Cyberbullying Detection with a Pronunciation Based Convolutional Neural Network
Abstract
Cyberbullying can have a deep and long lasting impact on its victims, who are often adolescents. Accurately detecting cyberbullying helps prevent it. However, the noise and errors in social media posts and messages make detecting cyberbullying very challenging. In this paper, we propose a novel pronunciation based convolutional neural network (PCNN) to address this challenge. Upon observing that the pronunciation of misspelled words in informal online conversations is often unchanged, we used the phoneme codes of the text as the features for a convolutional neural network. This procedure corrects spelling errors that did not alter the pronunciation, thereby alleviating the problem of noise and bullying data sparsity. To overcome class imbalance, a common problem in cyberbullying datasets, we implement three techniques that include threshold-moving, cost function adjusting, and a hybrid solution in our model. We evaluate the performance of our models using two cyberbullying datasets collected from Twitter and Formspring.me. The results of our experiment show that PCNN can achieve improved recall and precision compared to baseline convolutional neural networks.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
A few studies exploit RNN-based techniques (LSTM, BiLSTM, RNN) while some other studies use CNN-based techniques (CNN, PCNN, Char-CNNS) to detect cyberbullying from different sources.
“A few studies [21,134] exploit RNN-based techniques, i.e., LSTM, BiLSTM, RNN, etc., while some other studies [5,137] use CNN-based techniques (i.e., CNN, PCNN, Char-CNNS, etc.) to detect cyberbullying from different sources.”
From A Review on Deep-Learning-Based Cyberbullying Detection (2023) · cites this paper as [137]
Theano is heavily used in cyberbullying-related tasks.
“Theano is another heavily used framework in cyberbullying-related tasks [137,170,171] due to its quick processing speed.”
From A Review on Deep-Learning-Based Cyberbullying Detection (2023) · cites this paper as [137]
Cites
Gradient-based learning applied to document recognition
Lecun, Y., Bottou, L., Bengio, Y., & Haffner, P. (1998) · Proceedings of the IEEE · doi:10.1109/5.726791 · Cited by 58,805 · see citing works
Convolutional Neural Networks for Sentence Classification
Kim, Y. (2014) · Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.3115/v1/d14-1181 · Cited by 14,831 · see citing works
ADADELTA: An Adaptive Learning Rate Method
Zeiler, M. D. (2012) · arXiv · doi:10.48550/arxiv.1212.5701 · Cited by 5,322 · see citing works
Theano: A Python framework for fast computation of mathematical expressionsPreprint
Al-Rfou, R., Alain, G., Almahairi, A., Angermueller, C., Bahdanau, D., Ballas, N., Bastien, F., Bayer, J., Belikov, A., Belopolsky, A., et al. (2016) · arXiv.org · doi:10.48550/arxiv.1605.02688 · Cited by 2,438 · see citing works
Static Analysis of Shape in TensorFlow ProgramsPreprint
The Theano Development Team, Al‐Rfou, R., Alain, G., et al. (2016) · arXiv (Cornell University) · doi:10.4230/lipics.ecoop.2020.15 · Cited by 1,629 · see citing works
Research on School Bullying and Victimization: What Have We Learned and Where Do We Go From Here?
Espelage, D. L., & Swearer, S. M. (2003) · School Psychology Review · doi:10.1080/02796015.2003.12086206 · Cited by 1,250 · see citing works
Modeling the Detection of Textual Cyberbullying
Dinakar, K., Reichart, R., & Lieberman, H. A. (2021) · Proceedings of the International AAAI Conference on Web and Social Media · doi:10.1609/icwsm.v5i3.14209 · Cited by 517 · see citing works
Using Machine Learning to Detect Cyberbullying
Reynolds, K., Kontostathis, A., & Edwards, L. (2011) · doi:10.1109/icmla.2011.152 · Cited by 462 · see citing works
Semantic Parsing for Single-Relation Question Answering
Yih, W.-T., He, X., & Meek, C. (2014) · Annual Meeting of the Association for Computational Linguistics (ACL) · doi:10.3115/v1/p14-2105 · Cited by 426 · see citing works
Measuring cyberbullying: Implications for research
Patchin, J. W., & Hinduja, S. (2015) · Aggression and Violent Behavior · doi:10.1016/j.avb.2015.05.013 · Cited by 418 · see citing works
Improving Cyberbullying Detection with User Context
Dadvar, M., Trieschnigg, D., Ordelman, R., & de Jong, F. M. G. (2013) · Lecture notes in computer science · doi:10.1007/978-3-642-36973-5_62 · Cited by 384 · see citing works
Learning from Bullying Traces in Social Media
Xu, J., Jun, K.-S., Zhu, X., & Bellmore, A. D. (2012) · Cited by 336 · see citing works
Cyber Bullying Detection Using Social and Textual Analysis
Huang, Q., Singh, V. K., & Atrey, P. K. (2014) · doi:10.1145/2661126.2661133 · Cited by 212 · see citing works
The Impact of Imbalanced Training Data for Convolutional Neural Networks
Masko, D., & Hensman, P. (2015) · KTH Publication Database DiVA (KTH Royal Institute of Technology) · Cited by 198 · see citing works
Experts and Machines against Bullies: A Hybrid Approach to Detect Cyberbullies
Dadvar, M., Trieschnigg, D., & de Jong, F. M. G. (2014) · Lecture notes in computer science · doi:10.1007/978-3-319-06483-3_25 · Cited by 139 · see citing works
