Identifying Relevant YouTube Comments to Derive Socially Augmented User Models: A Semantically Enriched Machine Learning Approach
Media resources in social Web spaces trigger social interactions, as they consist of motivating means to create and exchange user-generated content. The massive social content could provide rich resources towards deriving social profiles to augment user models and improve adaptation in simulated learning environments. However, potentially valuable social contributions can be buried within highly noisy content that is irrelevant or spam. This paper sketches a research roadmap toward augmenting user models with key user characteristics derived from social content. It then focuses on the first step: identifying relevant content to create data corpus about a specific activity. A novel, semantically enriched machine learning approach to filter out the noisy content from social media is described. An application on public comments in YouTube on job interview videos has been made to evaluate the approach. Evaluation results, which illustrate the ability of the approach to filter noise and identify relevant social media content, are analysed.
KeywordsClassification Machine Learning Noise Filtration Social Media
Unable to display preview. Download preview PDF.
- 1.Agarwal, N., Liu, H.: Modelling and Data Mining in Blogosphere. In: Grossman, R. (ed.) Synthesis Lectures on Data Mining and Knowledge Discovery, vol. 1. Morgan & Claypool Publishers (2009)Google Scholar
- 2.Agichtein, E., Castillo, C., Donato, D., Gionis, A., Mishne, G.: Finding high-quality content in social media. In: Proceedings of the International Conference on Web Search and Web Data Mining (WSDM), Palo Alto, California, USA (2008)Google Scholar
- 3.Chung, S.F., Kathleen, A., Chu-Ren, H.: Using WordNet and SUMO to Determine Source Domains of Conceptual Metaphors. In: Proceedings of 5th Chinese Lexical Semantics Workshop (CLSW-5), pp. 91–98. COLIPS, Singapore (2004)Google Scholar
- 6.Kamaliha, E., Riahi, F., Qazvinian, V., Adibi, J.: Characterizing network motifs to identify spam comments. In: IEEE International Conference on Data Mining Workshops, ICDMW 2008, pp. 919–928 (2008)Google Scholar
- 8.Kolb, P.: DISCO: A Multilingual Database of Distributionally Similar Words. In: Proceedings of KONVENS-2008, Berlin (2008)Google Scholar
- 10.Metsis, V., Androutsopoulos, I., Paliouras, G.: Spam filtering with naive bayes - which naive bayes? In: 3rd Conference on Email and Anti-Spam CEAS (2006)Google Scholar
- 11.Schimratzki, O., Bakalov, F., Knoth, A., König-Ries, B.: Semantic Enrichment of Social Media Resources for adaptation. In: Proceedings of International Workshop on Adaptation in Social and Semantic Web (SAS-WEB 2010), Big Island of Hawaii, pp. 31–41 (2010)Google Scholar
- 12.Siersdorfer, S., Chelaru, S., Nejdl, W., Pedro, J.S.: How useful are your comments?: analyzing and predicting YouTube comments and comment ratings. In: Proceedings of the 19th International Conference on World Wide Web, Raleigh, North Carolina, USA, pp. 26–30 (2010)Google Scholar
- 13.Smeeton, N.C.: Early History of the Kappa Statistic. Biometrics 41, 795 (1985)Google Scholar
- 17.Zhu, L., Sun, A., Choi, B.: Online spam-blog detection through blog search. In: Proceedings of the Seventeenth ACM International Conference on Information and Knowledge Management (CIKM), pp. 1347–1348 (2008)Google Scholar