Using Machine Learning for Web Page Classification in Search Engine Optimization

This paper presents a novel approach of using machine learning algorithms based on experts’ knowledge to classify web pages into three predefined classes according the degree content adjustment search engine optimization (SEO) recommendations. In this study, classifiers were built and trained an unknown sample (web page) one identify important factors that affect page adjustment. The data in training set are manually labeled by domain experts. experimental results show can be used for predicting SEO recommendations—classifier accuracy ranges from 54.59% 69.67%, which is higher than baseline classification samples majority class (48.83%). Practical significance proposed providing core building software agents expert systems automatically detect pages, or parts need improvement comply with guidelines and, therefore, potentially gain rankings engines. Also, study contribute field detecting optimal values ranking engines use rank pages. Experiments suggest taken consideration when preparing title, meta description, H1 tag (heading), body text—which aligned findings previous research. Another result research new further