçük and F. Can, "Stance Detection: Concepts, Approaches, Resources, and Outstanding Issues," presented at the Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval, Virtual Event, Canada, 2021.
 
[5] A. I. Al-Ghadir, A. M. Azmi, and A. Hussain, "A novel approach to stance detection in social media tweets by fusing ranked lists and sentiments," Information Fusion, vol. 67, pp. 29-40, 2021/03/01/ 2021.
[6] M. Hardalov, A. Arora, P. Nakov, and I. Augenstein, A Survey on Stance Detection for Mis- and Disinformation Identification. 2021.
[7] A. Gillioz, J. Casas, E. Mugellini, and O. Abou Khaled, Overview of the Transformer-based Models for NLP Tasks. 2020, pp. 179-183.
[8] B. Min et al., Recent Advances in Natural Language Processing via Large Pre-Trained Language Models: A Survey. 2021.
[9] A. Rahali and M. A. Akhloufi, "End-to-End Transformer-Based Models in Textual-Based NLP," AI, vol. 4, no. 1, pp. 54-110doi: 10.3390/ai4010004.
[10] B. Zhang, X. Fu, D. Ding, H. Huang, Y. Li, and L. Jing, Investigating Chain-of-thought with ChatGPT for Stance Detection on Social Media. 2023.
[11] M. Gambini, C. Senette, T. Fagni, and M. Tesconi, "From Tweets to Stance: An Unsupervised Framework for User Stance Detection on Twitter," in Discovery Science, Cham, A. Bifet, A. C. Lorena, R. P. Ribeiro, J. Gama, and P. H. Abreu, Eds., 2023// 2023: Springer Nature Switzerland, pp. 96-110.
[12] G. Giasemidis, N. Kaplis, I. Agrafiotis, and J. R. C. Nurse, "A Semi-Supervised Approach to Message Stance Classification," IEEE Transactions on Knowledge and Data Engineering, vol. 32, no. 1, pp. 1-11.
[13] D. U. J. L. J. C. D. M. A. O. R. Z. J. X. U. R. Liu Changjian, "An Interactive Stance Classification Method Incorporating Background Knowledge," Acta Scientiarum Naturalium Universitatis Pekinensis, vol. 56, no. 1, pp. 16-22.
[14] C. A. C. Sáenz and K. Becker, "Understanding stance classification of BERT models: an attention-based framework," Knowledge and Information Systems, vol. 66, no. 1, pp. 419-451.
[15] G. Ma, C. Hu, L. Ge, and H. Zhang, "DSMM: A dual stance-aware multi-task model for rumour veracity on social networks," Information Processing & Management, vol. 61, no. 1, p. 103528, 2024/01/01/ 2024, doi: https://doi.org/10.1016/j.ipm.2023.103528.
[16] C. C. Chen, H. Y. Tsai, H. H. Huang, and H. H. Chen, "Stance Identification by Sentiment and Target Detection," in 2020 IEEE/WIC/ACM International Joint Conference on Web Intelligence and Intelligent Agent Technology (WI-IAT), 14-17 Dec. 2020 2020, pp. 331-338.
[17] J. Lin, W. Mao, and Y. Zhang, "An Enhanced Topic Modeling Approach to Multiple Stance Identification," presented at the Proceedings of the 2017 ACM on Conference on Information and Knowledge Management, Singapore, Singapore, 2017.
[18] S. E. Bestvater and B. L. Monroe, "Sentiment is Not Stance: Target-Aware Opinion Classification for Political Text Analysis," Political Analysis, vol. 31, no. 2, pp. 235-256, 2023, doi: 10.1017/pan.2022.10.
[19] S. M. Padnekar, G. S. Kumar, and P. Deepak, "BiLSTM-Autoencoder Architecture for Stance Prediction," in 2020 International Conference on Data Science and Engineering (ICDSE), 3-5 Dec. 2020 2020, pp. 1-5.
[20] H. Zhang, H. Kwak, W. Gao, and J. An, "Wearing Masks Implies Refuting Trump?: Towards Target-specific User Stance Prediction across Events in COVID-19 and US Election 2020," presented at the Proceedings of the 15th ACM Web Science Conference 2023, Austin, TX, USA, 2023.
[21] M. Lai, A. T. Cignarella, D. I. Hernández Farías, C. Bosco, V. Patti, and P. Rosso, "Multilingual stance detection in social media political debates," Computer Speech & Language, vol. 63, p. 101075.
[22] P. Kasnesis, L. Toumanidis, and C. Z. Patrikakis, "Combating Fake News with Transformers: A Comparative Analysis of Stance Detection and Subjectivity Analysis," Information, vol. 12, no. 10.
