Social media user stance detection without stance text

• Pedro Semcovici USP http://orcid.org/0009-0008-8455-8509
• Ivandré Paraboni USP https://orcid.org/0000-0002-7270-1477

DOI: https://doi.org/10.5753/sbsi.2025.245657

Resumo

Context: User stance detection systems are intended to determine whether an individual holds a stance for or against a given target topic. For instance, ‘Vaccines save lives’ is a stance in favour of vaccination. Problem: Most existing approaches to stance detection take as an input a piece of text assumed to convey a stance towards the intended target, and then predict its polarity. However, when stance text is unavailable (e.g., when the individual did not publish any opinion regarding that particular topic), models of this kind are unable to determine the user’s stance. Solution: In the case of social media, we may consider as a substitute for stance text the use of other (non-stance) publications made by the user, or even by their close contacts. Information Systems theory: The work was considering Social Network Theory and Social Information Processing Theory. Method:We built a number of stance detection models from stance text and from non-stance data authored by the target users and their close contacts using supervised BERT, prompt-based LLama, and stacking. Results: The non-stance publications made by an individual and, to a lesser extent, those made by his/her contacts, were found to be strong predictors of user stance and, in some cases, their combination was shown to outperform the actual use of text stance. Contributions: Using network-related information may be indeed a substitute for stance text, and may enable the development of systems for scenarios in which stance text is unavailable.

Palavras-chave: Natural language processing, user stance detection, social media

Referências

Abeer Aldayel and Walid Magdy. 2021. Stance detection on social media: State of the art and trends. Information Processing & Management 58, 4 (2021), 102597.

Emily Allaway and Kathleen McKeown. 2020. Zero-Shot Stance Detection: A Dataset and Model using Generalized Topic Representations. In EMNLP-2020 proceedings. Assoc. for Computational Linguistics, Online, 8913–8931. DOI: 10.18653/v1/2020.emnlp-main.717

Emily Allaway and Kathleen R. McKeown. 2020. Zero-Shot Stance Detection: A Dataset and Model using Generalized Topic Representations. In EMNLP-2020 proceedings. Assoc. for Computational Linguistics, Online, 8913–8931. DOI: 10.18653/v1/2020.emnlp-main.717

Adrian Benton and Mark Dredze. 2018. Using Author Embeddings to Improve Tweet Stance Classification. In The 2018 EMNLP Workshop W-NUT: The 4th Workshop on Noisy User-generated Text, Wei Xu, Alan Ritter, Tim Baldwin, and Afshin Rahimi (Eds.). Association for Computational Linguistics, Brussels, Belgium, 184–194. DOI: 10.18653/v1/W18-6124

Laís Carraro Leme Cavalheiro, Matheus Camasmie Pavan, and Ivandré Paraboni. 2023. Stance prediction from multimodal social media data. In Recents Advances in Natural Language Processing (RANLP-2023). INCOMA Ltd., Shoumen, Bulgaria, Varna, Bulgaria, 242–248. DOI: 10.26615/978-954-452-092-2_027

Wang Chunling, Zhang Yijia, Yu Xingyu, Liu Guantong, Chen Fei, and Lin Hongfei. 2023. Adversarial Network with External Knowledge for Zero-Shot Stance Detection. In Proceedings of the 22nd Chinese National Conference on Computational Linguistics. Chinese Information Processing Society of China, Harbin, China, 824–835. DOI: 10.1007/978-981-99-6207-5_26

Alessandra Cignarella, Mirko Lai, Cristina Bosco, Viviana Patti, and Paolo Rosso. 2020. SardiStance @ EVALITA2020: Overview of the Task on Stance Detection in Italian Tweets. In CEURS Proceedings vol. 2765. CEUR-WS.org, online, 177–186.

