An Effective Classification Method for Facebook Data

Year 2017, , 9 - 13, 24.09.2017

Fatih Ertam

https://doi.org/10.18100/ijamec.2018SpecialIssue30463

Abstract

Today, the use of the internet has become very common. One of the most important reasons for its widespread use is social media tools. Especially Facebook has a very important place in social media tools. For this study, classification was done by using Facebook data. Classifications made by artificial learning algorithms on a previously used data set are compared with accuracy values and learning times. For this purpose, support vector machines (SVM), extreme learning machines (ELM) and K nearest neighbor (kNN) approaches are compared. For the study, SVM and ELM algorithms were observed using different activation functions. For the study with KNN, different K values were tested with different distance metric calculation methods. In the classification approach with ELM, it was observed that higher accuracy values were reached in a shorter time. In addition, Receiver Operating Characteristic (ROC) curves are plotted for the classification in which the best values are obtained for each algorithm.

Keywords

Extreme learning machine, machine learning, roc curves, social media classification, support vector machine

References

• A. M. Kaplan and M. Haenlein, “Users of the world, unite! The challenges and opportunities of Social Media,” Bus. Horiz., vol. 53, no. 1, pp. 59–68, 2010.
• Statista, “Number of Worldwide Social Network Users 2010-2019,” Statista, 2016. [Online]. Available: http://www.statista.com/statistics/278414/number-of-worldwide-social-network-users/.
• Statista, “Facebook users worldwide 2016,” statista.com, 2016. [Online]. Available: http://www.statista.com/statistics/264810/number-of-monthly-active-facebook-users-worldwide/.
• D. Korschun and S. Du, “How virtual corporate social responsibility dialogs generate value: A framework and propositions,” J. Bus. Res., vol. 66, no. 9, pp. 1494–1504, 2013.
• W. G. Mangold and D. J. Faulds, “Social media: The new hybrid element of the promotion mix,” Bus. Horiz., vol. 52, no. 4, pp. 357–365, 2009.
• E. Turban, R. Sharda, and D. Delen, Decision Support and Business Intelligence Systems, vol. 8th. 2011.
• R. Zafarani, M. A. Abbasi, and H. Liu, Social Media Mining. Cambridge: Cambridge University Press, 2014.
• U. M. L. Repository, “Facebook metrics Data Set,” www.ics.uci.edu, 2016.
• S. Moro, P. Rita, and B. Vala, “Predicting social media performance metrics and evaluation of the impact on brand building: A data mining approach,” J. Bus. Res., vol. 69, no. 9, pp. 3341–3351, 2016.
• V. N. Vapnik, “Statistical Learning Theory,” Interpreting, vol. 2. p. 736, 1998.
• A. Statnikov, C. Aliferis, and I. Tsamardinos, “A comprehensive evaluation of multicategory classification methods for microarray gene expression cancer diagnosis,” Bioinformatics, vol. 21, no. 5, pp. 631–643, 2005.
• G. Huang, Q. Zhu, and C. Siew, “Extreme Learning Machine : A New Learning Scheme of Feedforward Neural Networks,” IEEE Int. Jt. Conf. Neural Networks, vol. 2, pp. 985–990, 2004.
• J. Luo, C.-M. Vong, and P.-K. Wong, “Sparse Bayesian extreme learning machine for multi-classification,” IEEE Trans. Neural Networks Learn. Syst., vol. 25, no. 4, pp. 836–43, 2014.
• G. Bin Huang, D. H. Wang, and Y. Lan, “Extreme learning machines: A survey,” Int. J. Mach. Learn. Cybern., vol. 2, no. 2, pp. 107–122, 2011.
• F. Ertam and E. Avcı, “A new approach for internet traffic classification: GA-WK-ELM,” Measurement, vol. 95, pp. 135–142, 2017.
• G. Huang, G. Bin Huang, S. Song, and K. You, “Trends in extreme learning machines: A review,” Neural Networks, vol. 61. pp. 32–48, 2015.
• F. Ertam and E. Avci, “Classification with Intelligent Systems for Internet Traffic in Enterprise Networks,”, Int’l Journal of Computing, Communications & Instrumentation Engg.(IJCCIE) vol. 3, no. 1, pp. 9–15, 2016.
• P. Courrieu, “Fast Computation of Moore-Penrose Inverse Matrices,” Neural Inf. Process. - Lett. Rev., vol. 8, no. 2, pp. 25–29, 2008.
• M.L. Zhang and Z.H. Zhou, ML-KNN: A lazy learning approach to multi-label learning. Pattern recognition, 40(7), 2038-2048, 2007.
• F. Ertam and E. Avcı, Network Traffic Classification via Kernel Based Extreme Learning Machine. International Journal of Intelligent Systems and Applications in Engineering, 4 (Special Issue), 109-113, 2016.