Kontostathis, A., Reynolds, K., Garron, A., & Edwards, L. (2013) · ACM Web Science Conference (WebSci) · doi:10.1145/2464464.2464499 · Cited by 119 · see citing works
Dadvar, M., & de Jong, F. M. G. (2012) · International World Wide Web Conference (WWW) · doi:10.1145/2187980.2187995 · Cited by 107 · see citing works
Identification and characterization of cyberbullying dynamics in an online social network
Squicciarini, A., Rajtmajer, S. M., Liu, Y., & Griffin, C. H. (2015) · IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM) · doi:10.1145/2808797.2809398 · Cited by 94 · see citing works
Collaborative detection of cyberbullying behavior in Twitter data
Mangaonkar, A., Hayrapetian, A., & Raje, R. R. (2015) · IEEE International Conference on Electro Information Technology · doi:10.1109/eit.2015.7293405 · Cited by 76 · see citing works
Expert knowledge for automatic detection of bullies in social networks
Dadvar, M., Trieschnigg, D., & Jong, D. F. (2013) · University of Twente Research Information · Cited by 29 · see citing works
Honjo, M., Hasegawa, T., Hasegawa, T., Mishima, K., Suda, T., & Yoshida, T. (2011) · International Conference on Social Computing · doi:10.1109/passat/socialcom.2011.221 · Cited by 14 · see citing works
A predictive model to detect online cyberbullying
Kasture, A. S. (2015) · Tuwhera (Auckland University of Technology) · Cited by 11 · see citing works
Improved Cyberbullying Detection Through Personal Profiles
Dadvar, M., & Jong, D. F. (2012) · University of Twente Research Information · Cited by 3 · see citing works
Flagged first, then by citations
4 of the 27 references couldn’t be matched to a known paper.
Cited by
Sorted by citations
Automatic cyberbullying detection: A systematic review
Rosa, H., Pereira, N., Ribeiro, R., Ferreira, P. C., Carvalho, J. P., Oliveira, S., Coheur, L., Paulino, P., Veiga Simão, A. M., & Trancoso, I. (2019) · Computers in Human Behavior · doi:10.1016/j.chb.2018.12.021 · Cited by 307 · see citing works
Social Media Cyberbullying Detection using Machine Learning
Hani, J., Nashaat, M., Ahmed, M., Emad, Z., Amer, E., & Mohammed, A. (2019) · International Journal of Advanced Computer Science and Applications · doi:10.14569/ijacsa.2019.0100587 · Cited by 160 · see citing works
“[11] in their paper uses novel pronunciation based convolution neural network (PCNN), thereby alleviating the problem of noise and bullying data sparsity to overcome class imbalance.”
Murshed, B. A. H., Abawajy, J., Mallappa, S., Saif, M. A. N., & Al-Ariki, H. D. E. (2022) · IEEE Access · doi:10.1109/access.2022.3153675 · Cited by 137 · see citing works
Cyberbullying detection: Utilizing social media features
Bozyiğit, A., Utku, S., & Nasibov, E. N. (2021) · Expert Systems with Applications · doi:10.1016/j.eswa.2021.115001 · Cited by 131 · see citing works
Raj, C., Agarwal, A., Bharathy, G., Narayan, B., & Prasad, M. (2021) · Electronics · doi:10.3390/electronics10222810 · Cited by 128 · see citing works
“Although they are primarily employed in visual tasks, CNNs have displayed tremendous performance in one-dimensional text classification [13,14].”
A Review on Deep-Learning-Based Cyberbullying Detection
Hasan, M. T., Hossain, M. A. E., Mukta, M. S. H., Akter, A., Ahmed, M., & Islam, S. (2023) · Future Internet · doi:10.3390/fi15050179 · Cited by 103 · see citing works
“Zhang et al. [137] proposed a new pronunciation-based convolutional neural network (PCNN) to handle the difficulty of noise and distortion in social media postings and messages in detecting cyberbullying.”
BackgroundMethodInfluentialA Human-Centered Systematic Literature Review of Cyberbullying Detection Algorithms
Kim, S.-H., Razi, A., Stringhini, G., Wiśniewski, P., & Choudhury, M. D. (2021) · Proceedings of the ACM on Human-Computer Interaction · doi:10.1145/3476066 · Cited by 86 · see citing works
“[5, 17, 24, 25, 27– 29, 38, 59, 89, 93, 106, 123, 152, 164–167], Logistic Regression (23.2”
BackgroundInfluentialCyberbullying Ends Here: Towards Robust Detection of Cyberbullying in Social Media
Yao, M., Chelmis, C., & Zois, D. (2019) · International World Wide Web Conference (WWW) · doi:10.1145/3308558.3313462 · Cited by 80 · see citing works
Teng, T. H., & Varathan, K. D. (2023) · IEEE Access · doi:10.1109/access.2023.3275130 · Cited by 77 · see citing works
Collaborative detection of cyberbullying behavior in Twitter data
Mangaonkar, A., Hayrapetian, A., & Raje, R. R. (2015) · IEEE International Conference on Electro Information Technology · doi:10.1109/eit.2015.7293405 · Cited by 76 · see citing works
When the Timeline Meets the Pipeline: A Survey on Automated Cyberbullying Detection
Elsafoury, F., Katsigiannis, S., Pervez, Z., & Ramzan, N. (2021) · IEEE Access · doi:10.1109/access.2021.3098979 · Cited by 80 · see citing works
Lu, N., Wu, G., Zhang, Z., Zheng, Y., Ren, Y., & Choo, K. R. (2020) · Concurrency and Computation: Practice and Experience · doi:10.1002/cpe.5627 · Cited by 76 · see citing works
“24 Previous psychological and sociological studies suggested that emotional information can be used to better understand bullying behaviors, and thon emoticons in social text messages conveyed the emotions of users.”
