{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,25]],"date-time":"2026-02-25T06:18:53Z","timestamp":1772000333938,"version":"3.50.1"},"reference-count":43,"publisher":"MDPI AG","issue":"2","license":[{"start":{"date-parts":[[2026,2,16]],"date-time":"2026-02-16T00:00:00Z","timestamp":1771200000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Information"],"abstract":"<jats:p>Cyberbullying demonstrates notable metaphorical and contextual traits, characterized by a high-dimensional sparse semantic space and dynamic evolution. Pre-trained models utilize extensive textual data for learning and employ transformer-based word vector generation techniques to accurately capture intricate semantics and nuanced syntax in text. However, although a single pre-trained model demonstrates strong performance in contextual modeling, it still faces challenges including inadequate feature representation and limited generalization capability in classifying cyberbullying texts. This study proposes a cyberbullying detection model employing BERT-BiGRU-CNN (BBGC) to address this issue. The BBGC model initially employs BERT to produce word embeddings, subsequently inputs them into a BiGRU layer to acquire sequence features, and finally utilizes a CNN for the extraction of local features. The features derived from BERT, BiGRU, and CNN are integrated, followed by the application of the softmax function to yield the final outcome of cyberbullying detection. Experimental findings indicate that the BBGC fusion model surpasses individual pre-trained models in the task of detecting cyberbullying text. Furthermore, in comparison to hybrid neural network models utilizing RoBERTa, ALBERT, DistilBERT and other pre-trained models, the BBGC model demonstrates considerable advantages.<\/jats:p>","DOI":"10.3390\/info17020205","type":"journal-article","created":{"date-parts":[[2026,2,16]],"date-time":"2026-02-16T11:11:28Z","timestamp":1771240288000},"page":"205","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Cyberbullying Detection Based on Hybrid Neural Networks and Multi-Feature Fusion"],"prefix":"10.3390","volume":"17","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8689-6626","authenticated-orcid":false,"given":"Junkuo","family":"Cao","sequence":"first","affiliation":[{"name":"Information Network and Data Center, Hainan Normal University, Haikou 571158, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-4871-5594","authenticated-orcid":false,"given":"Yunpeng","family":"Xiong","sequence":"additional","affiliation":[{"name":"School of Intelligence Institute, Hainan Normal University, Haikou 571158, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Weiquan","family":"Wang","sequence":"additional","affiliation":[{"name":"Hainan Provincial Center for Disease Control and Prevention, Haikou 570203, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guolian","family":"Chen","sequence":"additional","affiliation":[{"name":"State-Owned Assets Management Office, Hainan Normal University, Haikou 571158, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2026,2,16]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"139","DOI":"10.1007\/s13278-023-01152-2","article-title":"Investigating the cyberbullying risk in digital media: Protecting victims in school teenagers","volume":"13","author":"Obaidat","year":"2023","journal-title":"Soc. Netw. Anal. Min."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"e34051","DOI":"10.1097\/MD.0000000000034051","article-title":"Cyberbullying in teenagers\u2014A true burden in the era of online socialization","volume":"102","author":"Balas","year":"2023","journal-title":"Medicine"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1515\/ijamh-2021-0133","article-title":"Cyberbullying in adolescents: A literature review","volume":"35","author":"Santre","year":"2023","journal-title":"Int. J. Adolesc. Med. Health"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"2024079","DOI":"10.31893\/multirev.2024079","article-title":"Cyberbullying and cyberstalking: Parents\u2019 role to protect their children","volume":"7","author":"Haziri","year":"2024","journal-title":"Multidiscip. Rev."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3375547","article-title":"A survey of figurative language and its computational detection in online social networks","volume":"14","author":"Abulaish","year":"2020","journal-title":"ACM Trans. Web (TWEB)"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"93","DOI":"10.58982\/jdlp.v2i2.314","article-title":"The role of INSTIKI students in preventing cyberbullying among teenagers","volume":"2","author":"Sari","year":"2023","journal-title":"J. Digit. Law Policy"},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Singh, V.K., Mohankumar, P., and Kamal, A. (2024). Cyber Threat Detection by Leveraging Contextual and Semantic Knowledge. International Conference on Data-Processing and Networking, Springer.","DOI":"10.1007\/978-981-96-3102-5_27"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"2288492","DOI":"10.1080\/2331186X.2023.2288492","article-title":"The digital defence against cyberbullying: A systematic review of tech-based approaches","volume":"10","author":"Nee","year":"2023","journal-title":"Cogent Educ."