Pablo Botton da Costa, Matheus Camasmie Pavan, Wesley Ramos dos Santos, Samuel Caetano da Silva, and Ivandré Paraboni. 2023. BERTabaporu: assessing a genre-specific language model for Portuguese NLP. In Recents Advances in Natural Language Processing (RANLP-2023). INCOMA Ltd., Shoumen, Bulgaria, Varna, Bulgaria, 217–223. DOI: 10.26615/978-954-452-092-2_024

Kareem Darwish, Walid Magdy, and Tahar Zanouda. 2017. Improved Stance Prediction in a User Similarity Feature Space. In IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining 2017. Assoc. for Computing Machinery, New York, USA, 145–148. DOI: 10.1145/3110025.3110112

Kareem Darwish, Peter Stefanov, Michael Aupetit, and Preslav Nakov. 2020. Unsupervised User Stance Detection on Twitter. Proceedings of the International AAAI Conference on Web and Social Media 14, 1 (2020), 141–152. DOI: 10.1609/icwsm.v14i1.7286

André de Sousa and Karin Becker. 2023. SSSD: Leveraging Pre-trained Models and Semantic Search for Semi-supervised Stance Detection. In Proceedings of the 14th International Conference on Recent Advances in Natural Language Processing. INCOMA Ltd., Shoumen, Bulgaria, Varna, Bulgaria, 264–273. DOI: 10.26615/978-954-452-092-2_029

Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In NAACL-2019 proceedings. Assoc. for Computational Linguistics, Minneapolis, USA, 4171–4186.

Maria S. Espinosa, Rodrigo Agerri, Alvaro Rodrigo, and Roberto Centeno. 2020. SardiStance: Combining Textual, Social and Emotional Features. In 7th Evaluation Campaign of Natural Language Processing and Speech Tools for Italian (EVALITA 2020). CEUR-WS.org, online.

Arthur Marçal Flores, Matheus Camasmie Pavan, and Ivandré Paraboni. 2022. User profiling and satisfaction inference in public information access services. Journal of Intelligent Information Systems 58, 1 (2022), 67–89. DOI: 10.1007/s10844-021-00661-w

Henri-Jacques Geiss, Flora Sakketou, and Lucie Flek. 2022. OK Boomer: Probing the socio-demographic Divide in Echo Chambers. In 10th International Workshop on Natural Language Processing for Social Media. Assoc. for Computational Linguistics, Seattle, Washington USA, 83–105. DOI: 10.18653/v1/2022.socialnlp-1.8

Dilek Kucuk and Fazli Can. 2020. Stance Detection: A Survey. ACM Computing Surveys 53, 1 (2020), 1–37.

Mirko Lai, Alessandra Cignarella, and Delia Hernandez-Farias. 2017. itacos at ibereval2017: Detecting stance in Catalan and Spanish tweets. In IberEval-2017 proceedings. CEUR-WS.org, Murcia, Spain.

M. Lai, A. T. Cignarella, D. I. Hernandez Farias, C. Bosco, V. Patti, and P. Rosso. 2020. Multilingual stance detection in social media political debates. Computer Speech and Language 63 (2020), 101075.

Mirko Lai, Viviana Patti, Giancarlo Ruffo, and Paolo Rosso. 2020. #Brexit: Leave or remain? the role of user’s community and diachronic evolution on stance detection. Journal of Intelligent & Fuzzy Systems 39, 2 (2020), 2341–2352.

Rasmus Lehmann and Leon Derczynski. 2019. Political Stance in Danish. In 22nd Nordic Conference on Computational Linguistics. Linköping University Electronic Press, Turku, Finland, 197–207.

Veronica Lynn, Salvatore Giorgi, Niranjan Balasubramanian, and H. Andrew Schwartz. 2019. Tweet Classification without the Tweet: An Empirical Examination of User versus Document Attributes. In Third Workshop on Natural Language Processing and Computational Social Science, Svitlana Volkova, David Jurgens, Dirk Hovy, David Bamman, and Oren Tsur (Eds.). Association for Computational Linguistics, Minneapolis, Minnesota, 18–28. DOI: 10.18653/v1/W19-2103

Walid Magdy, Kareem Darwish, Norah Abokhodair, Afshin Rahimi, and Timothy Baldwin. 2016. #ISISisNotIslam or #DeportAllMuslims? Predicting Unspoken Views. In 8th ACM Conference on Web Science. Assoc. for Computing Machinery, New York, NY, USA, 95–106. DOI: 10.1145/2908131.2908150

Miller McPherson, Lynn Smith-Lovin, and James M. Cook. 2001. Birds of a Feather: Homophily in Social Networks. Annual Review of Sociology 27, 1 (2001), 415–444.