BackgroundCyberbullying detection on social multimedia using soft computing techniques: a meta-analysis
Kumar, A., & Sachdeva, N. (2019) · Multimedia Tools and Applications · doi:10.1007/s11042-019-7234-z · Cited by 73 · see citing works
“NET 1 [6] LibSVM 1 [32] ESpeakTheano 1 [55] IGraph 1 [36] SKLearn 1 [36] Java 1 [46] Séance 1 [50] Scipy.”
BackgroundInfluentialCyberbullying Detection in Social Networks Using Deep Learning Based Models
Dadvar, M., & Eckert, K. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-59065-9_20 · Cited by 68 · see citing works
“es [6]–[9] have used conventional Machine Learning (ML) models to detect cyberbullying incidents. Recently Deep Neural Network Based (DNN) models have also been applied for detection of cyberbullying [10], [11]. In [11], authors have used DNN models for detection of cyberbullying and have expanded their models across…”
MethodA “Deeper” Look at Detecting Cyberbullying in Social Networks
Rosa, H., de Matos, D. M., Ribeiro, R., Coheur, L., & Carvalho, J. P. (2018) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn.2018.8489211 · Cited by 63 · see citing works
“Zhang et al. [26] proposed a novel pronunciation-based CNN (PCNN) that used phoneme codes of text as features to minimize the misspelling of words, thus alleviating the problem of bullying data sparsity.”
MethodCyberbullying detection from tweets using deep learning
Bharti, S., Yadav, A. K., Kumar, M., & Yadav, D. (2022) · Kybernetes · doi:10.1108/k-01-2021-0061 · Cited by 56 · see citing works
Kumar, A., & Sachdeva, N. (2020) · Multimedia Systems · doi:10.1007/s00530-020-00672-7 · Cited by 62 · see citing works
Emmery, C., Verhoeven, B., Pauw, G. D., Jacobs, G., Hee, C. V., Lefever, E., Desmet, B., Hoste, V., & Daelemans, W. M. P. (2020) · Language Resources and Evaluation · doi:10.1007/s10579-020-09509-1 · Cited by 66 · see citing works
Cyberbullying Identification System Based Deep Learning Algorithms
Aldhyani, T. H. H., Al-Adhaileh, M. H., & Alsubari, S. N. (2022) · Electronics · doi:10.3390/electronics11203273 · Cited by 55 · see citing works
Session-based cyberbullying detection in social media: A survey
Yi, P., & Zubiaga, A. (2023) · Online Social Networks and Media · doi:10.1016/j.osnem.2023.100250 · Cited by 55 · see citing works
The effect of rebalancing techniques on the classification performance in cyberbullying datasets
Khairy, M., Mahmoud, T. M., & El‐Hafeez, T. A. (2023) · Neural Computing and Applications · doi:10.1007/s00521-023-09084-w · Cited by 53 · see citing works
Identification of cyberbullying on multi‐modal social media posts using genetic algorithm
Kumari, K., & Singh, J. P. (2020) · Transactions on Emerging Telecommunications Technologies · doi:10.1002/ett.3907 · Cited by 52 · see citing works
Chen, J., Wu, Z., & Zhang, J. (2019) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2018.2886280 · Cited by 51 · see citing works
“include the Focal Loss [60], the conventional softmax classifier [52], [48], [50], and over-sampling+softmax [71].”
MethodUsing Fuzzy Fingerprints for Cyberbullying Detection in Social Networks
Rosa, H., Carvalho, J. P., Calado, P. P., Martins, B., Ribeiro, R., & Coheur, L. (2018) · IEEE International Conference on Fuzzy Systems (FUZZ-IEEE) · doi:10.1109/fuzz-ieee.2018.8491557 · Cited by 45 · see citing works
“[19] proposed a novel pronunciation based convolutional neural network (PCNN) using phonetic transcriptions as features to minimize the misspelling of words, thus alleviating the problem of bullying”
Detecting cyberbullying using deep learning techniques: a pre-trained glove and focal loss technique
Koshiry, A. M. E., Eliwa, E. H. I., El‐Hafeez, T. A., & Khairy, M. (2024) · PeerJ Computer Science · doi:10.7717/peerj-cs.1961 · Cited by 44 · see citing works
“Zhang et al. (2016) aimed to use deep learning techniques to create a robust, universal cyberbullying detection algorithm.”
MethodJacobs, G., Hee, C. V., & Hoste, V. (2020) · Natural Language Engineering · doi:10.1017/s135132492000056x · Cited by 44 · see citing works
“2016; Zhao and Mao 2017; Agrawal and Awekar 2018); in case of comparison with traditional machine learning methods in benchmarking tasks, they currently seem to slightly outperform or perform on par with classifiers like support vector machine (SVM) and even random forest and logistic regression (LR) (Zhang et al. 201…”
BackgroundMethodArif, M. (2021) · Journal of Information Security and Cybercrimes Research · doi:10.26735/gbtv9013 · Cited by 45 · see citing works
“Deep learning architectures like LSTM and its variants, CNN, and BERT (including its variants) are prevalent in recent years.”
