Research on the Application of Improved Text Classific Algorithm in Intelligent Learning Platform

摘要

With the rapid developing of the network information, it seems to be quite important to provide a more reasonable text classification algorithm for learners. In this paper, we adopt a sensitivity method to modify the characteristic weight in the distance formula and put up with a cutting method of training sample database based on CURE algorithm and Tabu algorithm; then adopt CURE cluster algorithm to acquire each representative sample in order to constitute a new training sample collection, then use Tabu algorithm to make a further maintenance to this sample collection. While appending the sample, it is only necessary to consider appending the samples of different type boundary. Append or delete sample with classification accuracy highest and with the original training sample database nearest to the rule, and provide learners with reasonable text classification system.