Using shallow and deep learning to automatically detect hate motivated by gender and sexual orientation on Twitter in Spanish
Open accessAbstract
The increasing phenomenon of “cyberhate” is concerning because of the potential social implications of this form of verbal violence, which is aimed at already-stigmatized social groups. According to information collected by the Ministry of the Interior of Spain, the category of sexual orientation and gender identity is subject to the third-highest number of registered hate crimes, ranking behind racism/xenophobia and ideology. However, most of the existing computational approaches to online hate detection simultaneously attempt to address all types of discrimination, leading to weaker prototype performances. These approaches focus on other reasons for hate—primarily racism and xenophobia—and usually focus on English messages. Furthermore, few detection models have used manually generated databases as a training corpus. Using supervised machine learning techniques, the present research sought to overcome these limitations by developing and evaluating an automatic detector of hate speech motivated by gender and sexual orientation. The focus was Spanish-language posts on Twitter. For this purpose, eight predictive models were developed from an ad hoc generated training corpus, using shallow modeling and deep learning. The evaluation metrics showed that the deep learning algorithm performed significantly better than the shallow modeling algorithms, and logistic regression yielded the best performance of the shallow algorithms.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
Similar research has already been undertaken for the automatic detection of sexual prejudice: Arcila-Calderón et al. (2021) used shallow and deep learning to automatically detect hate speech based specifically on gender and sexual orientation.
“In fact, similar research has already been undertaken for the automatic detection of sexual prejudice: for instance, Arcila-Calderón et al. (2021) used shallow and deep learning to automatically detect hate speech that was based specifically on gender and sexual orientation.”
From “Real men in the battlefield”: a hybrid AI–discourse analysis of online homophobia and transphobia (2026) · cites this paper as Arcila-Calderón et al. (2021)
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
SemEval-2019 Task 5: Multilingual Detection of Hate Speech Against Immigrants and Women in Twitter
Basile, V., Bosco, C., Fersini, E., Nozza, D., Patti, V., Pardo, F. M. R., Rosso, P., & Sanguinetti, M. (2019) · International Workshop on Semantic Evaluation (SemEval) · doi:10.18653/v1/s19-2007 · Cited by 889 · see citing works
Fanning the Flames of Hate: Social Media and Hate Crime
Müller, K., & Schwarz, C. (2021) · Journal of the European Economic Association · doi:10.1093/jeea/jvaa045 · Cited by 448 · see citing works
Us and them: identifying cyber hate on Twitter across multiple protected characteristics
Burnap, P., & Williams, M. L. (2016) · EPJ Data Science · doi:10.1140/epjds/s13688-016-0072-6 · Cited by 397 · see citing works
Developing an online hate classifier for multiple social media platforms
Salminen, J. O., Hopf, M., Chowdhury, S. A., Jung, S., Almerekhi, H., & Jansen, B. J. J. (2020) · Human-centric Computing and Information Sciences · doi:10.1186/s13673-019-0205-6 · Cited by 295 · see citing works
Detecting Hate Speech in Social Media
Malmasi, S., & Zampieri, M. (2017) · doi:10.26615/978-954-452-049-6_062 · Cited by 289 · see citing works
Violence motivated by perception of sexual orientation and gender identity: a systematic review
Blondeel, K., Vasconcelos, S. D., Garcia‐Moreno, C., Stephenson, R. B., Temmerman, M., & Toskin, I. (2017) · Bulletin of the World Health Organization · doi:10.2471/blt.17.197251 · Cited by 257 · see citing works
Detecting and Monitoring Hate Speech in Twitter
Pereira-Kohatsu, J. C., Quijano-Sánchez, L., Liberatore, F., & Camacho‐Collados, M. (2019) · Sensors · doi:10.3390/s19214654 · Cited by 220 · see citing works
Understanding the predictive power of social media