InfluentialKumar, R., & Bhat, A. (2022) · International Journal of Information Security · doi:10.1007/s10207-022-00600-y · Cited by 45 · see citing works
“The Deep learning-based model is also an effective technique for detecting cyberbullying and has improved Recall and precision than the baseline ML algorithms [74].”
MethodA Deep Analysis of Textual Features Based Cyberbullying Detection Using Machine Learning
Mahmud, M. I., Mamun, M., & Abdelgawad, A. (2022) · IEEE Global Conference on Artificial Intelligence and Internet of Things (GCAIoT) · doi:10.1109/gcaiot57150.2022.10019058 · Cited by 41 · see citing works
“[22], 2016 23,243 Twitters dataset PCNN (Proposed), Random forests, SVM, CNN random PCNN: accuracy 98.”
BackgroundMethodTowards multidomain and multilingual abusive language detection: a survey
Pamungkas, E. W., Basile, V., & Patti, V. (2021) · Personal and Ubiquitous Computing · doi:10.1007/s00779-021-01609-1 · Cited by 41 · see citing works
Arabic Toxic Tweet Classification: Leveraging the AraBERT Model
Koshiry, A. M. E., Eliwa, E. H. I., El‐Hafeez, T. A., & Omar, A. (2023) · Big Data and Cognitive Computing · doi:10.3390/bdcc7040170 · Cited by 39 · see citing works
FAEO-ECNN: cyberbullying detection in social media platforms using topic modelling and deep learning
Murshed, B. A. H., Suresha, Abawajy, J., Saif, M. A. N., Abdulwahab, H. M., & Ghanem, F. A. (2023) · Multimedia Tools and Applications · doi:10.1007/s11042-023-15372-3 · Cited by 39 · see citing works
“Other researchers, such as [12, 6, 62, 32], and [75], used CNNs to improve CB detection.”
MethodRetracted: A Study of Cyberbullying Detection Using Machine Learning Techniques
Kargutkar, S. M., & Chitre, V. (2020) · International Conference on Computing Methodologies and Communication (ICCMC) · doi:10.1109/iccmc48092.2020.iccmc-000137 · Cited by 38 · see citing works
RetractedDetecting Cyberbullying using Machine Learning Approaches
Haider, A., Siddique, A. B., Ali, R. H., Imad, M., Ijaz, A. Z., Arshad, U., Ali, N., Saleem, M., & Shahzadi, N. (2023) · International Conference on IT and Industrial Technologies (ICIT) · doi:10.1109/icit59216.2023.10335773 · Cited by 35 · see citing works
“To address unsupervised cyber-bullying, Zhang et al. [23] applied SVM on the Form Spring dataset, GHOSM on the YouTube comment section, and Na¨ıve Bayes on the Twitter comment section.”
MethodZiems, C., Vigfússon, Ý., & Morstatter, F. (2020) · Proceedings of the International AAAI Conference on Web and Social Media · doi:10.1609/icwsm.v14i1.7345 · Cited by 37 · see citing works
“Work Model Precision Recall F1 Class Zhang et al. (2016) CNN 99.”
BackgroundMethodInfluentialDetection of Hate Tweets using Machine Learning and Deep Learning
Ketsbaia, L., Issac, B., & Chen, X. (2020) · IEEE International Conference on Trust, Security and Privacy in Computing and Communications (TrustCom) · doi:10.1109/trustcom50675.2020.00103 · Cited by 35 · see citing works
Samee, N. M. A., Khan, U., Khan, S., Jamjoom, M. M., Sharif, M. I., & Kim, D. H. (2023) · IEEE Access · doi:10.1109/access.2023.3329347 · Cited by 34 · see citing works
“Zhang et al. [39] introduced the pronunciation-based convolutional neural network (PCNN), designed to handle spelling errors while maintaining accurate pronunciation, resulting in improved performance compared to other neural network models.”
ResultBalayn, A., Yang, J., Szlávik, Z., & Bozzon, A. (2021) · ACM Transactions on Social Computing · doi:10.1145/3479158 · Cited by 33 · see citing works
“Most papers use non-linear kernels when dealing with complex tasks, possibly with costsensitive SVM to circumvent dataset imbalance [99, 160, 255, 273, 302].”
BackgroundMethodOptimal Online Cyberbullying Detection
Zois, D., Kapodistria, A., Yao, M., & Chelmis, C. (2018) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2018.8462092 · Cited by 33 · see citing works
“The seriousness of the problem has led to a number of approaches to detect abusive behavior in online social networks based on text features, such as N–grams [2, 3, 4, 5], part–of–speech tags [2, 5, 6], statistical text–based features [7, 3, 6] including density of profane words, and word embeddings [5, 8, 9].”
BackgroundEmpirical Analysis of Supervised Machine Learning Techniques for Cyberbullying Detection
Kumar, A., Nayak, S., & Chandra, N. (2018) · Lecture notes in networks and systems · doi:10.1007/978-981-13-2354-6_24 · Cited by 31 · see citing works
Text Mining Techniques for Cyberbullying Detection: State of the Art
Bayari, R., & Benséfia, A. (2021) · Advances in Science Technology and Engineering Systems Journal · doi:10.25046/aj060187 · Cited by 31 · see citing works
Cyberbullying Detection by Using Artificial Neural Network Models
Bozyiğit, A., Utku, S., & Nasibov, E. N. (2019) · International Conference on Computer Science and Engineering (UBMK) · doi:10.1109/ubmk.2019.8907118 · Cited by 30 · see citing works
“Sanal zorbalığın otomatik olarak tespiti için farklı yöntemler içeren; zaman serileri [15], yapay sinir ağları [16], derin öğrenme [17], bulanık kural tabanlı sistemler [18], görüntü analizi [19] çalışmaları literatürde yerini almaktadır.”
