Social media is no doubt the richest source of human generated data. The user’s options, feedbacks and critiques provided by social network users reflect attitudes and sentiments of certain topics, products, or services. Every day, large quantity of messages is created, stored, commented, and shared by people on social media websites, such as Twitter, Instagram, Quora and Facebook. This in general acts as valuable data for researchers and practitioners in different application domains, such as data analytics, marketing, to inform decision-making. Extracting valuable social signals from the huge crowd’s messages is challenging, due to the dynamic crowd behaviors. These are the anomalies caused by a user because of his/her variable behavior towards different sources. Due to such risk parameters, it is always a great practice to have a mechanism to monitor each online social network user. This paper provides a way in which anomaly analysis can be implemented in social media such as Facebook. This work hence acts as a risk analyzer for the administrator of the Face book services so that they can formulate strategies to overcome the same.

Anomaly detection,Social network,SVM,Data Analytics

[1] M Swarna sudha ,K Arun Priya,”Data mining approach for anomaly detection in social network analysis”,2018,ICICCT conference 2018
[2] Z. Wang and Y. Parth, “Extreme Learning Machine for Multi-class Sentiment Classification of Tweets,” Proc. ELM-2015, Springer Int. Publ. 2016, vol. 1, pp. 1–11, 2016.
[3] M. Egele, G. Stringhini, C. Kruegel, and G. Vigna, “Towards detecting compromised accounts on social networks,” IEEE Transactions on Dependable andSecureComputing,vol.14,no.4,pp.447 – 460,2015.
[4] R. Yu, X. He, and Y. Liu, “Glad: group anomaly detection in social media analysis,” ACM Transactions on Knowledge Discovery from Data, vol. 10, no. 2, pp. 18–22, 2015.
[5] Z. Wang, J. C. Tong, and D. Chan, “Issues of social data analytics with a new method for sentiment analysis of social media data,” in 2014 IEEE 6th International Conference on Cloud Computing Technology and Science, 2014, pp. 899–904.
[6]M.Egele,G. Stringhini, “Compa: Detecting compromised accounts on social networks,” in NDSS, 2013,
[7] E. Haddi, X. Liu, and Y. Shi, “The role of text pre-processing in sentiment analysis,” Procedia Computer Science, vol. 17, pp. 26-32, Jan.2013.
[8] P. Gonçalves and M. Araújo, “Comparing and combining sentiment analysis methods,” Proc. first ACM Conf. Online Soc. networks. ACM, pp. 27–38, 2013.
[9] B. Yuan, Y. Liu, and H. Li, “Sentiment classification in Chinese microblogs:Lexicon-based and learning-based approaches,” Int. Proc. Econ. Dev. Res., vol. 68, pp. 1–6, 2013
[10] J. Ortigosa-Hernández, J. D. Rodríguez, L. Alzate, M. Lucania, I. Inza, “Approaching sentiment analysis by using semisupervised learning of multi-dimensional classifiers,” Neurocomputing, vol. 92, pp. 98-115, Sep. 2012.
[11] H. Ji, H. Deng, and J. Han, “Uncertainty reduction for knowledge discovery and information extraction on the World Wide Web,” Proceedings of the IEEE, vol. 100, no. 9, pp. 2658-2674, Sep. 2012.
[12] T. Takahashi, R. Tomioka, and K. Yamanishi, “Discovering emerging topics in social streams via link anomaly detection,”2011 IEEE 11th International Conference on Data Mining, pp. 1230–1235, 2011.
[13] X. Glorot, A. Bordes, and Y. Bengio, “Domain adaptation for largescalesentiment classification: A deep learning approach,” Proceedings of the 28th International Conference on Machine Learning
[14] B. Gokaraju, S. S. Durbha, R. L. King, S. Member, and N. H. Younan,“A machine learning based spatio-temporal data mining approach for
detection of harmful algal blooms in the Gulf of Mexico,” IEEE Journal, vol.4, pp. 710-720, 2011.
[15] N. A. Heard, D. J. Weston, K. Platanioti, D. J. Hand, et al.,“Bayesian anomaly detection methods for social networks,” ANNS, vol. 4, pp. 645–662, 2010.
[16] L. Akoglu, M. McGlohon, and C. Faloutsos, “Oddball: Spottinganomalies in weighted graphs,” in Pacific-Asia Conference on KnowledgeDiscovery and Data Mining, pp. 410–421, 2010.
[17] R. Sommer and V. Paxson, “Outside the closed world: On using machine learning for network intrusion detection,” in 2010 IEEE Symposium on Security and Privacy, pp. 305–316, May 2010.
[18] T. Wilson, J. Wiebe, “Recognizing contextual polarity: An exploration of features for phrase-level sentiment analysis,” ACL, vol. 35, no. 3, 2009.
[19] G.-B. Huang, Q.-Y. Zhu, and C.-K. Siew, “Extreme learning machine: Theory and applications,” Neurocomputing, vol. 70, no. 1–3, pp. 489– 501,Dec. 2006.
[20] B. Pang, L. Lee, and S. Vaithyanathan, “Thumbs up? sentiment classificationusing machine learning techniques,” Proc. ACL-02 Conf. Empir. methods Nat. Lang. Process. Assoc. Comput. Linguist., vol. 10, pp. 79–86, 2002.