Semi-supervised Text Classification Using SVM with Exponential Kernel

Kernel-based learning methods (kernel methods for short) in general and support vector machine (SVM) in particular have been successfully applied to the task of text classification. This is mainly due to their relatively high classification accuracy on several application domains as well as their ability to handle high dimensional and sparse data which is the prohibitive characteristics of textual data representation. A significant challenge in text classification is to reduce the need for labeled training data while maintaining an acceptable performance. This paper presents a semi-supervised technique using the exponential kernel for text classification. Specifically, the semantic similarities between terms are first determined with both labeled and unlabeled training data by means of a diffusion process on a graph defined by lexicon and co-occurrence information, and the exponential kernel is then constructed based on the learned semantic similarity. Finally, the SVM classifier trains a model for each class during the training phase and this model is then applied to all test examples in the test phase. The main feature of this approach is that it takes advantage of the exponential kernel to reveal the semantic similarities between terms in an unsupervised manner, which provides a kernel framework for semi-supervised learning. The proposed approach is demonstrated on several benchmark data sets for text classification and the experimental results show that it can significantly improve the classification performance.