SOFT COMPUTING TECHNIQUES FOR WEB QUALITY ANALYTICS

Abstract

Studies are indicative of the fact that high quality websites get better rankings on the search engines. A superior website is the one which provides reliable content, has good design & user interface and can address global audience. But the end- users struggle with the predicament of selecting qualitative websites. Although, “Quality” is fairly a subjective term, there is an obvious need of a useful and valid model which evaluates the quality attributes of a website. “A Website quality model essentially consists of a set of criteria used to determine if a website reaches certain levels of fineness”. The quality of a website must be assured in terms of technicality, accuracy of information, response time, design of website, ease of use, and many more. In this research, we start with the identification of features of a website that determines its quality, further we conduct an empirical study on 700 websites from 7 top-level domains using soft computing techniques. We run 6 baseline classifiers to categorize websites into good, average and poor using quality attributes. Subsequently, the use of metaheuristic-based algorithms (Particle Swarm Optimization, Elephant Search Algorithm and Wolf Search Algorithm) for optimal feature selection have been implemented to get an optimal subset of quality attributes that is able to predict the quality of website more accurately and to optimise the results of classifiers. Also, fuzzy logic-based inference system has been used for website quality quantification to generate a website quality score. This model is named as QualScoresite model. Comparative analysis of performance of optimised machine learning based website quality analytics and fuzzy logic-based website quality quantification has been done. The study confirms that optimised machine learning based website quality analytics is superlative in comparison to QualScoresite.