An Optimal Web Page Re-ranking Based on Improved Rider Optimization

Web page ranking is important in search engines. User queries make it difficult to retrieve relevant documents quickly in the web environment. This research proposes an efficient web page re-ranking algorithm to address this issue. Web pages are initially generated by Google and Bing depending on user queries. Search engines retrieve relevant web pages and filter them for further processing. Preprocessed documents are sent to feature extraction, which extracts text-, correlation-, semantic-, and statistical-based features. The Improved Rider optimization approach uses the re-ranking measure after feature extraction. The standard rider optimization approach is improved by opposition-based learning. The suggested IROA takes and analyzes search engine ranking scores to re-rank them. However, the suggested IROA approach yields satisfactory precision, recall, and F-measure values of 0.95, 0.96, and 0.90.