The Random Neural Network Applied to an Intelligent Search Assistant
Will Serrano · Communications in computer and information science · 2016
Users can not guarantee the results they obtain from Web search engines are exhaustive, or that they actually respond to their needs. Search results are influenced by the users’ own ambiguity in formulating their requests or queries as well as by the commercial interest of Web search engines and Internet users that want to reach a wider audience. This paper presents an Intelligent Search Assistant (ISA) based on a Random Neural Network that acts as the interface between users and search engines to present data to users in a manner that reflects their actual needs or their observed or stated preferences. Our ISA tracks the user’s preferences and makes a selection on the output of one or more search engines using the preferences that it has learned. We also introduce a “relevance metric” to compare the performance of our Intelligent Search Assistant against a few search engines, showing that it provides better performance.