String vector based KNN for text categorization

Abstract

This research proposes the string vector based version of the KNN as the approach to the text categorization. Traditionally, texts should be encoded into numerical vectors for using the traditional version of KNN, and encoding so leads to the three main problems: huge dimensionality, sparse distribution, and poor transparency. In order to solve the problems, in this research, texts are encoded into string vectors, instead of numerical vectors, the similarity measure between string vectors is defined, and the KNN is modified into the version where string vector is given its input. As the benefits from this research, we may expect the better performance, more compact representation of each text, and better transparency. The goal of this research is to improve the text categorization performance by solving them.