Exportar Publicação

Fialho, P., Ribeiro, R., Batista, F., Ramos, G., Fonseca, A., Moro, S....Silva, C. (2025). Counter Hate Speech Detection in Youtube Conversations. In Information Processing and Management of Uncertainty in Knowledge-Based Systems. (pp. 94-105).

P. M. Fialho et al.,  "Counter Hate Speech Detection in Youtube Conversations", in Information Processing and Management of Uncertainty in Knowledge-Based Systems, 2025, pp. 94-105

@inproceedings{fialho2025_1764998615677,
	author = "Fialho, P. and Ribeiro, R. and Batista, F. and Ramos, G. and Fonseca, A. and Moro, S. and Guerra, R. and Carvalho, P. and Marques, C. and Silva, C.",
	title = "Counter Hate Speech Detection in Youtube Conversations",
	booktitle = "Information Processing and Management of Uncertainty in Knowledge-Based Systems",
	year = "2025",
	editor = "",
	volume = "",
	number = "",
	series = "",
	doi = "10.1007/978-3-031-73997-2_9",
	pages = "94-105",
	publisher = "",
	address = "",
	organization = ""
}

TY  - CPAPER
TI  - Counter Hate Speech Detection in Youtube Conversations
T2  - Information Processing and Management of Uncertainty in Knowledge-Based Systems
AU  - Fialho, P.
AU  - Ribeiro, R.
AU  - Batista, F.
AU  - Ramos, G.
AU  - Fonseca, A.
AU  - Moro, S.
AU  - Guerra, R.
AU  - Carvalho, P.
AU  - Marques, C.
AU  - Silva, C.
PY  - 2025
SP  - 94-105
DO  - 10.1007/978-3-031-73997-2_9
AB  - One of the forms to fight the spread of hate speech is to reply to such utterances with counter speech. In this paper, we present models to identify counter speech, based on an annotated set of comments to Youtube videos spoken in Portuguese. We leverage the sequence of replies to comments, to form a corpus of pairs of comments, where a target is labelled as neutral, hate speech or counter speech, relative to a context, which corresponds to a preceding comment. To the best of our knowledge, this is the first corpus with counter speech examples in Portuguese. Using such corpus, we compute models by fine-tuning pre-trained models based on Transformers, and experiment with both multilingual and Portuguese pre-trained models. Our approach follows a recent work for English, both in corpus design and experimental setup, and we obtain similar performance results in Portuguese.
ER  -