A Study of University Website Content Classification Using Machine Learning

Abstract

Abstract A university website is a gateway to the institution’s information, products, and services. As websites grow into millions in numbers, it is essential to ensure that the content reflects the needs of its students, staff, and other academic institution as their primary users. This research investigates the development of a new framework that uses machine learning techniques based on webometrics and web usability to classify the web pages of academic websites automatically. The framework briefly introduced how it can help classify web content and eliminate unrelated content and reduce storage space. The findings can also be used to analyse other web-based data to give additional insights that may be beneficial for webometrics studies and identify university website’ characteristics.