An improved kNN text classification method. (28th November 2019)

• Record Type: Journal Article
• Authors: Wang, Fengfei; Liu, Zhen; Wang, Chundong
• Is Part Of: International journal of computational science and engineering. Volume 20:Number 3(2019)
• Page Start: 397
• Page End: 403
• Publication Date: 2019-11-28
• Subjects: text classification -- k-nearest neighbours -- kNN -- self-organising map -- SOM -- neural network -- computer science -- engineering; Computer science -- Mathematics -- Periodicals; Computer simulation -- Mathematical aspects -- Periodicals; Computational intelligence -- Periodicals; 004.015105
• Languages: English
• ISSNs: 1742-7185

Abstract

This paper proposes an improved k NN text classification method. The k NN algorithm in vector space models (VSM) has several limitations, such as occupying excessive storage space and all dimensions in the k NN algorithm share the same weight, making classification inaccurate. To solve these problems, this paper proposes a SOM neural network with principal component weighting. In this model, the principal component analysis process is embedded into the SOM neural network. Specifically, principal component analysis is used to extract the main feature components of the assessed target. Then, it is inputted into the network for computation. Meanwhile, variance contribution rates of principal components are introduced into the Euclidean distance function in the forms of weights. Using the principal component weighting SOM algorithm to compute the weights of VSM dimensions together with the k NN algorithm could effectively reduce dimensions of a vector space, and increase the precision and speed of the k k NN text classification method.