},{"key":"ref_9","first-page":"2339","article-title":"Detection of Cyberbullying on Social Media Using Naive Bayes Classifier","volume":"Volume 1","author":"Parveen","year":"2024","journal-title":"2024 10th International Conference on Advanced Computing and Communication Systems (ICACCS)"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"506","DOI":"10.1016\/j.procs.2024.06.200","article-title":"Cyberbullying detection system on social media using supervised machine learning","volume":"239","author":"Perera","year":"2024","journal-title":"Procedia Comput. Sci."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Thangarasu, G., and Alla, K.R. (2023). Detection of Cyberbullying Tweets in Twitter Media Using Random Forest Classification. 2023 IEEE 13th Symposium on Computer Applications & Industrial Electronics (ISCAIE), IEEE.","DOI":"10.1109\/ISCAIE57739.2023.10165118"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"115001","DOI":"10.1016\/j.eswa.2021.115001","article-title":"Cyberbullying detection: Utilizing social media features","volume":"179","author":"Utku","year":"2021","journal-title":"Expert Syst. Appl."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"e5627","DOI":"10.1002\/cpe.5627","article-title":"Cyberbullying detection in social media text based on character-level convolutional neural network with shortcuts","volume":"32","author":"Lu","year":"2020","journal-title":"Concurr. Comput. Pract. Exp."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"100111","DOI":"10.1016\/j.nlp.2024.100111","article-title":"Recurrent neural network based multiclass cyber bullying classification","volume":"9","author":"Sifath","year":"2024","journal-title":"Nat. Lang. Process. J."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"25857","DOI":"10.1109\/ACCESS.2022.3153675","article-title":"DEA-RNN: A hybrid deep learning approach for cyberbullying detection in Twitter social media platform","volume":"10","author":"Murshed","year":"2022","journal-title":"IEEE Access"},{"key":"ref_16","first-page":"181","article-title":"LSTM-based model for cyberbully detection","volume":"18","author":"Esan","year":"2024","journal-title":"LAUTECH J. Eng. Technol."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"1839","DOI":"10.1007\/s00530-020-00701-5","article-title":"Cyberbullying detection solutions based on deep learning architectures","volume":"29","author":"Iwendi","year":"2023","journal-title":"Multimed. Syst."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"4291","DOI":"10.1109\/TNNLS.2020.3019893","article-title":"Attention in natural language processing","volume":"32","author":"Galassi","year":"2020","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Luo, Y., Zhang, X., Hua, J., and Shen, W. (2021). Multi-featured cyberbullying detection based on deep learning. 2021 16th International Conference on Computer Science & Education (ICCSE), IEEE.","DOI":"10.1109\/ICCSE51940.2021.9569270"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Wang, J., Fu, K., and Lu, C.T. (2020). Sosnet: A graph convolutional network approach to fine-grained cyberbullying detection. 2020 IEEE International Conference on Big Data (Big Data), IEEE.","DOI":"10.1109\/BigData50022.2020.9378065"},{"key":"ref_21","unstructured":"Devlin, J. (2018). Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv."},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Delobelle, P., Winters, T., and Berendt, B. (2020). Robbert: A dutch roberta-based language model. arXiv.","DOI":"10.18653\/v1\/2020.findings-emnlp.292"},{"key":"ref_23","unstructured":"Lan, Z. (2019). Albert: A lite bert for self-supervised learning of language representations. arXiv."},{"key":"ref_24","unstructured":"Sanh, V. (2019). DistilBERT, A Distilled Version of BERT: Smaller, Faster, Cheaper and Lighter. arXiv."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"1897","DOI":"10.1007\/s00530-020-00710-4","article-title":"CyberBERT: BERT for cyberbullying identification: BERT for cyberbullying identification","volume":"28","author":"Paul","year":"2022","journal-title":"Multimed. Syst."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"97391","DOI":"10.1109\/ACCESS.2023.3313113","article-title":"Cyberbullying detection and severity determination model","volume":"11","author":"Obaid","year":"2023","journal-title":"IEEE Access"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"1537","DOI":"10.1007\/s11280-021-00920-4","article-title":"A Bi-GRU with attention and CapsNet hybrid model for cyberbullying detection on social media","volume":"25","author":"Kumar","year":"2022","journal-title":"World Wide Web"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"1351","DOI":"10.11591\/eei.v13i2.6530","article-title":"Enhancing Arabic offensive language detection with BERT-BiGRU model","volume":"13","author":"Bensoltane","year":"2024","journal-title":"Bull. Electr. Eng. Inform."