Analysisof Students’ Web Browsing Behaviours Using Data Miningat a Campus Network

Murizah Kassim, Muhammad Ahlami Ashraf Roslan

doi:10.17762/turcomat.v12i6.5779

Abstract

Analytics provides insight to people based on the analytics of past usage by using techniques such as statistics, data mining, machine learning and artificial intelligence. Lack of monitoring system of browsing causes low engagements that reduce the growth of certain businesses caused by unnecessary browsing for students learning time. This paper presents an analysis on browsing behavior that classifies browsed words followed their ethical word-groups browsing. An Analytic platform is created as a monitoring system of browsing behavior. Data mining, indexing and classification method are used in this research as data is the essential key of creating a predictive model and four types of ethical groups have been filtered based on the browsing behaviors. The browsed words are categorized into four types of browsing called queries, applications, social media, Campus-related sites. The research method uses software tools and data mining process on the browsing data and analytics is presented on the development of the dashboard mainly using the R programming language. Few unethical words using the indexing method are generated in analytic graphs based on the type of browsing versus time. Data collected from the browsing behaviors of students’analysis taken from browsing database of personal computer and laboratory computer in the campus network. The result shows that othercategories are the highest categories which reached79.6% for personals' computer browsing compared to72.4% browsing at the laboratory computers. It is identified that about 21% of the browsing behavior was filtered during the data mined processed. The other category is still on the research portfolio where these libraries must be filtered in detail to identify whether they are learning or non-learning activities. This research is significant in that helps to increase the effectiveness of suggestions applications, optimize the internet usage by blocking unnecessary words or webpages, and even campus guide systems by monitoring the surrounding browsing behavior of the students’ usages of the campus network computer labs.

Highlights

The web has changed dramatically over the last two decades with online information was published scholarly and freely
Analysis shows that 9.91% of data on the web browser is the real browsing behaviour for personal computers while about 18.88% is from the laboratory computers
Web browsing behaviours have been studied in many aspects from web usage mining, applications, images downloadable, personalized systems, and many more

Summary

Introduction

The web has changed dramatically over the last two decades with online information was published scholarly and freely. Technology has changed where the internet is increasingly used to gain knowledge and understanding of a topic This knowledge is often acquired by browsing on the web and some factors that have influenced critical internet use have become social. It is a fact that the user will use incognito mode to browse unnecessary and unethical things to hide from leaving a cyber footprint. This private browsing was made for different goals but is used for a different purpose by the user as mentions in a study(Bursztein et al, 2010). There are several bits of knowledge that need to be gained such as the knowledge of data science, programming language, analytics, and the most important part is valid data. This research filters the words fetched from the words that are browsed by people from different situations

Literature Review

Methodology

Result and Analysis

Findings

Conclusion