Ir al contenido

Documat

Language Independent Stance Detection: Social Interaction-based Embeddings and Large Language Models

  • Autores: Joseba Fernández de Landa, Rodrigo Agerri Gascón Árbol académico
  • Localización: Procesamiento del lenguaje natural, ISSN 1135-5948, Nº. 74, 2025, págs. 139-157
  • Idioma: inglés
  • Títulos paralelos:
    • Detección de Stance Independiente del Idioma: Representaciones Vectoriales basadas en Interacciones Sociales y Grandes Modelos de Lenguaje
  • Enlaces
  • Resumen
    • español

      La gran mayoría de los trabajos sobre la detección de stance (posicionamiento) se han centrado en clasificación de texto, incluso cuando los datos se recolectan de redes sociales como Twitter. Este articulo aborda la tarea de detección de stance haciendo énfasis, además de en los datos textuales de los mensajes, en los datos de interacción disponibles en las redes sociales. Proponemos un nuevo método para representar información social como amigos y retuits generando embeddings relacionales, es decir, representaciones vectoriales densas basadas en pares de interacción. Nuestros experimentos en siete conjuntos de datos públicamente disponibles y para cuatro idiomas (catalán, euskera, español e italiano) demuestran que la combinación de los embeddings relacionales con métodos textuales ayuda a mejorar el rendimiento, obteniendo resultados del estado del arte en seis de los siete escenarios de evaluación, superando otras aproximaciones basadas en grandes modelos de lenguaje u otros enfoques basados en interacciones como DeepWalk o node2vec.

    • English

      The large majority of the research performed on stance detection has been focused on developing more or less sophisticated text classification systems, even when many benchmarks are based on social network data such as Twitter. This paper aims to take on the stance detection task by placing the emphasis not so much on the text itself but on the interaction data available on social networks. More specifically, we propose a new method to leverage social information such as friends and retweets by generating Relational Embeddings, namely, dense vector representations of interaction pairs. Our experiments on seven publicly available datasets and four different languages (Basque, Catalan, Italian, and Spanish) show that combining our relational embeddings with discriminative textual methods helps to substantially improve performance, obtaining state-of-the-art results for six out of seven evaluation settings, outperforming strong baselines based on Large Language Models, or other popular interaction-based approaches such as DeepWalk or node2vec.

