Online Forums Hotspot Detection and Analysis Using Aging Theory

Authors: K. Nirmala Devi, V. Murali Bhaskaran

Abstract:

The exponential growth of social media arouses much attention on public opinion information. The online forums, blogs, micro blogs are proving to be extremely valuable resources and are having bulk volume of information. However, most of the social media data is unstructured and semi structured form. So that it is more difficult to decipher automatically. Therefore, it is very much essential to understand and analyze those data for making a right decision. The online forums hotspot detection is a promising research field in the web mining and it guides to motivate the user to take right decision in right time. The proposed system consist of a novel approach to detect a hotspot forum for any given time period. It uses aging theory to find the hot terms and E-K-means for detecting the hotspot forum. Experimental results demonstrate that the proposed approach outperforms k-means for detecting the hotspot forums with the improved accuracy.

Keywords: Hotspot forums, Micro blog, Blog, Sentiment Analysis, Opinion Mining, Social media, Twitter, Web mining.

Digital Object Identifier (DOI): doi.org/10.5281/zenodo.1105177

References:

[1] Johan Bollen, Huina Mao, and Xiao-Jun Zeng, “Twitter mood predicts the stock market”, IEEEComputer, vol. 44 no.10,pp. 91–94, 2011.
[2] Nirmala Devi, K., Murali Bhaskaran, V.,2012, “A Semantic Enhanced Approach for Online Hotspot Forums Detection”, Proceedings of IEEE Conference - ICRTIT 2012,pp. 497-501, 2012.
[3] Chen, K., Luesukprasert, L. and Chou, S., “Hot topic extraction based on timeline analysisand multidimensional sentence modeling”, IEEE Transactions on Knowledge and Data Engineering, vol.19, no.8, pp.1016–1025, 2007.
[4] Peng, W., “Predicting collective sentiment dynamics from time-series social media”, Proceedings of the Conference WISDOM ’12, 2012.
[5] Liu, H., “Internet public opinion hotspot detection and analysis based on Kmeans and SVMalgorithm”, Proceedings of the International Conference of Information Science andManagement Engineering – ISME-2010, pp.257–261, 2010.
[6] Hu M. and Liu B, “Mining and summarizing customer review”, Proceedings of ACM Transactions on Knowledge and Data Engineering, pp.168-177, 2004.
[7] Lan You, Yongping Du, Jiayia Ge, Xuanjing Huang and Lide Wu, “BBS based hot topic retrieval using back propagation neural network”, Proceedings of IJCNLP 2004, Springer – Verlag, pp. 139-148, 2005.
[8] Tingting He, Guozhong Qu, Siwei Li and et.al., “Semi-automatic hot event detection”, Proceedings of the 2nd International Conference on advanced Data Engineering and Applications, pp.1008-1016, 2006.
[9] Zhang, Z. and Li, Q., “QuestionHolic: hot topic discovery and trend analysis in community question answering systems”, Expert Systems with Applications, Vol. 38, No. 6, pp.6949–6855, 2011.
[10] Platakis. M., Kotasakos,D and Gunopulos. D, “ Discovering Hot topics in the Blogosphere”, Proceedings of the 2nd panhellenic Scientific Student Conference on Informatics, Related Technologies and Applications EUREKA 2008, pp. 122-132.
[11] Zheng, D. and Li, F., “Hot topic detection on BBS using aging theory”, Proceedings of the WISM 2009, LNCS 5854, pp.129–138, 2009.
[12] Chen,C.C., Chen, Y.T., Sun, Y., Chen, M.C., “Life Cycle Modeling of News Events using Aging Theory”, LNCS(LNAI), vol.2837, pp.47-59, Springer, Heidelberg, 2003.
[13] Nirmala Devi,K. and Murali Bhaskaran, V. ,” Forecasting Indian Stock Market Using Particle Swarm Optimization and Support Vector Machine”, International Journal of Applied Engineering Research, vol.10, no.1, pp.1891-1900, 2015.
[14] http:// forums.digitalpoint.com