Cyberbullying detection, prevention, and analysis on social media via trustable LSTM-autoencoder networks over synthetic data: The TLA-NET approach

Vista sencilla de ítem
dc.contributor.authorCuzzocrea, Alfredo
dc.contributor.authorAkter, Mst Shapna
dc.contributor.authorShahriar, Hossain
dc.contributor.authorGarcía Bringas, Pablo
dc.date.accessioned2025-03-14T11:11:08Z
dc.date.available2025-03-14T11:11:08Z
dc.date.issued2025-02
dc.date.updated2025-03-14T11:11:08Z
dc.description.abstractThe plague of cyberbullying on social media exerts a dangerous influence on human lives. Due to the fact that online social networks continue to daily expand, the proliferation of hate speech is also growing. Consequentially, distressing content is often implicated in the onset of depression and suicide-related behaviors. In this paper, we propose an innovative framework, named as the trustable LSTM-autoencoder network (TLA NET), which is designed for the detection of cyberbullying on social media by employing synthetic data. We introduce a state-of-the-art method for the automatic production of translated data, which are aimed at tackling data availability issues. Several languages, including Hindi and Bangla, continue to face research limitations due to the absence of adequate datasets. Experimental identification of aggressive comments is carried out via datasets in Hindi, Bangla, and English. By employing TLA NET and traditional models, such as long short-term memory (LSTM), bidirectional long short-term memory (BiLSTM), the LSTM-autoencoder, Word2vec, bidirectional encoder representations from transformers (BERT), and the Generative Pre-trained Transformer 2 (GPT-2), we perform the experimental identification of aggressive comments in datasets in Hindi, Bangla, and English. In addition to this, we employ evaluation metrics that include the F1-score, accuracy, precision, and recall, to assess the performance of the models. Our model demonstrates outstanding performance across all the datasets by achieving a remarkable 99% accuracy and positioning itself as a frontrunner when compared to previous works that make use of the dataset featured in this researchen
dc.description.sponsorshipThis work was partially supported by project SERICS (PE00000014) under the MUR National Recovery and Resilience Plan funded by the European Union- NextGenerationEUen
dc.identifier.citationCuzzocrea, A., Akter, M. S., Shahriar, H., & Garcia Bringas, P. (2025). Cyberbullying detection, prevention, and analysis on social media via trustable LSTM-autoencoder networks over synthetic data: The TLA-NET approach. Future Internet, 17(2). https://doi.org/10.3390/FI17020084
dc.identifier.doi10.3390/FI17020084
dc.identifier.eissn1999-5903
dc.identifier.urihttp://hdl.handle.net/20.500.14454/2534
dc.language.isoeng
dc.publisherMultidisciplinary Digital Publishing Institute (MDPI)
dc.rights© 2025 by the authors
dc.subject.otherCyber-bullying
dc.subject.otherDeep learning
dc.subject.otherNatural language processing
dc.subject.otherNeural networks
dc.titleCyberbullying detection, prevention, and analysis on social media via trustable LSTM-autoencoder networks over synthetic data: The TLA-NET approachen
dc.typejournal article
dcterms.accessRightsopen access
oaire.citation.issue2
oaire.citation.titleFuture Internet
oaire.citation.volume17
oaire.licenseConditionhttps://creativecommons.org/licenses/by/4.0/
oaire.versionVoR
Archivos
Bloque original
Mostrando 1 - 1 de 1
Miniatura
Nombre:
cuzzocrea_cyberbullying_2025.pdf
Tamaño:
2.61 MB
Formato:
Adobe Portable Document Format
Descargar
Colecciones
Artículos