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"103504","DOI":"10.1109\/ACCESS.2024.3431939","article-title":"From Text to Insight: An Integrated CNN-BiLSTM-GRU Model for Arabic Cyberbullying Detection","volume":"12","author":"Daraghmi","year":"2024","journal-title":"IEEE Access"},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"7881","DOI":"10.1109\/ACCESS.2022.3143799","article-title":"HCovBi-caps: Hate speech detection using convolutional and Bi-directional gated recurrent unit with Capsule network","volume":"10","author":"Khan","year":"2022","journal-title":"IEEE Access"},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"156","DOI":"10.3390\/make6010009","article-title":"An Ensemble-Based Multi-Classification Machine Learning Classifiers Approach to Detect Multiple Classes of Cyberbullying","volume":"6","author":"Alqahtani","year":"2024","journal-title":"Mach. Learn. Knowl. Extr."},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Talpur, B.A., and O\u2019Sullivan, D. (2020). Multi-class imbalance in text classification: A feature engineering approach to detect cyberbullying in twitter. Informatics, 7.","DOI":"10.3390\/informatics7040052"},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"1781","DOI":"10.1109\/TCSS.2023.3236527","article-title":"BiCapsHate: Attention to the linguistic context of hate via bidirectional capsules and hatebase","volume":"11","author":"Kamal","year":"2023","journal-title":"IEEE Trans. Comput. Soc. Syst."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"694","DOI":"10.3390\/analytics2030038","article-title":"The use of a large language model for cyberbullying detection","volume":"2","author":"Ogunleye","year":"2023","journal-title":"Analytics"},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"3881","DOI":"10.1109\/TCSS.2024.3422185","article-title":"Cyberbullying Detection Using PCA Extracted GLOVE Features and RoBERTaNet Transformer Learning Model","volume":"12","author":"Umer","year":"2024","journal-title":"IEEE Trans. Comput. Soc. Syst."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"1941","DOI":"10.1007\/s00530-020-00690-5","article-title":"ALBERT-based fine-tuning model for cyberbullying analysis","volume":"28","author":"Tripathy","year":"2022","journal-title":"Multimed. Syst."},{"key":"ref_37","first-page":"75","article-title":"Cyberbullying Detection using Ensemble Method","volume":"12","author":"Saranyanath","year":"2022","journal-title":"CS IT Conf. Proc."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"4335","DOI":"10.1016\/j.jksuci.2022.05.006","article-title":"BiCHAT: BiLSTM with deep CNN and hierarchical attention for hate speech detection","volume":"34","author":"Khan","year":"2022","journal-title":"J. King Saud Univ.-Comput. Inf. Sci."},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"46611","DOI":"10.1007\/s11042-023-15372-3","article-title":"FAEO-ECNN: Cyberbullying detection in social media platforms using topic modelling and deep learning","volume":"82","author":"Murshed","year":"2023","journal-title":"Multimed. Tools Appl."},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"607","DOI":"10.51519\/journalisi.v6i2.692","article-title":"Shielding Social Media: BERT and SVM Unite for Cyberbullying Detection and Classification","volume":"6","author":"Aggarwal","year":"2024","journal-title":"J. Inf. Syst. Inform."},{"key":"ref_41","doi-asserted-by":"crossref","unstructured":"Muneer, A., Alwadain, A., Ragab, M.G., and Alqushaibi, A. (2023). Cyberbullying detection on social media using stacking ensemble learning and enhanced BERT. Information, 14.","DOI":"10.3390\/info14080467"},{"key":"ref_42","doi-asserted-by":"crossref","unstructured":"Nurfiqri, M.R. (2024). The Performance Analysis of Graph Neural Network (GNN) and Convolutional Neural Network (CNN) Algorithms for Cyberbullying Detection in Twitter Comments. Indones. J. Comput. Sci., 13.","DOI":"10.33022\/ijcs.v13i3.3940"},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"125641","DOI":"10.1016\/j.eswa.2024.125641","article-title":"Automatic detection of cyberbullying behaviour on social media using Stacked Bi-Gru attention with BERT model","volume":"262","author":"Mali","year":"2025","journal-title":"Expert Syst. Appl."}],"container-title":["Information"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2078-2489\/17\/2\/205\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,25]],"date-time":"2026-02-25T05:18:08Z","timestamp":1771996688000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2078-2489\/17\/2\/205"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2,16]]},"references-count":43,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2026,2]]}},"alternative-id":["info17020205"],"URL":"https:\/\/doi.org\/10.3390\/info17020205","relation":{},"ISSN":["2078-2489"],"issn-type":[{"value":"2078-2489","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2,16]]}}}