The increase of use of Social networking sites in recent years has both pros and consequences. The idea is to have safer use of these Social media sites so as to obtain maximum benefits from them rather than having malicious effects from them. One of the misuses of these social networking sites like Twitter, Facebook, and Instagram is posting of absurd contents over these Social Medias. This content can be extremely harmful as it causes insult, depression, anxiety, peer pressure. This needs to be detected and reported for better use of social media. This measure will make an approach for better use of Internet yard. Hence, this research work aims at Predicting and detecting these harassing comments with the help of Machine learning Algorithms. The idea is to do Sentimental Analysis of the tweets obtained from Twitter, Pre-process them, apply Machine Learning algorithms along with Bag-Of-Words on the tweets and classify the tweets as positive and negative. Tweets classified as negative will help to detect the tweet as bullying or not. The proposed research work uses bag of words approach along with Laplace version of the Naive-Bayes classifier with Laplace function for Detection. For Prediction CART model with Bag-of-Words approach is used. The platform used here is R studio with various packages.

Prediction, Detection, Hectoring, Bag-of-word ,Laplace, Confusion Matrix

[1]. Bello-Orgaz, Gema, Jason J. Jung, and David Camacho. "Social big data: Recent achievements and new challenges." Information Fusion 28 (2016): 45-59.
[2]. Frommholz, Ingo, Haider M. Al-Khateeb et all"On textual analysis and machine learning for cyberstalking detection." Datenbank-Spektrum 16, no. 2 (2016),pp-127-135..
[3]. Al-garadi, Mohammed Ali, Kasturi Dewi Varathan, and Sri Devi Ravana. "Cybercrime detection in online communications: The experimental case of cyberbullying detection in the Twitter network." Computers in Human Behavior 63 (2016), pp. 433-443.
[4]. Chen, Ying, Yilu Zhou et all "Detecting offensive language in social media to protect adolescent online safety." In Privacy, Security, Risk and Trust (PASSAT), 2012 International Conference on and 2012 International Confernece on Social Computing (SocialCom), pp. 71-80. IEEE, 2012..
[5]. Parker, Shawniece L., and Yen-Hung Hu. "Content Mining Techniques for Detecting Cyberbullying in Social Media." Virginia Journal of Science 67, no. 3 (2016),pp 1-8.
[6]. Sheela, L. Jaba. "A Review of Sentiment Analysis in Twitter Data Using Hadoop." International Journal of Database Theory and Application 9, no. 1 (2016): 77-86.
[7]. Zhao, Rui, Anna Zhou, and Kezhi Mao. "Automatic detection of cyberbullying on social networks based on bullying features." In Proceedings of the 17th international conference on distributed computing and networking, p. 43. ACM, 2016.
[8]. Ismail, Mohamed Maher Ben, and Ouiem Bchir. "Insult detection in social network comments using possibilistic based fusion approach." In Computer and Information Science, pp. 15-25. Springer International Publishing, 2015.
[9]. Nagar, Himanshu, Chetna Dabas, and J. P. Gupta. "Navie Bayes and K-Means Hybrid Analysis for Extracting Extremist Tweets", ACM Conference, pp 27-32.