The purposes of this study are to find out linguistic features to be used in Thai clause segmentation using support vector machine (SVM) model as well as to compare efficiency of those features on clause segmentation system. The corpus used

The main purpose of this study is to develop the intrinsic plagiarism detection in Thai academic writing system using Support Vector Machine model (SVM.) as well as comparing performance of two different kinds of input and feature and then analyzes... whether the length of input has an effect on accuracy. This study uses 300 pieces of master theses of undergraduate students from Chulalongkorn University consists of 5,155,589 words in total. Support Vector Machine model applied in the research is libsvm