Kalampokis, E., Tambouris, E., & Tarabanis, K. A. (2013) · Internet Research · doi:10.1108/intr-06-2012-0114 · Cited by 190 · see citing works
Automatic Identification and Classification of Misogynistic Language on Twitter
Anzovino, M., Fersini, E., & Rosso, P. (2018) · Lecture notes in computer science · doi:10.1007/978-3-319-91947-8_6 · Cited by 183 · see citing works
Southern, R., & Harmer, E. (2019) · Social Science Computer Review · doi:10.1177/0894439319865519 · Cited by 140 · see citing works
Lingiardi, V., Carone, N., Semeraro, G., Musto, C., D’Amico, M., & Brena, S. (2020) · Behaviour & Information Technology · doi:10.1080/0144929x.2019.1607903 · Cited by 113 · see citing works
A Survey on Text Classification: From Shallow to Deep LearningPreprint
Li, Q., Peng, H. M., Li, J., Xia, C., Yang, R., Sun, L., Yu, P. S., & He, L. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2008.00364 · Cited by 110 · see citing works
Normalizing misogyny: hate speech and verbal abuse of female politicians on Japanese Twitter
Fuchs, T., & Schäfer, F. (2020) · Japan Forum · doi:10.1080/09555803.2019.1687564 · Cited by 84 · see citing works
Deeplearning Model Used in Text Classification
Cai, J., Li, J., Li, W., & Ji, W. (2018) · International Computer Conference on Wavelet Active Media Technology and Information Processing (ICCWAMTIP) · doi:10.1109/iccwamtip.2018.8632592 · Cited by 83 · see citing works
Alden, H. L., & Parker, K. F. (2005) · Deviant Behavior · doi:10.1080/016396290931614 · Cited by 78 · see citing works
The problem of identifying misogynist language on Twitter (and other online social spaces)
Hewitt, S., Tiropanis, T., & Bokhove, C. (2016) · ACM Conference on Web Science (WebSci) · doi:10.1145/2908131.2908183 · Cited by 73 · see citing works
Calderón, C. A., Blanco‐Herrero, D., & Apolo, M. B. V. (2020) · Revista Española de Investigaciones Sociológicas · doi:10.5477/cis/reis.172.21 · Cited by 55 · see citing works
Self-citationTaxonomia de la comunicació violenta i el discurs de l’odi a Internet
Llinares, F. M. (2016) · IDP Revista de Internet Derecho y Política · doi:10.7238/idp.v0i22.2975 · Cited by 49 · see citing works
Amores, J. J., Blanco‐Herrero, D., Holgado, P. S., & Frías-Vázquez, M. (2021) · Cuadernos info · doi:10.7764/cdi.49.27817 · Cited by 48 · see citing works
Self-citationTrust across political conflicts: Evidence from a survey experiment in divided societies
Martini, S., & Torcal, M. (2016) · Party Politics · doi:10.1177/1354068816685933 · Cited by 44 · see citing works
Automated Detection of Hate Speech towards Woman on Twitter
Sahi, H., Kılıç, Y., & Sağlam, R. B. (2018) · doi:10.1109/ubmk.2018.8566304 · Cited by 43 · see citing works
del Azuay, U., Apolo, M. B. V., Calderón, C. A., de Salamanca, U., Amores, J. J., & de Salamanca, U. (2019) · Revista de la Asociación Española de Investigación de la Comunicación · doi:10.24137/raeic.6.12.2 · Cited by 39 · see citing works
Self-citationAguilés, A. V., & Pecourt, J. (2021) · Teknokultura Revista de Cultura Digital y Movimientos Sociales · doi:10.5209/tekn.70225 · Cited by 39 · see citing works
Puente, S. N., & Romero, D. F. (2019) · Investigaciones Feministas · doi:10.5209/infe.66501 · Cited by 34 · see citing works
Natural Language Processing and Information Systems
Silberztein, M. D., Atigui, F., Kornyshova, E., Métais, E., & Meziane, F. (2018) · Lecture notes in computer science · doi:10.1007/978-3-319-91947-8 · Cited by 18 · see citing works
Ahluwalia, R., Shcherbinina, E., Callow, E., Nascimento, A. C. A., & Cock, M. D. (2018) · University of Washington Tacoma Digital Commons (University of Washington Tacoma) · Cited by 15 · see citing works
Gallego, M., Gualda, E., & Díaz, C. R. (2017) · Repositorio Institucional de la Universidad de Huelva (Universidad de Huelva) · doi:10.14273/unisa-929 · Cited by 9 · see citing works
Carratalá, A. (2020) · LA Referencia (Red Federada de Repositorios Institucionales de Publicaciones Científicas) · Cited by 1 · see citing works
Flagged first, then by citations
Research works printed but not linked: 1
- Müller, K.; Schwarz, C. Fanning the Flames of Hate: Social Media and Hate Crime. J. Eur. Econ. Assoc. 2021, 19, 2131-2167.
