Detecting Cyber Bullying on Twitter using Support Vector Machine
Abstract
On the platform provided by social media, a significant number of young people are subjected to bullying. Cyberbullying is becoming a more widespread problem with the proliferation of social networking platforms. To discover word similarities in the tweets that were written by bullies, utilize Machine Learning, and develop a ML model that can do automatic identification of the bullying acts on different social media websites or platforms. Yet, many other methods for detecting bullying on social media have been deployed, however, the majority of these methods are text-based. The goal of this work is to show how software may be developed that can detect bullying in tweets, postings, and other online communications. It has been suggested to use a model that uses machine learning to identify bullying on Twitter. SVM is used in the classification process, whereas NLP is utilized for the processing of the data. Additionally, in order to decide whether or not a tweet constitutes bullying, the Twitter API is used to gather the tweets, which are then loaded into a model.
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?
Collection and labeling of data is cost and time consuming due to restrictions of data source platforms such as Twitter, Facebook, YouTube, and Instagram.
“(3) Collection and labeling of data is cost and time consuming due to restrictions of data sources platforms which are social media platforms such as twitter, Facebook, YouTube, and Instagram.”
From Cyberbullying detection: Exploring datasets, technologies, and approaches on social media platforms (2026) · cites this paper as [8]
High quality training and testing data are required to train and test cyberbullying detection models to get effective algorithms.
“High quality training and testing data are required to train and test cyberbullying detection models to get effective algorithms in detecting and identifying cyberbullying instances on social media platforms [8].”
From Cyberbullying detection: Exploring datasets, technologies, and approaches on social media platforms (2026) · cites this paper as [8]
Cites
1 retracted
Praveen, S. P., Krishna, T. B. M., Anuradha, C., Mandalapu, S. R., Sarala, P., & Sindhura, S. (2022) · International Journal of Healthcare Management · doi:10.1080/20479700.2022.2157071 · Cited by 45 · see citing works
Self-citationRetractedThe need to belong: Desire for interpersonal attachments as a fundamental human motivation.
Baumeister, R. F., & Leary, M. R. (1995) · Psychological Bulletin · doi:10.1037//0033-2909.117.3.497 · Cited by 23,245 · see citing works
Cyberbullying Definition and Measurement
Menesini, E., & Nocentini, A. (2009) · Zeitschrift für Psychologie · doi:10.1027/0044-3409.217.4.230 · Cited by 247 · see citing works
Cyberbullying in social networking sites: An adolescent victim’s perspective
Dredge, R., Gleeson, J., & de la Piedad Garcia, X. (2014) · Computers in Human Behavior · doi:10.1016/j.chb.2014.03.026 · Cited by 133 · cited 1× · see citing works
“For example, a financial analyst may be required to make an estimate of the value of a company based on a variety of factors, such as its value, the performance of similar stocks in the past, and an index of macroeconomic factors [6].”
BackgroundCyberbullying and self-esteem in Australian adults
Brack, K., & Caltabiano, N. (2014) · Cyberpsychology: Journal of Psychosocial Research on Cyberspace · doi:10.5817/cp2014-2-7 · Cited by 93 · see citing works
Social media bullying detection using machine learning on Bangla text
Abdhullah-Al-Mamun, & Akhter, S. (2018) · International Conference on Electrical and Computer Engineering (ICECE) · doi:10.1109/icece.2018.8636797 · Cited by 78 · see citing works
Sentiment Analysis for Product Reviews Based on Weakly-Supervised Deep Embedding
Sindhura, S., Praveen, S. P., Safali, M. A., et al. (2021) · International Conference on Inventive Research in Computing Applications (ICIRCA) · doi:10.1109/icirca51532.2021.9544985 · Cited by 29 · see citing works
Self-citationArava, K., Chaitanya, R. S. K., Sikindar, S., et al. (2022) · International Conference on Electronics and Sustainable Communication Systems (ICESC) · doi:10.1109/icesc54411.2022.9885648 · Cited by 22 · see citing works
Flagged first, then by citations
Cited by
Sorted by citations
Cyberbullying detection: Exploring datasets, technologies, and approaches on social media platforms
Philipo, A. G., Sarwatt, D. S., Ding, J., Daneshmand, M., & Ning, H. (2026) · ACM Computing Surveys · doi:10.1145/3785654 · Cited by 14 · see citing works
- Authors
- Dedeepya, P., Sowmya, P., Saketh, T. D., Sruthi, P., Abhijit, P., & Praveen, S. P.
- Affiliations
- Prasad V. Potluri Siddhartha Institute of Technology (IN)
- Venue
- 2023 Third International Conference on Artificial Intelligence and Smart Energy (ICAIS)
- Publisher
- IEEE
- Published
- 2023-02-02
- Pages
- 817-822
- OpenAlex
- W4360994597
- Cited by
- 14
- References
- 8
- Citations by year
- 2026: 1 · 2025: 4 · 2024: 2 · 2023: 7
- FWCI
- 2.49
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- International Conference on Artificial Intelligence and Smart Energy (ICAIS) (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Hate Speech and Cyberbullying Detection
- Physical Sciences › Computer Science › Information Systems › Spam and Phishing Detection
- Social Sciences › Psychology › Social Psychology › Bullying, Victimization, and Aggression
- Keywords
- cyberbullying detection, Twitter, support vector machine, social media, text classification, word similarity, Twitter API
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