Deep Learning Cyberbullying Detection Using Stacked Embbedings Approach
Mahlangu, T., & Tu, C. (2019) · International Conference on Soft Computing & Machine Intelligence (ISCMI) · doi:10.1109/iscmi47871.2019.9004292 · Cited by 28 · see citing works
“[20] Presents operative mechanisms for classifying cyberbullying and cyber trolling as harmful behavior.”
BackgroundPaul, S., Saha, S., & Singh, J. P. (2022) · Multimedia Tools and Applications · doi:10.1007/s11042-021-11601-9 · Cited by 28 · see citing works
“[26] proposed a pronunciation based convolutional neural network (PCNN) to address this issue.”
BackgroundA comprehensive review of cyberbullying-related content classification in online social media
Teng, T. H., Varathan, K. D., & Crestani, F. (2023) · Expert Systems with Applications · doi:10.1016/j.eswa.2023.122644 · Cited by 28 · see citing works
Transformer network-based word embeddings approach for autonomous cyberbullying detection
Pericherla, S., & Ilavarasan, E. (2024) · International Journal of Intelligent Unmanned Systems · doi:10.1108/ijius-02-2021-0011 · Cited by 23 · see citing works
A survey of uncover misleading and cyberbullying on social media for public health
Darwish, O., Tashtoush, Y. M., Bashayreh, A., Alomar, A., Alkhaza’leh, S., & Darweesh, D. (2022) · Cluster Computing · doi:10.1007/s10586-022-03706-z · Cited by 25 · see citing works
“[164] CNN and PCNN TM (threshold moving), CFA (cost function adjusting), and a hybrid solution (TM CFA) Removing nonalphanumeric characters tokens Dataset1 Dataset 2 1313 13,000 Cyberbullying (Psychological Health)”
MethodCyberbullying detection and machine learning: a systematic literature review
Balakrisnan, V., & Kaity, M. (2023) · Artificial Intelligence Review · doi:10.1007/s10462-023-10553-w · Cited by 23 · see citing works
“…foul words (i.e., explicit content) (Reynolds et al. 2011; Haidar et al. 2017a; Hosseinmardi et al. 2015a; Soni and Singh 2018 ), spelling mistakes (Zhang et al., 2017), density of uppercase characters (Kumar et al. 2019; Soni and Singh 2018 ), semantic features (Di Capua et al., 2016; Haidar et…”
BackgroundResultInfluentialCyberbullying Detection on Instagram with Optimal Online Feature Selection
Yao, M., Chelmis, C., & Zois, D. (2018) · IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM) · doi:10.1109/asonam.2018.8508329 · Cited by 22 · see citing works
“State–of–the–art computational approaches for abusive behavior detection in online social media, mainly rely on text features, such as N–grams [12]–[15], part–of–speech tags [12], [15], [16], and statistical text–based features [13], [16], [17] including density of profane words, and word embeddings [15], [18], [19].”
BackgroundClassification of Cyberbullying Text in Arabic
Benaissa, A. R., Harbaoui, A., & Ghézala, H. B. (2020) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn48605.2020.9206643 · Cited by 18 · see citing works
“[16] made use of these words with incorrect spellings by mapping each word into a vector that represents its phonetic code.”
MethodSelf-Attention for Cyberbullying Detection
Pradhan, A., Madhav, Y. V., & Bera, P. (2020) · International Conference on Cyber Situational Awareness, Data Analytics and Assessment (CyberSA) · doi:10.1109/cybersa49311.2020.9139711 · Cited by 18 · see citing works
“Zhang et al. [19] use the phoneme text codes to minimize word mispelling through their Pronunciation-based CNN model.”
MethodFighting Cyberbullying: An Analysis of Algorithms Used to Detect Harassing Text Found on YouTube
Trana, R. E., Gomez, C. E., & Adler, R. F. (2020) · Advances in intelligent systems and computing · doi:10.1007/978-3-030-51328-3_2 · Cited by 18 · see citing works
Data expansion using back translation and paraphrasing for hate speech detection
Beddiar, D. R., Jahan, S., & Oussalah, M. (2021) · Online Social Networks and Media · doi:10.1016/j.osnem.2021.100153 · Cited by 25 · see citing works
“The comparison of these results clearly shows that both CNN model and PCNN model of [54] achieve a max of 96.”
MethodResultInfluentialDynamic, Incremental, and Continuous Detection of Cyberbullying in Online Social Media
Chelmis, C., & Zois, D. (2021) · ACM Transactions on the Web · doi:10.1145/3448014 · Cited by 15 · see citing works
Enhancing collaborative detection of cyberbullying behavior in Twitter data
Mangaonkar, A., Pawar, R., Chowdhury, N. S., & Raje, R. R. (2022) · Cluster Computing · doi:10.1007/s10586-021-03483-1 · Cited by 15 · see citing works
Cyberbullying detection on Tweets
Phanomtip, A., Sueb-in, T., & Vittayakorn, S. (2021) · International Conference on Electrical Engineering/Electronics, Computer, Telecommunications and Information Technology (ECTI-CON) · doi:10.1109/ecti-con51831.2021.9454848 · Cited by 14 · see citing works
“More recently, [18], [19] applied the deep learning approach to the task and achieved the better performance.”