  • Referencias bibliográficas
    • Agerri, R., R. Centeno, M. Espinosa, J. F. de Landa, and Álvaro Rodrigo. 2021. Vaxxstance@iberlef 2021: Overview of the task on going...
    • AlDayel, A. and W. Magdy. 2021. Stance detection on social media: State of the art and trends. Information Processing & Management, 58(4):102597.
    • Alkhalifa, R. and A. Zubiaga. 2020. QMULSDS@ SardiStance: Leveraging Network Inter-actions to Boost Performance on Stance Detection using...
    • Augenstein, I. 2021. Towards explainable fact checking. ArXiv, abs/2108.10274.
    • Augenstein, I., T. Rocktäschel, A. Vlachos, and K. Bontcheva. 2016. Stance detection with bidirectional conditional encoding. In Proceedings...
    • Brown, T. B., B. Mann, N. Ryder, M. Subbiah, J. Kaplan, P. Dhariwal, A. Neelakantan, P. Shyam, G. Sastry, A. Askell, S. Agarwal, A. Herbert-Voss,...
    • Cignarella, A. T., M. Lai, C. Bosco, V. Patti, and P. Rosso. 2020. SardiStance@ EVALITA2020: Overview of the Task on Stance Detection...
    • Conforti, C., J. Berndt, M. T. Pilehvar, C. Giannitsarou, F. Toxvaerd, and N. Collier. 2020. Will-they-won’t-they: A very large dataset for...
    • Conneau, A., K. Khandelwal, N. Goyal, V. Chaudhary, G. Wenzek, F. Guzmán, E. Grave, M. Ott, L. Zettlemoyer, and V. Stoyanov. 2020. Unsupervised...
    • Conover, M. D., J. Ratkiewicz, M. Francisco, B. Gon¸calves, F. Menczer, and A. Flammini. 2011. Political Polarization on Twitter. In Proceedings...
    • Darwish, K., P. Stefanov, M. Aupetit, and P. Nakov. 2020. Unsupervised user stance detection on twitter. In Proceedings of the International...
    • Del Tredici, M., D. Marcheggiani, S. Schulte im Walde, and R. Fernández. 2019. You shall know a user by the company it keeps: Dynamic representations...
    • Derczynski, L., K. Bontcheva, M. Liakata, R. Procter, G. W. S. Hoi, and A. Zubiaga. 2017. SemEval-2017 task 8: RumourEval: Determining rumour...
    • Devlin, J., M. Chang, K. Lee, and K. Toutanova. 2019. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In...
    • Dubey, A., A. Jauhri, A. Pandey, A. Kadian, A. Al-Dahle, A. Letman, A. Mathur, A. Schelten, A. Yang, A. Fan, et al. 2024. The Llama 3 Herd...
    • Espinosa, M. S., R. Agerri, A. Rodrigo, and R. Centeno. 2020. DeepReading@ SardiStance: Combining Textual, Social and Emotional Features....
    • Ferraccioli, F., A. Sciandra, M. D. Pont, P. Girardi, D. Solari, and L. Finos. 2020. TextWiller@SardiStance, HaSpeede2: Text or Context?...
    • Friedman, J. H. 2001. Greedy function approximation: a gradient boosting machine. Annals of statistics, pages 1189–1232.
    • Fruchterman, T. M. J. and E. M. Reingold. 1991. Graph drawing by force-directed placement. Software: Practice and Experience, 21.
    • Gatto, J., O. Sharif, and S. Preum. 2023. Chain-of-thought embeddings for stance detection on social media. In H. Bouamor, J. Pino, and K....
    • Ghosh, S., P. Singhania, S. Singh, K. Rudra, and S. Ghosh. 2019. Stance detection in web and social media: a comparative study. In International...
    • Giorgioni, S., M. Politi, S. Salman, R. Basili, and D. Croce. 2020. Unitor @ sardistance2020: Combining transformer-based architectures...
    • Glandt, K., S. Khanal, Y. Li, D. Caragea, and C. Caragea. 2021a. Stance detection in covid-19 tweets. In Proceedings of the 59th Annual Meeting...
    • Glandt, K., S. Khanal, Y. Li, D. Caragea, and C. Caragea. 2021b. Stance detection in covid-19 tweets. In ACL/IJCNLP.
    • Grave, E., P. Bojanowski, P. Gupta, A. Joulin, and T. Mikolov. 2018. Learning word vectors for 157 languages. In Proceedings of the International...
    • Grover, A. and J. Leskovec. 2016. node2vec: Scalable feature learning for networks. Proceedings of the 22nd ACM SIGKDD International Conference...
    • Hardalov, M., A. Arora, P. Nakov, and I. Augenstein. 2021. Cross-domain labeladaptive stance detection. In Proceedings of the 2021 Conference...
    • Hardalov, M., A. Arora, P. Nakov, and I. Augenstein. 2022. Few-shot crosslingual stance detection with sentiment-based pre-training. In Proceedings...
