A Filtering Algorithm of Main Word Frequency for Online Commodity Subject Classification in E-Commerce

Abstract

—Based on the traditional classification of plain text in E-Commerce, this article has put forward a processing method in accordance with semi-structured data and main information in web pages, which enhances the accuracy of the product distribution. On the basis of the traditional textmining, combined with the structure and links of web page, this article has proposed an improved web page text representation model in E-Commerce based on supporting vector machines and web text classification algorithm, but there are still a lot of shortcomings waiting for further improvement. According to the data contrast in precision ratio, recall ratio and F-measure, the effect of the improved experiment with LDF-IDF is comprehensively better than that of tf-idf. The precision rate in certain classification can reach 100%, but there is low precision rate caused by items with fewer samples or samples fuzziness. Therefore, the classification of the correct category will directly affect the effect of classification.