BackgroundClassification of Virtual Harassment on Social Networks Using Ensemble Learning Techniques
Azeez, N. A., & Fadhal, E. (2023) · Applied Sciences · doi:10.3390/app13074570 · Cited by 13 · see citing works
Analysis of Tweets for Cyberbullying Detection
Mathur, S. A., Isarka, S., Dharmasivam, B., & C. D., J. (2023) · 2023 Third International Conference on Secure Cyber Computing and Communication (ICSCCC) · doi:10.1109/icsccc58608.2023.10176416 · Cited by 12 · see citing works
“[6] utilized a Pronunciation-based Convolution Neural Network (PCNN) to overcome the problem of noise and bullying data sparsity.”
MethodCyberbullying Detection and Prevention: Data Mining in Social Media
Sultan, D., Suliman, A., Toktarova, A., Omarov, B. S., Mamikov, S., & Beissenova, G. (2021) · International Conference on Cloud Computing, Data Science & Engineering (Confluence) · doi:10.1109/confluence51648.2021.9377077 · Cited by 12 · see citing works
“In any case, the contrasts among cyberbullying and conventional genuine harassing are because of the highlights of the Internet: secrecy, the presence of a wide crowd, the capacity to make assaults 24 hours per day, and the chance of adulteration [2].”
BackgroundVishwamitra, N., Zhang, X., Tong, J., Hu, H., Luo, F., Kowalski, R. M., & Mazer, J. P. (2017) · ACM International Workshop on Security and Privacy Analytics (IWSPA) · doi:10.1145/3041008.3041013 · Cited by 12 · see citing works
“We have used a Pronunciation based CNN (PCNN) technique to improve the precision of textual cyberbullying detection in noisy data [22].”
MethodSelf-citationDeep Learning-Based Cyberbullying Detection in Kurdish Language
Badawi, S. S. (2024) · The Computer Journal · doi:10.1093/comjnl/bxae024 · Cited by 11 · see citing works
Cyberbullying Detection Neural Networks using Sentiment Analysis
Atoum, J. O. (2021) · International Conference on Computational Science and Computational Intelligence (CSCI) · doi:10.1109/csci54926.2021.00098 · Cited by 14 · see citing works
“Zhang et al. in [21] had proposed an approach that involves pronunciation-based CNN (PCNN) and phoneme codes of text as features to minimize the misspelling of words to improve the bullying data sparsity.”
MethodSexual Harassment Detection using Machine Learning and Deep Learning Techniques for Bangla Text
Islam, M., Rahman, M., Ahmed, M. T., Islam, A. Z. M. T., Das, D., & Hoque, M. M. (2023) · International Conference on Electrical, Computer and Communication Engineering · doi:10.1109/ecce57851.2023.10101522 · Cited by 10 · see citing works
“[10] proposed a method which is based on the Deep Learning and Neural Networks approach.”
MethodHung, B. W. K., Muramudalige, S. R., Jayasumana, A. P., Klausen, J., Libretti, R., Moloney, E., & Renugopalakrishnan, P. (2019) · IEEE Conference on Technologies for Homeland Security (HST) · doi:10.1109/hst47167.2019.9032956 · Cited by 10 · see citing works
“Natural language processing and machine learning algorithms in information extraction tasks have been used successfully in other domains such as understanding patient medical profiles in free-text clinical notes [1], [13], [26] and detecting cyberbullying [40], [41].”
Gamal, D., Alfonse, M., Jiménez-Zafra, S. M., & Aref, M. (2023) · Big Data and Cognitive Computing · doi:10.3390/bdcc7020058 · Cited by 9 · see citing works
Giri, S., & Banerjee, S. (2023) · Social Network Analysis and Mining · doi:10.1007/s13278-022-01023-2 · Cited by 10 · see citing works
“Most of the researchers performed traditional text pre-processing (Zhang et al. 2016; Iwendi et al. 2020; Ghosh et al. 2021) for text classification.”
Shielding against online harm: A survey on text analysis to prevent cyberbullying
Mishra, A., Sinha, S., & George, C. P. (2024) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2024.108241 · Cited by 13 · see citing works
Cyberbullying detection on multi-modal data using pre-trained deep learning architectures
Pericherla, S., & Ilavarasan, E. (2021) · Ingenieria Solidaria · doi:10.16925/2357-6014.2021.03.09 · Cited by 10 · see citing works
“al [16] proposed novel convolutional neural network based on pronunciation (PCNN).”
BackgroundMaLang: A Decentralized Deep Learning Approach for Detecting Abusive Textual Content
Kompally, P., Sethuraman, S. C., Walczak, S. M., Johnson, S., & Cruz, M. V. (2021) · Applied Sciences · doi:10.3390/app11188701 · Cited by 9 · see citing works
“A pronunciation-based CNN is proposed to tackle the challenges of cyberbullying such as misspellings in the messages and posts in social media [37].”
