Identification of Multiword Expressions in Tweets for Hate Speech Detection - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year :

Identification of Multiword Expressions in Tweets for Hate Speech Detection

Abstract

Multiword expression (MWE) identification in tweets is a complex task due to the complex linguistic nature of MWEs combined with the non-standard language use in social networks. MWE features were shown to be helpful for hate speech detection (HSD). In this article, we present joint experiments on these two related tasks on English Twitter data: first we focus on the MWE identification task, and then we observe the influence of MWE-based features on the HSD task. For MWE identification, we compare the performance of two systems: lexicon-based and deep neural networks-based (DNN). We experimentally evaluate seven configurations of a state-of-the-art DNN system based on recurrent networks using pre-trained contextual embeddings from BERT. The DNN-based system outperforms the lexicon-based one thanks to its superior generalisation power, yielding much better recall. For the HSD task, we propose a new DNN architecture for incorporating MWE features. We confirm that MWE features are helpful for the HSD task. Moreover, the proposed DNN architecture beats previous MWE-based HSD systems by 0.4 to 1.1 F-measure points on average on four Twitter HSD corpora.
Fichier principal
Vignette du fichier
LREC2022__Multiword_Identification_in_Tweets_for_Hate_Speech_Detection.pdf (243.5 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-03676508 , version 1 (24-05-2022)

Identifiers

  • HAL Id : hal-03676508 , version 1

Cite

Nicolas Zampieri, Carlos Ramisch, Irina Illina, Dominique Fohr. Identification of Multiword Expressions in Tweets for Hate Speech Detection. LREC 2022 - 13th Edition of its Language Resources and Evaluation Conference, Jun 2022, Marseille, France. ⟨hal-03676508⟩
96 View
190 Download

Share

Gmail Facebook Twitter LinkedIn More