Fuzzy Deep Neural Learning Based on Goodman and Kruskal's Gamma for Search Engine Optimization

Sethuraman Jayaraman, Manikandan Ramachandran, Rizwan Patan, Mahmoud Daneshmand, Amir H. Gandomi

Research output: Contribution to journalArticlepeer-review

4 Scopus citations

Abstract

Search engine optimization (SEO) is a significant problem for enhancing a website's visibility with search engine results. SEO issues, such as Site Popularity, Content Quality, Keyword Density, and Publicity, were not considered during the search engine optimization process. Therefore, the retrieval rate of the existing techniques is inadequate. In this study, Triangular Fuzzy Deep Structured Learning-Based Predictive Page Ranking (TFDSL-PPR) technique is proposed to solve these limitations. First, the TFDSL-PPR technique takes a number of user queries as input in the input layer, and then it employs four hidden layers in order to deeply analyze the web pages based on an input query. The first hidden layer determines the keywords from the user query. The second hidden layer measures the site popularity, content quality, keyword density and publicity of all web pages in the search engine. It then accomplishes Goodman and Kruskal's Gamma Predictive Ranking process in the third hidden layer, where it ranks the web pages by considering their similarities. The proposed TFDSL-PPR technique is applied to the ClueWeb09 Dataset with respect to a variety of user queries. The results are benchmarked by existing methods based on several metrics such as retrieval rate, time, and false-positive rate.

Original languageEnglish
Pages (from-to)268-277
Number of pages10
JournalIEEE Transactions on Big Data
Volume8
Issue number1
DOIs
StatePublished - 1 Feb 2022

Keywords

  • Content quality
  • Deep structured learning
  • Filtering
  • Keyword density
  • Publicity
  • Ranking
  • Search engine
  • Site popularity
  • Web pages

Fingerprint

Dive into the research topics of 'Fuzzy Deep Neural Learning Based on Goodman and Kruskal's Gamma for Search Engine Optimization'. Together they form a unique fingerprint.

Cite this