Cyberbullying on social media has become a pervasive and deeply concerning issue in today's digital age. With the ease of anonymity and the widespread accessibility of online platforms, individuals of all ages are increasingly vulnerable to harassment, intimidation, and cruelty. The impact on victims can be devastating, leading to profound psychological distress, anxiety, depression, and even thoughts of self-harm or suicide.
This paper proposes an automatic cyberbullying detection system for online comments. To achieve this objective, we followed four main steps: data collection and preprocessing, semantic processing, classification, and evaluation. We combined WordNet with GloVe word embeddings to cover lexico-semantic categories in comments and capture the semantic relationships between synonyms. In addition, we tested three synonym replacement strategies during semantic processing: (1) replacing a word with its closest synonym, (2) Type-1 fuzzy synonym replacement, and (3) Type-2 fuzzy synonym replacement. For the classification, we used Logistic Regression, Random Forest, Decision Tree, Extremely Randomized Trees, XGBoost, AdaBoost, LSTM and RNN in order to build robust models capable of accurately detecting cyberbullying behaviors, thereby offering an effective solution to promote a safer and more benevolent online environment.
Experimental results show that our proposed system was able to detect cyberbullying with an Accuracy of 94.36%.
AkankshaM.SharadS.Clint PazhayidamG. (2024). Shielding against online harm: A survey on text analysis to prevent cyberbullying. Engineering Applications of Artificial Intelligence, 133(D), 108241. https://doi.org/10.1016/j.engappai.2024.108241
2.
AlotaibiM.AlotaibiB.RazaqueA. (2021). A multichannel deep learning framework for cyberbullying detection on social media. Electronics, 10(21), 2664. https://doi.org/10.3390/electronics10212664
3.
AlzaqebahM.JaradatG. M.NassanD.AlnasserR.AlsmadiM. K.AlmarashdehI.JawarnehS.AlwohaibiM.Al-MullaN. A.AlshehabN.AlkhushayniS. (2023). Cyberbullying detection framework for short and imbalanced arabic datasets. Journal of King Saud University–Computer and Information Sciences, 35(8), 101652. https://doi.org/10.1016/j.jksuci.2023.101652
4.
AmbareenK.Meenakshi SundaramS. (2023). A survey of cyberbullying detection and performance: Its impact in social Media using artificial intelligence. SN Computer Science, 4(859), 1–8. https://doi.org/10.1007/s42979-023-02301-2
5.
BenarafaH.BenkhalifaM.AkhloufiM.Wordnet semantic relations based enhancement of KNN model for implicit aspect identification in sentiment analysis. International Journal of Computational Intelligence Systems, 16(3), 1–14.
6.
DessD.DiegoR. R. (2022). Lextex: A framework to generate lexicons using WordNet word senses in domain specific categories. Journal of Intelligent Information Systems, 59(1), 21–44. https://doi.org/10.1007/s10844-021-00679-0
7.
EjazN.RaziF.ChoudhuryS. (2024). Towards comprehensive cyberbullying detection: A dataset incorporating aggressive texts, repetition, peerness, and intent to harm. Computers in Human Behavior, 153(1), 108123. https://doi.org/10.1016/j.chb.2023.108123
8.
ElsafouryF.KatsigiannisS.PervezZ.RamzanN. (2021). When the timeline meets the pipeline: A survey on automated cyberbullying detection. IEEE Access, 9(1), 103541–103563. https://doi.org/10.1109/ACCESS.2021.3098979
9.
EronenJ.PtaszynskiM.MasuiF.ArataM.LeliwaG.WroczynskiM. (2022). Transfer language selection for zero-shot cross-lingual abusive language detection. Information Processing & Management, 59(4), 102981. https://doi.org/10.1016/j.ipm.2022.102981
10.
GalalM. A.YousefA. H.ZayedH. H.MedhatW. (2024). Arabic sarcasm detection: An enhanced fine-tuned language model approach. Ain Shams Engineering Journal, 15(6), 1–14. https://doi.org/10.1016/j.asej.2024.102736
11.
HasanM. T.HossainM. A. E.MuktaM. S. H.AkterA.AhmedM.IslamS. (2023). A review on deep-learning-based cyberbullying detection. Future Internet, 15(5), 179. https://doi.org/10.3390/fi15050179
12.
HiteshiS.HimashriM.RituR.GarimaJ.ArunS.AmitaD. (2024). Enhancing cyberbullying detection: A comparative study of ensemble CNN–SVM and BERT models. Social Network Analysis and Mining, 14(1), 1–18. https://doi.org/10.1007/s13278-023-01158-w
13.
