Identifying Hidden Contexts in Classification
In this study we investigate how to identify hidden contexts from the data in classification tasks. Contexts are artifacts in the data, which do not predict the class label directly. For instance, in speech recognition task speakers might have different accents, which do not directly discriminate between the spoken words. Identifying hidden contexts is considered as data preprocessing task, which can help to build more accurate classifiers, tailored for particular contexts and give an insight into the data structure. We present three techniques to identify hidden contexts, which hide class label information from the input data and partition it using clustering techniques. We form a collection of performance measures to ensure that the resulting contexts are valid. We evaluate the performance of the proposed techniques on thirty real datasets. We present a case study illustrating how the identified contexts can be used to build specialized more accurate classifiers.
KeywordsLinear Discriminant Analysis Class Label Normalize Mutual Information Concept Drift Handling Strategy
Unable to display preview. Download preview PDF.
- 6.Harries, M.: Splice-2 comparative evaluation: Electricity pricing. Technical report, U. New South Wales (1999)Google Scholar
- 12.Ren, J., Shi, X., Fan, W., Yu, P.S.: Type-independent correction of sample selection bias via structural discovery and re-balancing. In: Proc. of the SIAM Int. Conf. on Data Mining (SDM 2008), pp. 565–576 (2008)Google Scholar
- 13.Roth, V., Lange, T., Braun, M., Buhmann, J.: A resampling approach to cluster validation. In: Proc. of Int. Conf. on Computational Statistics, pp. 123–128 (2002)Google Scholar
- 14.Strang, T., Linnhoff-Popien, C.: A context modeling survey. In: Workshop on Advanced Context Modelling, Reasoning and Management at the 6th Int. Conf. on Ubiquitous Computing (UbiComp 2004) (2004)Google Scholar
- 15.Turney, P.: The identification of context-sensitive features: A formal definition of context for concept learning. In: Proc. of the ICML 1996 Workshop on Learning in Context-Sensitive Domains, pp. 53–59 (1996)Google Scholar
- 16.Turney, P.: The management of context-sensitive features: A review of strategies. In: Proc. of the ICML 1996 Workshop on Learning in Context-Sensitive Domains, pp. 60–65 (1996)Google Scholar
- 17.Widmer, G., Kubat, M.: Learning in the presence of concept drift and hidden contexts. Machine Learning 23(1), 69–101 (1996)Google Scholar
- 18.Wu, M., Scholkopf, B.: A local learning approach for clustering. In: Advances Neural Information Processing Systems (NIPS 2006) (2006)Google Scholar