Cited by
Sorted by citations
A comprehensive review on automatic hate speech detection in the age of the transformer
Ramos, G., Batista, F., Ribeiro, R., Fialho, P., Moro, S., Fonseca, A. J. F., Guerra, R., Carvalho, P., Marques, C. M. V. A., & Silva, C. (2024) · Social Network Analysis and Mining · doi:10.1007/s13278-024-01361-3 · Cited by 54 · see citing works
Calderón, C. A., Holgado, P. S., Gómez, J., Barbosa, M., Qi, H., Matilla-Molina, A., Amado, P., Guzmán, A., López-Matías, D., & Fernández-Villazala, T. (2024) · Humanities and Social Sciences Communications · doi:10.1057/s41599-024-03899-1 · Cited by 43 · see citing works
Detecting Hateful and Offensive Speech in Arabic Social Media Using Transfer Learning
Boulouard, Z., Ouaissa, M., Ouaissa, M., Krichen, M., Almutiq, M., & Gasmi, K. (2022) · Applied Sciences · doi:10.3390/app122412823 · Cited by 27 · see citing works
Calderón, C. A., Amores, J. J., Holgado, P. S., Vrysis, L., Vryzas, N., & Alonso, M. O. (2022) · Sustainability · doi:10.3390/su142013094 · Cited by 26 · see citing works
Self-citationGarcía, S. A., & Menéndez, I. M. (2022) · El Profesional de la Informacion · doi:10.3145/epi.2023.ene.06 · Cited by 21 · see citing works
Leveraging Transfer Learning for Hate Speech Detection in Portuguese Social Media Posts
Ramos, G., Batista, F., Ribeiro, R., Fialho, P., Moro, S., Fonseca, A. J. F., Guerra, R., Carvalho, P., Marques, C. M. V. A., & Silva, C. (2024) · IEEE Access · doi:10.1109/access.2024.3430848 · Cited by 16 · see citing works
González-Baquero, W., Amores, J. J., & Calderón, C. A. (2023) · Religions · doi:10.3390/rel14060724 · Cited by 14 · see citing works
Self-citationEl discurso de odio en Twitter durante la crisis migratoria de Ceuta en mayo de 2021
Román-San-Miguel, A., Olivares-García, F. J., & Jiménez-Zafra, S. M. (2022) · Revista ICONO14 · doi:10.7195/ri14.v20i2.1858 · Cited by 13 · see citing works
Hate Speech and Polarization Around the “Trans Law” in Spain
Holgado, P. S., Calderón, C. A., & Barbosa, M. (2023) · Politics and Governance · doi:10.17645/pag.v11i2.6374 · Cited by 13 · see citing works
Jayapal, P. K., Raja, D. R. K., & Lella, K. K. (2023) · International Journal of Knowledge and Innovation Studies · doi:10.56578/ijkis010202 · Cited by 10 · see citing works
Measuring Online Hate on 4chan Using Pre-Trained Deep Learning Models
Bermudez-Villalva, A., Mehrnezhad, M., & Toreini, E. (2025) · IEEE Transactions on Technology and Society · doi:10.1109/tts.2025.3549931 · Cited by 9 · see citing works
Analyzing Zero-Shot transfer Scenarios across Spanish variants for Hate Speech Detection
Castillo-López, G., Riabi, A., & Seddah, D. (2023) · Workshop on NLP for Similar Languages, Varieties and Dialects (VarDial) · doi:10.18653/v1/2023.vardial-1.1 · Cited by 9 · see citing works
Systematic literature review on hate speech detection in Indian low-resource languages
Pannerselvam, K., & Saranya, R. (2025) · Journal of Computational Social Science · doi:10.1007/s42001-025-00432-5 · Cited by 7 · see citing works
Arısoy, M. V., Yalçınkaya, M. A., Gürfidan, R., & Arısoy, A. (2025) · Applied Sciences · doi:10.3390/app15041715 · Cited by 4 · see citing works
Sibrian, N., Alfaro, A., & Núñez, J. C. (2024) · Revista Latina de Comunicación Social · doi:10.4185/rlcs-2024-2226 · Cited by 4 · see citing works
