A HYBRID MCDM MODEL FOR THE INTELLIGENT ENHANCEMENT OF SEARCH ENGINE OPTIMIZATION
DOI:
https://doi.org/10.35546/kntu2078-4481.2025.4.2.17Keywords:
search engine optimization, SEO, DEMATEL, DANP, VIKOR, web analytics, relevance, backlinks, keywords, digital marketing.Abstract
The objective of the study is to develop an integrated decision-support model for search engine optimization (SEO) based on a hybrid multi-criteria approach combining the DEMATEL, DANP, and VIKOR methods. The proposed framework enables a comprehensive evaluation of the interdependencies among technical, content-related, and behavioral SEO factors, identification of their systemic roles, and formulation of well-grounded optimization decisions in the context of increasingly complex search engine algorithms. Unlike classical linear or hierarchical evaluation approaches, this model considers causal relationships and inter-criteria dependencies, making it particularly suitable for analyzing modern SEO environments. Within the empirical investigation, a group of technology-sector websites was analyzed based on expert evaluations across eight key criteria: content quality, keyword semantics, page loading speed, site structure, mobile responsiveness, backlink profile strength, user behavior signals, and technical SEO. The DEMATEL method was employed to construct a causal-effect influence matrix and identify dominant criteria, with site structure and loading speed demonstrating the strongest causal impact. Subsequently, the DANP method enabled the calculation of global criteria weights that reflect their relative importance within the network of mutual influences. At the final stage, the VIKOR method was applied to perform compromise-based ranking of the evaluated websites and to determine those with the most balanced SEO performance. The findings demonstrate the effectiveness of the hybrid MCDM model for supporting strategic SEO decision-making, optimizing resource allocation, identifying systemic bottlenecks, and enhancing the relevance and visibility of web resources in search engine results. The proposed approach can serve as a quantitative, transparent, and analytically robust tool for SEO specialists, digital marketers, and analysts involved in evaluating and improving website optimization strategies.
References
Amin G. R., Emrouznejad A. Optimizing search engines results using linear programming. Expert Systems with Applications. 2011. Vol. 38, no. 9. P. 11534–11537.
Aswani R., Kar A. K., Ilavarasan P. V., Dwivedi Y. K. Search engine marketing is not all gold: insights from Twitter and SEOClerks. International Journal of Information Management. 2018. Vol. 38, no. 1. P. 107–116.
Bar-Ilan J., Mat-Hassan M., Levene M. Methods for comparing rankings of search engine results. Computer Networks. 2006. Vol. 50, no. 10. P. 1448–1463.
Dye K. Website abuse for search engine optimization. Network Security. 2008. No. 3. P. 4–6.
Malaga R. A. Search engine optimization – black and white hat approaches. Advances in Computers. 2010. Vol. 78. P. 1–39.
Mavridis T., Symeonidis A. L. Identifying valid search engine ranking factors in a Web 2.0 and Web 3.0 context for building efficient SEO mechanisms. Engineering Applications of Artificial Intelligence. 2015. Vol. 41. P. 75–91.
Yalçın N., Köse U. What is search engine optimization: SEO? Procedia – Social and Behavioral Sciences. 2010. Vol. 9. P. 487–493.
Xiang Z., Gretzel U. Role of social media in online travel information search. Tourism Management. 2010. Vol. 31, no. 2. P. 179–188.
Zhang J., Dimitroff A. The impact of webpage content characteristics on webpage visibility in search engine results (part I). Information Processing & Management. 2005. Vol. 41, no. 3. P. 665–690.
Tzeng G. H., Huang J. J. Multiple attribute decision making: methods and applications. London : Chapman & Hall/CRC, 2011. 352 p.
Tsuei H. J., Tsai W. H., Pan F. T., Tzeng G. H. Improving search engine optimization (SEO) by using hybrid modified MCDM models. Artificial Intelligence Review. 2020. Vol. 53. P. 1–16.
Jansen B. J., Spink A. An analysis of web searching by European AlltheWeb.com users. Information Processing & Management. 2005. Vol. 41, no. 2. P. 361–381.
Spink A., Jansen B. J., Blakely C., Koshman S. A study of results overlap and uniqueness among major web search engines. Information Processing & Management. 2006. Vol. 42, no. 5. P. 1379–1391.
Hung Y. H. та ін. Online reputation management for improving marketing by using a hybrid MCDM model. Knowledge-Based Systems. 2012. Vol. 35. P. 87–93.
Vaughan L. New measurements for search engine evaluation proposed and tested. Information Processing & Management. 2004. Vol. 40, no. 4. P. 677–691.