[23] M. Umer, Z. Imtiaz, S. Ullah, A. Mehmood, G. S. Choi, and B. W. On, "Fake News Stance Detection Using Deep Learning Architecture (CNN-LSTM)," IEEE Access, vol. 8, pp. 156695-156706, 2020, doi: 10.1109/ACCESS.2020.3019735.
[24] A. Chernyavskiy, D. Ilvovsky, and P. Nakov, "WhatTheWikiFact: Fact-Checking Claims Against Wikipedia," presented at the Proceedings of the 30th ACM International Conference on Information & Knowledge Management, Virtual Event, Queensland, Australia, 2021. [Online].
[25] M. Gómez-Suta, J. Echeverry-Correa, and J. A. Soto-Mejía, "Stance detection in tweets: A topic modeling approach supporting explainability," Expert Systems with Applications, vol. 214, p. 119046.
[26] M. Reveilhac and G. Schneider, "Replicable semi-supervised approaches to state-of-the-art stance detection of tweets," Information Processing & Management, vol. 60, no. 2, p. 103199.
[27] K. Glandt, S. Khanal, Y. Li, D. Caragea, and C. Caragea, "Stance Detection in COVID-19 Tweets," in Annual Meeting of the Association for Computational Linguistics, 2021.
[28] Y. Fu et al., "Incorporate opinion-towards for stance detection," Knowledge-Based Systems, vol. 246, p. 108657.
[29] S. Vychegzhanin and E. Kotelnikov, "A New Method for Stance Detection Based on Feature Selection Techniques and Ensembles of Classifiers," IEEE Access, vol. 9, pp. 134899-134915.
[30] M. Alam, A. Iana, A. Grote, K. Ludwig, P. Müller, and H. Paulheim, "Towards Analyzing the Bias of News Recommender Systems Using Sentiment and Stance Detection," presented at the Companion Proceedings of the Web Conference 2022, Virtual Event, Lyon, France, 2022.
[31] L. Mascarell et al., "Stance Detection in German News Articles," Proceedings of the Fourth Workshop on Fact Extraction and VERification (FEVER), 2021.
[32] Q. Sun, Z. Wang, S. Li, Q. Zhu, and G. Zhou, "Stance detection via sentiment information and neural network model," Frontiers of Computer Science, vol. 13, no. 1, pp. 127-138.
[33] R. Liu, Z. Lin, Y. Tan, and W. Wang, Enhancing Zero-shot and Few-shot Stance Detection with Commonsense Knowledge Graph. 2021, pp. 3152-3157.
[34] T. Clark, C. Conforti, F. Liu, Z. Meng, E. Shareghi, and N. Collier, Integrating Transformers and Knowledge Graphs for Twitter Stance Detection. 2021, pp. 304-312.
[35] Y. Liu et al., RoBERTa: A Robustly Optimized BERT Pretraining Approach. 2019.
[36] Y. Luo, Z. Liu, Y. S. Shi, and Y. Zhang, "Exploiting Sentiment and Common Sense for Zero-shot Stance Detection," in International Conference on Computational Linguistics, 2022.
[37] S. Zhang, H. Tong, J. Xu, and R. Maciejewski, "Graph convolutional networks: a comprehensive review," Computational Social Networks, vol. 6, no. 1, p. 11.
[38] X. F. Zhang, N. Beauchamp, and L. Wang, Generative Entity-to-Entity Stance Detection with Knowledge Graph Augmentation. 2022, pp. 9950-9969.
[39] V. Bagal, R. Aggarwal, P. K. Vinod, and U. D. Priyakumar, "MolGPT: Molecular Generation Using a Transformer-Decoder Model," Journal of Chemical Information and Modeling, vol. 62, no. 9, pp. 2064-2076.
[40] Y. Siddiqui et al., "MeshGPT: Generating Triangle Meshes with Decoder-Only Transformers," ArXiv, vol. abs/2311.15475, 2023.
[41] M. Fujitake, DTrOCR: Decoder-only Transformer for Optical Character Recognition. 2023.
[42] J. Ma, C. Wang, H. Xing, D. Zhao, and Y. Zhang, Chain of Stance: Stance Detection with Large Language Models. 2024.
[43] Z. Zhang, Y. Li, J. Zhang, and H. Xu, LLM-Driven Knowledge Injection Advances Zero-Shot and Cross-Target Stance Detection. 2024.
[44] S. Mohammad, S. Kiritchenko, P. Sobhani, X. Zhu, and C. Cherry, S. Bethard, M. Carpuat, D. Cer, D. Jurgens, P. Nakov, and T. Zesch, Eds. SemEval-2016 Task 6: Detecting Stance in Tweets. San Diego, California: Association for Computational Linguistics, 2016, pp. 31-41.