AI Based Cyberbullying Detection and Prevention
Gupta, R., Singh, A. K., Utkarsh, Mittal, P., & Radhika (2024) · IEEE Delhi Section Conference (DELCON) · doi:10.1109/delcon64804.2024.10866680 · Cited by 8 · see citing works
Shakeel, N., & Dwivedi, R. K. (2022) · Lecture notes in networks and systems · doi:10.1007/978-981-19-2894-9_29 · Cited by 8 · see citing works
Ensemble Deep Learning (EDL) for Cyber-bullying on Social Media
Bai, Z. S., & Malempati, S. (2023) · International Journal of Advanced Computer Science and Applications · doi:10.14569/ijacsa.2023.0140761 · Cited by 8 · see citing works
Sangwan, S. R., & Bhatia, M. P. S. (2021) · Expert Systems · doi:10.1111/exsy.12766 · Cited by 8 · see citing works
Abusive Comments Classification in Social Media Using Neural Networks
Janardhana, D. R., Shetty, A. B., Hegde, M. N., Kanchan, J., & Hegde, A. (2020) · Advances in intelligent systems and computing · doi:10.1007/978-981-15-5113-0_33 · Cited by 7 · see citing works
Amer, A. Y. A., Siddiqui, T., & Athamena, B. (2022) · Research Square · doi:10.21203/rs.3.rs-2184218/v1 · Cited by 7 · see citing works
A Novel Hybrid Attention-Based RoBERTa-BiLSTM Model for Cyberbullying Detection
Mahdi, M. A., Fati, S. M., Ragab, M. G., Hazber, M. A. G., Ahamad, S., Saad, S. A., & Al-Shalabi, M. (2025) · Mathematical and Computational Applications · doi:10.3390/mca30040091 · Cited by 7 · see citing works
“Zhang et al. [32] introduced a pronunciation-based CNN to detect cyberbullying, drawing on datasets from Twitter and Formspring.”
A Detailed Survey On Cyberbullying in Social Networks
Krithika, V., & Priya, V. (2020) · International Conference on Emerging Trends in Information Technology and Engineering (ICETITE) · doi:10.1109/ic-etite47903.2020.031 · Cited by 6 · see citing works
“The proportion of the corpus was of 34% female and 66 %male and the accuracy was performed using 10-fold cross validation [34].”
MethodA Survey on Detection of Cyberbullying in Social Media Using Machine Learning Techniques
Shakeel, N., & Dwivedi, R. K. (2022) · Lecture notes on data engineering and communications technologies · doi:10.1007/978-981-19-1844-5_25 · Cited by 6 · see citing works
Ahmed, M. T., Antar, A. H., Rahman, M., Islam, A. Z. M. T., Das, D., & Rashed, M. G. (2023) · Journal of Intelligent Learning Systems and Applications · doi:10.4236/jilsa.2023.154008 · Cited by 6 · see citing works
ChildProtect: A parental control application for tracking hostile surfing content
Ameur, H., Rekik, A., Jamoussi, S., & Hamadou, A. B. (2022) · Entertainment Computing · doi:10.1016/j.entcom.2022.100517 · Cited by 6 · see citing works
Sahana, E. A. (2023) · International Journal on Recent and Innovation Trends in Computing and Communication · doi:10.17762/ijritcc.v11i10.8505 · Cited by 8 · see citing works
Explainable AI for Reliable Detection of Cyberbullying
Gongane, V. U., Munot, M. V., & Anuse, A. D. (2023) · IEEE Pune Section International Conference (PuneCon) · doi:10.1109/punecon58714.2023.10450132 · Cited by 5 · see citing works
“Zhang et al. [12] reported pronunciation of words from the bullying content as features that are applied to a CNN model.”
MethodAn in-depth examination of cyberbullying detection utilizing machine learning techniques
Gadicha, A. B., Gadicha, V. B., Obaid, A. J., & Abbood, Z. A. (2024) · AIP conference proceedings · doi:10.1063/5.0234200 · Cited by 5 · see citing works
A Hierarchical Approach for Timely Cyberbullying Detection
Nazar, I. M., Zois, D., & Yao, M. (2019) · IEEE Data Science Workshop (DSW) · doi:10.1109/dsw.2019.8755598 · Cited by 5 · see citing works
“, N–grams, part–of–speech tags, word embeddings) [6–10].”
Unraveling Cyberbullying Dynamis: A Computational Framework Empowered by Artificial Intelligence
Barbosa-Santillán, L. I., Guzman-Velázquez, B. P., Orozco-Aguilera, M. T., & Flores-Pulido, L. (2025) · Information · doi:10.3390/info16020080 · Cited by 6 · see citing works
Detecting context abusiveness using hierarchical deep learning
Lee, J.-H., Park, J.-U., Cha, J.-W., & Han, Y.-S. (2019) · Workshop on Natural Language Processing for Internet Freedom: Censorship, Disinformation, and Propaganda (NLP4IF) · doi:10.18653/v1/d19-5002 · Cited by 4 · see citing works
“Zhang et al. (2016) noticed that lots of noise and errors in social media data made the abusive detection challenging.”
BackgroundAli, W. N. H. W., Mohd, M., Fauzi, F., Shirai, K., & Noor, M. J. M. (2021) · Malaysian Journal of Computer Science · doi:10.22452/mjcs.sp2021no2.6 · Cited by 4 · see citing works
An Improved Detection of Cyberbullying on Social Media Using Randomized Sampling
Dhingra, N., Chawla, S., Saini, O., & Kaushal, R. (2023) · International Journal of Bullying Prevention · doi:10.1007/s42380-023-00188-4 · Cited by 4 · see citing works
“…Hee et al. (2018), Hosseinmardi et al. (2015), Xu et al. (2012), word embeddings Zhao et al. (2016) or messages are represented in phonetic forms Zhang et al. (2016), along with frequency counts of curse words, hostile or insulting terms, pronouns, emojis, and punctuation using a dictionary…”
KNCD: Knowledge-Enhanced Network for Cyberbullying Detection
Yan, Y., Du, W., Sun, Y., & Yin, D. (2023) · International Conference on Intelligent Computing and Human-Computer Interaction (ICHCI) · doi:10.1109/ichci58871.2023.10277885 · Cited by 4 · see citing works
“X. Zhang et al. [5] were among the pioneers in applying CNN models for cyberbullying detection, demonstrating promising results.”
