A Comprehensive Model for Evaluating Website Competence Using Web Mining Techniques

Evaluating websites has become increasingly critical as they function as primary platforms for information dissemination, communication, and digital service delivery. Website quality directly affects user experience and significantly influences the perceived credibility of online content. Although numerous evaluation models have been proposed, many remain constrained by manual assessment procedures, limiting their scalability and suitability for dynamic web environments. To address these limitations, this study proposes a web-mining–driven evaluation model for assessing website competence through automated data extraction and weighted criteria analysis. The model integrates quantifiable indicators encompassing usability, content relevance, accessibility, reliability, and overall performance across multiple domains. Model robustness was validated through expert review and user-based evaluation. Statistical analysis demonstrates strong internal consistency (Cronbach’s alpha = 0.88), while content validity of the survey instrument—confirmed through expert evaluation—reached 0.94. Experimental results further indicate that the proposed approach outperforms existing methods, achieving 95% classification accuracy, high scalability, and an 80% user satisfaction rate, particularly in real-time evaluation contexts. Overall, the proposed framework offers a transparent, evidence-based mechanism for website quality assessment. By minimizing subjectivity and enabling automated analysis, it enhances digital trust and supports informed decision-making for developers, policymakers, and end users across diverse application domains.