Performance Analysis of Enhanced Reinforcement Algorithms While Web Content Retrieval in Topic Categorization
M. Karthica · International Journal for Research in Applied Science and Engineering Technology · 2025
Web content mining is the process of extracting or mining knowledge or useful information from web pages. The purpose of this work is to investigate web content extraction technology enhanced Reinforcement algorithm which anticipates user interest by analyzing the page according to user view related topic. Information seekers rely heavily on search engines to extract relevant information because of the Internet's exponential development in users and traffic. The availability of a vast amount of textual, audio, video, and other content has expanded search engines' duty. Users of the Internet can obtain pertinent information about their query from the search engine by using factors like content and link structure. The three improved algorithms like ANB-MLM, CBARM-MLM was then applied to a web text mining system and used to mine and collect information from various users. To test the performance of the proposed algorithms, the study compared the precision, recall, accuracy and F1-score values of the three algorithms under TREC dataset. The proposed algorithms was found and compared to find the better performance with maximum recall value, accuracy value and Fvalue in the dataset. Finally, it was found that the latter could achieve a maximum prediction accuracy which is much more accurate than the traditional algorithm for customer information collection. This ERA-MLM procedure involves locating web sites linked to user queries and using hyperlinks to locate a collection of related web pages and find the topic categorization using machine learning method compare existing and proposed methods.