Saif Mohammad, Svetlana Kiritchenko, Parinaz Sobhani, Xiaodan Zhu, and Colin Cherry. 2016. SemEval-2016 Task 6: Detecting Stance in Tweets. In 10th International Workshop on Semantic Evaluation (SemEval-2016). Assoc. for Computational Linguistics, San Diego, California, 31–41. DOI: 10.18653/v1/S16-1003

Matheus Camasmie Pavan, Vitor Garcia dos Santos, Alex Gwo Jen Lan, Jo ao Trevisan Martins, Wesley Ramos dos Santos, Caio Deutsch, Pablo Botton da Costa, Fernando Chiu Hsieh, and Ivandré Paraboni. 2023. Morality Classification in Natural Language Text. IEEE transactions on Affective Computing 14, 1 (2023), 857–863. DOI: 10.1109/TAFFC.2020.3034050

Matheus Camasmie Pavan,Wesley Ramos dos Santos, and Ivandré Paraboni. 2020. Twitter Moral Stance Classification using Long Short-Term Memory Networks. In BRACIS-2020 proceedings LNAI 12319. Springer, online, 636–647. DOI: 10.1007/978-3-030-61377-8_45

Matheus Camasmie Pavan and Ivandré Paraboni. 2022. Cross-target Stance Classification as Domain Adaptation. In Advances in Computational Intelligence - MICAI 2022 - Lecture Notes in Artificial Intelligence vol 13612, Obdulia Pichardo Lagunas, Juan Martínez-Miranda, and Bella Martínez Seis (Eds.). Springer Nature Switzerland, Cham, 15–25. DOI: 10.1007/978-3-031-19493-1_2

Matheus Camasmie Pavan and Ivandré Paraboni. 2024. A benchmark for Portuguese zero-shot stance detection. Journal of the Brazilian Computer Society 30, 1 (2024), 469–479. DOI: 10.5753/jbcs.2024.3932

Camila Pereira, Matheus Pavan, Sungwon Yoon, Ricelli Ramos, Pablo Costa, Laís Cavalheiro, and Ivandré Paraboni. 2024. UstanceBR: a social media language resource for stance prediction. DOI: 10.48550/arXiv.2312.06374 arXiv:2312.06374

Younes Samih and Kareem Darwish. 2021. A Few Topical Tweets are Enough for Effective User Stance Detection. In Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume, Paola Merlo, Jorg Tiedemann, and Reut Tsarfaty (Eds.). Association for Computational Linguistics, Online, 2637–2646. DOI: 10.18653/v1/2021.eacl-main.227

Mariona Taulé, Maria Antònia Martí, Francisco Manuel Rangel Pardo, Paolo Rosso, Cristina Bosco, and Viviana Patti. 2017. Overview of the Task on Stance and Gender Detection in Tweets on Catalan Independence at IberEval 2017. In 2nd Workshop on Evaluation of Human Language Technologies for Iberian Languages (IberEval 2017). CEUR-WS.org, Murcia, Spain, 157–177.

Hugo Touvron, Thibaut Lavril, Gautier Izacard, Xavier Martinet, Marie-Anne Lachaux, Timothée Lacroix, Baptiste Rozière, Naman Goyal, Eric Hambro, Faisal Azhar, Aurelien Rodriguez, Armand Joulin, Edouard Grave, and Guillaume Lample. 2023. LLaMA: Open and Efficient Foundation Language Models. [link] cite arxiv:2302.13971.

Haoyang Wen and Alexander Hauptmann. 2023. Zero-Shot and Few-Shot Stance Detection on Varied Topics via Conditional Generation. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers). Association for Computational Linguistics, Toronto, Canada, 1491–1499. DOI: 10.18653/v1/2023.acl-short.127

Bowen Zhang, Daijun Ding, and Liwen Jing. 2023. How would Stance Detection Techniques Evolve after the Launch of ChatGPT? arXiv:2212.14548 [cs.CL]

Xuechen Zhao, Jiaying Zou, Zhong Zhang, Feng Xie, Bin Zhou, and Lei Tian. 2022. Zero-shot stance detection based on cross-domain feature enhancement by contrastive learning. DOI: 10.48550/arXiv.2210.03380