Detection of Cyberbullying in Twitter Data Using Machine Learning Techniques
 |
International Journal of Computer Trends and Technology (IJCTT) |  |
| © 2019 by IJCTT Journal | ||
| Volume-67 Issue-10 |
||
| Year of Publication : 2019 | ||
| Authors : Shahina K M | ||
| DOI : 10.14445/22312803/IJCTT-V67I10P110 |
MLA Style:Shahina K M"Detection of Cyberbullying in Twitter Data Using Machine Learning Techniques," International Journal of Computer Trends and Technology 67.10 (2019):60-62.
APA Style Shahina K M. Detection of Cyberbullying in Twitter Data Using Machine Learning TechniquesInternational Journal of Computer Trends and Technology, 67(10),60-62.
Abstract
Analyzing comments in online interactions poses an important role in todays technological world. Although the social media plays a significant role in communication, it spreads cyberbullying among the young generation. Usage of aggressive and distorting words in social media is turn into a trend in nowadays. This will constitute a culture with dishonor and adverse communication in cyber world. so, intelligence systems based on different algorithms are emerged to classify this social media contents. This paper focused on analyzing and experimenting feature extraction and detection of cyber bullying in twitter messages with the help of Natural Language Processing tools and different Machine learning algorithms. Four feature extraction methods including Bag of words, TFIDF, doctovec and wordtovec are applied on the data set to create the feature set and then different classification methods are performed on these features. The classification methods include Logistic Regression, Support Vector Machine, Random Forest, and XGBoost. The result shows that XGBoost model on word2vec features has outperformed all the other methods. Machine learning algorithms for classification is implemented here using anaconda python distribution.
Reference
[1] Cynthia Van Hee, Els Lefever, Ben Verhoeveny, Automatic Detection and Prevention of Cyberbullying. HUSO 2015- The First International Conference on Human and Social Analytics.
[2] Despoina Chatzakouy, Nicolas Kourtellisz, Jeremy Blackburnz, Mean Birds: Detecting Aggression and Bullying on Twitter, arXiv:1702.06877 [cs.CY].
[3] Cynthia Van Hee1, Gilles Jacobs1, Chris Emmery2, Bart Desmet1, Els Lefever1, Ben Verhoeven2, Guy De Pauw2, Walter Daelemans2, and Veronique Host, Automatic Detection of Cyberbullying in Social Media Text.
[4] Ying Chen, Sencun Zhu, Yilu Zhou, Heng Xu, Detecting Offensive Language in Social Media to Protect Adolescent Online Safety, ACM, 2012
[5] K. Van Royen, K. Poels,W. Daelemans, and H. Vandebosch, Automatic monitoring of cyberbullying on social networking sites: From technological feasibility to desirability, Telematics and Informatics, vol. 32, 2015, pp. 8997, ISSN: 0736-5853
Keywords
Bag of words, TFIDF ,doctovec, wordtovec, Random Forest, Logistic Regression