    • Jiang, A. Q., A. Sablayrolles, A. Mensch, C. Bamford, D. S. Chaplot, D. d. l. Casas, F. Bressand, G. Lengyel, G. Lample, L. Saulnier, et al....
    • Kenter, T., A. Borisov, and M. de Rijke. 2016. Siamese CBOW: Optimizing word embeddings for sentence representations. In Proceedings of the...
    • Kojima, T., S. S. Gu, M. Reid, Y. Matsuo, and Y. Iwasawa. 2022. Large language models are zero-shot reasoners. In ICML 2022 Workshop on Knowledge...
    • Küçük, D. and F. Can. 2020. Stance Detection: a Survey. ACM Computing Surveys (CSUR), 53(1):1–37.
    • Lai, M., A. T. Cignarella, L. Finos, and A. Sciandra. 2021. Wordup! at vaxxstance 2021: Combining contextual information with textual and...
    • Lai, M., V. Patti, G. Ruffo, and P. Rosso. 2020. #brexit: Leave or remain? the role of user’s community and diachronic evolution on stance...
    • Li, Y., C. Zhao, and C. Caragea. 2021. Improving stance detection with multidataset learning and knowledge distillation. In Proceedings of...
    • Martín-Corral, D., M. García-Herranz, M. Cebrian, and E. Moro. 2022. Social media sensors to detect early warnings of influenza at scale....
    • McInnes, L., J. Healy, N. Saul, and L. Großberger. 2018. Umap: Uniform manifold approximation and projection. J. Open Source Softw., 3:861.
    • Mikolov, T., K. Chen, G. Corrado, and J. Dean. 2013. Efficient estimation of word representations in vector space. arXiv preprint arXiv:1301.3781.
    • Mishra, P., M. Del Tredici, H. Yannakoudakis, and E. Shutova. 2018. Author profiling for abuse detection. In Proceedings of the 27th International...
    • Mohammad, S., S. Kiritchenko, P. Sobhani, X. Zhu, and C. Cherry. 2016. SemEval-2016 task 6: Detecting stance in tweets. In Proceedings of...
    • Perozzi, B., R. Al-Rfou, and S. Skiena. 2014. Deepwalk: Online learning of social representations. In Proceedings of the 20th ACM SIGKDD international...
    • Pomerleau, D. and D. Rao. 2017. The fake news challenge: Exploring how artificial intelligence technologies could be leveraged to combat fake...
    • Rashed, A., M. Kutlu, K. Darwish, T. Elsayed, and C. Bayrak. 2021. Embeddings-based clustering for target specific stances: The case of a...
    • Schiller, B., J. Daxenberger, and I. Gurevych. 2021. Stance detection benchmark: How robust is your stance detection? KIK ¨unstliche Intelligenz,...
    • Sobhani, P., D. Inkpen, and X. Zhu. 2017. A dataset for multi-target stance detection. In Proceedings of the 15th Conference of the European...
    • Stefanov, P., K. Darwish, A. Atanasov, and P. Nakov. 2020. Predicting the topical stance and political leaning of media using tweets. In ACL.
    • Taranukhin, M., V. Shwartz, and E. Milios. 2024. Stance reasoner: Zero-shot stance detection on social media with explicit reasoning. In N....
    • Taulé, M., F. Rangel, M. A. Martí, and P. Rosso. 2018. Overview of the task on multimodal stance detection in tweets on catalan 1oct referendum....
    • Wang, X., J. Wei, D. Schuurmans, Q. V. Le, E. H. Chi, S. Narang, A. Chowdhery, and D. Zhou. 2023. Self-consistency improves chain of thought...
    • Wei, J., X.Wang, D. Schuurmans, M. Bosma, brian ichter, F. Xia, E. H. Chi, Q. V. Le, and D. Zhou. 2022. Chain of thought prompting elicits...
    • Zhang, B., X. Fu, D. Ding, H. Huang, Y. Li, and L. Jing. 2023a. Investigating chain-of-thought with chatgpt for stance detection on social...
    • Zhang, Z., A. Zhang, M. Li, and A. Smola. 2023b. Automatic chain of thought prompting in large language models. In The Eleventh International...
    • Zotova, E., R. Agerri, M. Nuñez, and G. Rigau. 2020. Multilingual stance detection in tweets: The Catalonia independence corpus. In Proceedings...
    • Zotova, E., R. Agerri, and G. Rigau. 2021. Semi-automatic generation of multilingual datasets for stance detection in Twitter. Expert Systems...
    • Zubiaga, A., B. Wang, M. Liakata, and R. Procter. 2019. Political homophily in independence movements: Analyzing and classifying social media...
Fundación Dialnet

Mi Documat

Opciones de artículo

Opciones de compartir

Opciones de entorno