Creating Sentiment Corpora from Microblogging Using Machine Learning

Author(s): A. Alghamdi

This paper describes our work-in-progress implementation of a system to create microblogging sentiment corpora. We developed a smart phone application that aims to create microblogging lexical resources which can be used for sentient analysis. Our proposed approach to machine learning is to use active learning which aims to make the process of resource creation more effort and time efficient. Active learning helps us identify instants that if labeled will improve our sentiment analyser. Microblogging, on the other hand, reduces the cost of creating the resources.

1. Josh Attenberg and Foster Provost. Inactive learning?: difficulties employing active learning in practice. SIGKDD Explor. Newsl., 12(2):36–41, March 2011. ISSN 1931-0145. http://dx.doi.org/10.1145/1964897.1964906
2. A.S. Harpale and Y. Yang. Personalized active learning for collaborative filtering. In Proceedings of the 31st annual international ACM SIGIR conference on Research and development in information retrieval, pages 91–98. ACM, 2008. http://dx.doi.org/10.1145/1390334.1390352
3. David D. Lewis. A sequential algorithm for training text classifiers: corrigendum and additional data. SIGIR Forum, 29(2):13–19, September 1995. ISSN 0163-5840. http://dx.doi.org/10.1145/219587.219592
4. Burr Settles. Active learning literature survey. Computer Sciences Technical Report 1648, University of Wisconsin–Madison, 2009.
5. Vlachos. Workshop on adaptive text extraction and mining. In EACL 2006, Trento, 2006.
6. L. Von Ahn and L. Dabbish. Labeling images with a computer game. In Proceedings of the SIGCHI conference on Human factors in computing systems, pages 319–326. ACM, 2004. http://dx.doi.org/10.1145/985692.985733