HuangG.ZhuX.WastiS. H.JiangY. (2023). Multi-knowledge resources-based semantic similarity models with application for movie recommender system. Artificial Intelligence Review, 56(2), 2151–2182. https://doi.org/10.1007/s10462-023-10573-6
14.
JamjoomA. A.KaramtiH.UmerM.AlsubaiS.KimT.AshrafI. (2024). RoBERTaNET: Enhanced RoBERTa transformer based model for cyberbullying detection with GloVe features. IEEE Access, 12(1), 58950–58959. https://doi.org/10.1109/ACCESS.2024.3386637
15.
KalraV.KashyapI.KaurH. (2022). Improving document classification using domain-specific vocabulary: Hybridization of deep learning approach with TFIDF. International Journal of Information Technology, 14(5), 2451–2457. https://doi.org/10.1007/s41870-022-00889-x
16.
KhairyM.MahmoudT. M.OmarA.Abd El–HafeezT. (2024). Comparative performance of ensemble machine learning for arabic cyberbullying and offensive language detection. Language Resources and Evaluation, 58(2), 695–712. https://doi.org/10.1007/s10579-023-09683-y
17.
Kumar RoyP.Umeshbhai MaliF. (2022). Cyberbullying detection using deep transfer learning. Complex & Intelligent Systems, 8(3), 5449–5467. https://doi.org/10.1007/s40747-022-00772-z
MahmudT.PtaszynskiM.EronenJ.MasuiF. (2023). Cyberbullying detection for low-resource languages and dialects: Review of the state of the art. Information Processing and Management, 60(5), 103454. https://doi.org/10.1016/j.ipm.2023.103454
20.
MousaA.ShahinI.Bou NassifA.ElnagarA. (2024). Detection of arabic offensive language in social media using machine learning models. Intelligent Systems with Applications, 22(1), 200376. https://doi.org/10.1016/j.iswa.2024.200376
21.
MurshedB. A. H.Suresha, AbawajyJ.Naji SaifM. A.AbdulwahabH. M.GhanemF. A. (2023). FAEO–ECNN: Cyberbullying detection in social media platforms using topic modelling and deep learning. Multimedia Tools and Applications, 82(30), 46611–46650. https://doi.org/10.1007/s11042-023-15372-3
22.
NagyK. S.KapustaJ.MunkM. (2023). Feature extraction from unstructured texts as a combination of the morphological and the syntactic analysis and its usage in fake news classification tasks. Neural Computing and Applications, 35(29), 22055–22067. https://doi.org/10.1007/s00521-023-08967-2
23.
ParuchuriV. L.RajeshP. (2023). Cybernet: A hybrid deep CNN with N–gram feature selection for cyberbullying detection in online social networks. Evolutionary Intelligence, 16(6), 1935–1949. https://doi.org/10.1007/s12065-022-00774-3
24.
PokhunL.ChutturY. M. (2023). Can Machine Learning Really Detect Cyberbullying?. International Journal of Bullying Prevention, (in press). https://doi.org/10.1007/s42380-023-00191-9
25.
SmithP. K.MahdaviJ.CarvalhoM.FisherS.RussellS.TippettN. (2008). Cyberbullying: Its nature and impact in secondary school pupils. The Journal of Child Psychology and Psychiatry, 49(4), 376–385. https://doi.org/10.1111/j.1469-7610.2007.01846.x
26.
Van RoyenK.PoelsK.VandeboschH.AdamP. (2017). ‘‘Thinking before posting?’’ reducing cyber harassment on social networking sites through a reflective message. Computers in Human Behavior, 66(1), 345–352. https://doi.org/10.1016/j.chb.2016.09.040
27.
Vimala BalakrisnanV.KaityM. (2023). Cyberbullying detection and machine learning: A systematic literature review. Artificial Intelligence Review, 56(1), 1375–S1416. https://doi.org/10.1007/s10462-023-10553-w
28.
WangJ.FuK.LuC. T. (2020). SOSNet: A Graph Convolutional Network Approach to Fine-Grained Cyberbullying Detection. the proceedings of the 2020 IEEE International Conference on Big Data (IEEE BigData 2020).
29.
YiP.ZubiagaA. (2024). Session-based cyberbullying detection in social media: A survey. Online Social Networks and Media, 36(1), 100250. https://doi.org/10.1016/j.osnem.2023.100250
30.
YinW.ZubiagaA. (2021). Towards generalisable hate speech detection: a review on obstacles and solutions. Computer Science, 7(1). https://arxiv.org/abs/2102.08886
31.
ZamanW.AbdullahA.I. (2023). Multi-feature transformer for multiclass cyberbullying detection in bangla. In the proceeding of 19th Artificial Intelligence Applications and Innovations Conference, León, Spain, pp. 439–451.
