|
COMPARATIVE STUDY OF CLASSIFICATION TECHNIQUES USED FOR CYBERBULLYING
2
Author(s):
LAKHDEEP KAUR,DR. SONIA VATTA
Vol - 9, Issue- 1 ,
Page(s) : 23 - 29
(2019 )
DOI : https://doi.org/10.32804/RJSET
Abstract
With the advancement of technology, social media is a basic need of the modern world. Due to increasing the popularity of social media, cyberbullying is also becoming a big concern. Cyberbullying is different from traditional bullying due to the anonymity that the Internet can provide. Traditional bullying usually stops when a victim returns to the safety of his home, but cyberbullying is a continuous process maintained through email, texting, forum/blog posts and other communication vehicles. Even if cyberbullying victims change profile settings and avoid certain websites, cyberbullies may easily continue public bullying activities. It refers to causing bullying behavior towards other using digital appliances like mobile phones, internet or emails and is known as cyberbullying. Hazards of cyberbullying with sovereign consequences such as suicide, depression are daily reported in the press, newspaper. Children are more affected with the depression, stress, anger, anxiety & so on. In the recent survey of cyberbullying, 59% of U.S teens are suffering from bullying and online harassment[1]. In recent times, it has been recorded in surveys that cyberbullying has had a high percentage of victims in India to be 32% in 2012 and has remained the same since 2016. At present, cyberbullying in 2018 has seen an increase of 37% (as per the report). It is very shocking and alarming to note that the majority of the cyberbullying crimes are committed in India. Cyberbullying is quite dangerous and all the content posted online is easily visible to everyone which will harm the dignity of victim. Cyberbullying includes sending, posting, or sharing negative, harmful, false, or mean content about someone else. It can include sharing personal or private information about someone else causing embarrassment or humiliation. Cyberbullying occurs frequently towards a person, repeatedly causing abuse and hostility. Cyberbullying means to harass someone and bully to the person or victim on digital communication media. Different types of data mining techniques are employed for the prediction of cyberbullying like Naïve Bayes, KNN algorithm, Logistic Regression, SVM. The main purpose of this review paper is to explain various classification techniques of cyberbullying.
[1] http://www.pewinternet.org/2018/09/27/a-majority-of-teens-have-experienced-some-form-of-cyberbullying/
[2] Homa Hosseinmardi, Sabrina Arredondo Mattson, Rahat Ibn Rafiq, Richard Han, Qin Lv, Shivakant Mishra, “Predictions of Cyberbullying Incidents on the Instagram Social Network
[3] S.C. M. De Chaudhary, M. Gamon and E. Hortviz, “Predicting depression via social media. In International AAAI Conference on Weblogs and social media, Boston, MA, 2013.
[4] A Strickland. Bullying by peers has effect later in life. http://www.cnn.com/2015/05/08/health/bullying-mental-health-effects/index.html 2015.
[5] R. Broderick. 9 teenage suicides in the last year were linked to cyber-bullying on social network ask.fm. http://www.buzzfeed.com/ryanhatesthis/a-ninth-teenage-since-last-september-has-committed-suicide, 2013.
[6] Qianjia Huang, Vivek K. singh, Pradeep K. Atrey, “Cyberbullying detection using social and textual Analysis”.
[7] http://en.wikipedia.org/wiki/Cyberbullying
[8] D. C. Campfield. Cyber bullying and victimization: psychosocial characteristics of bullies, victims, and bully/victims. ProQuest, 2008.
[9] Nektaria Potha, Manolis Maragoudakis, “Cyberbullying Detection using Time Series Modeling”.
[10] Hariani, Imam Riadi, “Detection of Cyberbullying on Social Media Using Data Mining Techniques”.
[11] Cynthia Van Hee, Gilles Jacobs, Chris Emmery, Bart Desmet, Els Lefever, Ben Verhoeven, Guy De Pauw, Walter Daelemans and Veronique Hoste, “Automatic Detection of Cyberbullying in Social Media Text”.
[12] Data mining classifications
https://www.tutorialspoint.com/data_mining/dm_classification_prediction.htm
[13] https://qz.com/india/1435072/37-of-indian-kids-are-bullied-online-new-study-says/
[14] Child Grooming and sexually harassement https://en.wikipedia.org/wiki/Child_grooming
[15] Non-au harassment campaign in France https://www.connexionfrance.com/French-news/Speak-out!-and-help-stop-bullying
[16] Survey of cyberbullying on Facebook
https://www.comparitech.com/internet-providers/cyberbullying-statistics/
[17] CynthiaVan hee, Gilles Jacobs, Chris Emmery, Els Lefever, “Automatic detection of cyberbullying in social media text 2”
[18] Support Vector Machines, “http://www.statsoft.com/textbook/support-vector-machines”
[19] Advantages and disadvantages of SVM https://statinfer.com/204-6-8-svm-advantages-disadvantages-applications/
[20] Naïve bayes classifier http://www.statsoft.com/textbook/naive-bayes-classifier
[21] Advantages and disadvantages of Naïve bayes clasifier https://www.quora.com/What-are-the-disadvantages-of-using-a-naive-bayes-for-classification
[22] KNN Classifier https://www.analyticsvidhya.com/blog/2018/03/introduction-k-neighbours-algorithm-clustering/
[23] Advantages and disadvantages of KNN Classifier https://people.revoledu.com/kardi/tutorial/KNN/Strength%20and%20Weakness.htm
[24] Logistic Regression https://www.statisticssolutions.com/what-is-logistic-regression/
|