BackgroundCost-sensitive PLM-based Approach for Arabic and English Cyberbullying Classification
Harbaoui, A., Benaissa, A. R., & ghezala, H. B. (2023) · doi:10.21203/rs.3.rs-2524732/v1 · Cited by 3 · see citing works
Machine Learning Approaches for Detecting Hate-Driven Violence on Social Media
Abuhamda, Y., & García‐Teodoro, P. (2025) · Applied Sciences · doi:10.3390/app152111323 · Cited by 3 · see citing works
Khan, U., Khan, S., Mussiraliyeva, S., Samee, N. M. A., Alabdulhafith, M. I., & Shah, K. (2024) · Neural Computing and Applications · doi:10.1007/s00521-024-10148-8 · Cited by 3 · see citing works
From Tweets to Tolerance: Empowering Cyberbullying Detection with Deep Learning Models
Asfand-e-yar, M., Aftab, S., Hashir, Q., & Talha, T. (2023) · International Conference on Frontiers of Information Technology (FIT) · doi:10.1109/fit60620.2023.00050 · Cited by 3 · see citing works
“RNNs are used for image 232 recognition, machine translation, natural language processing, handwriting recognition, etc. [3].”
MethodBenaissa, A. R., Harbaoui, A., & Ghezala, H. H. B. (2024) · Behaviour and Information Technology · doi:10.1080/0144929x.2024.2313142 · Cited by 3 · see citing works
Analysing Machine Learning Techniques for Cyberbullying Detection: A Review Study
Aziz, S., Usman, M., Azam, A., Ahmad, F., Bilal, M., & Cheema, A. A. (2022) · International Conference on Emerging Technologies · doi:10.1109/icet56601.2022.10004667 · Cited by 3 · see citing works
“[8] aimed to propose a highprecision generalized cyberbullying detection classifier that uses the pronunciation of text words as a feature of the convolutional neural network (CNN).”
BackgroundInfluentialDetection of Cyberbullying on Social Media
Hudda, N., Mishra, A., & Kumar, S. (2023) · International Journal of Computer Applications · doi:10.5120/ijca2023922702 · Cited by 2 · see citing works
Detection Of Cyberbullying based On Online Social Networks
Rajeevan, A., & Krishnaraj, N. (2023) · International Conference on Computer Communication and Informatics (ICCCI) · doi:10.1109/iccci56745.2023.10128506 · Cited by 2 · see citing works
“We incorporate three strategies, including threshold-moving, cost function adjusting, and a hybrid solution, to address class imbalance, a typical issue in cyber bullying datasets[4].”
MethodKaarthika, R., Hemamalini, R., & Kanmani, R. S. (2024) · International Conference on Signal Processing, Computation, Electronics, Power and Telecommunication (IConSCEPT) · doi:10.1109/iconscept61884.2024.10627823 · Cited by 2 · see citing works
“The research paper [2] proposes a unique Pronunciation-based Convolutional Neural Network (PCNN) to resolve the noise and errors in social media messages.”
BackgroundSecuring Social Spaces: Harnessing Deep Learning to Eradicate Cyberbullying
Biswas, R., Ganguly, K., Das, A., & Saha, D. (2025) · Communications in computer and information science · doi:10.1007/978-3-031-81935-3_19 · Cited by 2 · see citing works
Extracting User Behavioural Control Styles based on Process Mining
Kumar, M. V., Sai, P. S., Selvi, A., & Amarnadh, D. V. S. (2021) · doi:10.1109/icspc51351.2021.9451795 · Cited by 2 · see citing works
- Authors
- Zhang, X., Tong, J., Vishwamitra, N., Whittaker, E., Mazer, J. P., Kowalski, R., Hu, H., Luo, F., Macbeth, J., & Dillon, E.
- Affiliations
- Clemson University (US)
- Fairfield University (US)
- ORCID
- Venue
- 2016 15th IEEE International Conference on Machine Learning and Applications (ICMLA)
- Publisher
- IEEE
- Published
- 2016-12
- Pages
- 740-745
- OpenAlex
- W2583149885
- Cited by
- 118
- References
- 27
- Citations by year
- 2026: 1 · 2025: 5 · 2024: 9 · 2023: 29 · 2022: 17 · 2021: 24 · 2020: 15 · 2019: 9 · 2018: 7 · 2017: 1 · 2015: 1
- FWCI
- 3.00
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- International Conference on Machine Learning and Applications (publishedVersion)
- Funders
- National Science Foundation
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Hate Speech and Cyberbullying Detection
- Physical Sciences › Computer Science › Information Systems › Spam and Phishing Detection
- Physical Sciences › Computer Science › Artificial Intelligence › Sentiment Analysis and Opinion Mining
- Keywords
- cyberbullying detection, phoneme features, spelling errors, spelling correction, class imbalance, social media text, Twitter
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