Amores, J. J., Escudero-Garrido, M., & González-Baquero, W. (2026) · Social Sciences & Humanities Open · doi:10.1016/j.ssaho.2026.102835 · Cited by 3 · see citing works
Self-citationLi, C., Cai, Y., Habeeb, L. J., Rahman, A., & Ritzkal, R. (2023) · Healthcraft Frontiers · doi:10.56578/hf010101 · Cited by 3 · see citing works
Segura-Navarrete, A., Martínez-Araneda, C., Labrín, S. M., Gómez, P., Vidal‐Castro, C., Espinoza-Silva, S., & Gutiérrez-Bunster, T. (2026) · IEEE Access · doi:10.1109/access.2026.3661575 · Cited by 1 · see citing works
Understanding Online Hate Toward Sexual and Gender Minorities: A Systematic Review
Mariotto, M., Costa, S., Brango, N. D., Corbelli, G., Verbena, S., Palladino, B. E., Zuffianò, A., & Ioverno, S. (2026) · Trauma Violence & Abuse · doi:10.1177/15248380261429520 · Cited by 1 · see citing works
Balbín, A. M., Caetano, N. S., Conde, M. Á., Costa, P., Felgueiras, C., Fidalgo-Blanco, Á., Fonseca, D., Gamazo, A., García‐Holgado, A., García‐Peñalvo, F. J., et al. (2023) · Lecture notes in educational technology · doi:10.1007/978-981-99-0942-1_73 · Cited by 1 · see citing works
“Real men in the battlefield”: a hybrid AI–discourse analysis of online homophobia and transphobia
Baider, F., & Mesaritou, O. (2026) · Frontiers in Communication · doi:10.3389/fcomm.2026.1748828
Morales-Garzón, A., Sánchez-Pérez, G. M., Sierra, J. C., & Martín-Bautista, M. J. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-42935-4_4
Identyfikacja i analiza przemocy wobec polskich polityków w postach na Twitterze
Kijewska, B., & Raca, K. (2024) · Horyzonty Polityki · doi:10.35765/hp.2572
DETECÇÃO AUTOMÁTICA DE DISCURSO HOMOFÓBICO UTILIZANDO APRENDIZADO DE MÁQUINA
Silva, S. H. S., Medeiros, E. C., Moser, P. C., Silva, B. G. F., Carvalho, F. F. D., Fonsêca, J. C. B., de Andrade, R. C. D., & Domingues, M. A. D. O. (2025) · Aracê. · doi:10.56238/arev7n5-029
Botas, B., Cifuentes, J. A., Jiménez, Y. A., & Ruiz, M. E. (2026) · Journal of Computational Social Science · doi:10.1007/s42001-025-00459-8
- Authors
- Arcila-Calderón, C., Amores, J. J., Sánchez-Holgado, P., & Blanco-Herrero, D.
- Affiliations
- Faculty of Social Sciences, Unamuno Campus, University of Salamanca, 37007 Salamanca, Spain
- Universidad de Salamanca (ES)
- Venue
- Multimodal Technologies and Interaction
- Publisher
- MDPI AG
- Published
- 2021-10-13
- Volume
- 5
- Issue
- 10
- Pages
- 63
- ISSN
- 2414-4088 (ISSN-L)
- OpenAlex
- W3206047310
- Cited by
- 24
- References
- 27
- Citations by year
- 2026: 5 · 2025: 4 · 2024: 4 · 2023: 7 · 2022: 4
- FWCI
- 1.33
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- Locations
- Multimodal Technologies and Interaction (publishedVersion, cc-by)
- Gredos (University of Salamanca) (publishedVersion, cc-by-nc-nd)
- Hispana (publishedVersion, cc-by-nc-nd)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- Funders
- Rights, Equality and Citizenship Programme (875217)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Hate Speech and Cyberbullying Detection
- Physical Sciences › Computer Science › Artificial Intelligence › Sentiment Analysis and Opinion Mining
- Social Sciences › Sociology and Political Science › Misinformation and Its Impacts
- Keywords
- online hate speech detection, cyberhate, Twitter, Spanish language, deep learning, shallow learning, logistic regression, training corpus, hate speech detection
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
