Personalised web search using ACO with information scent

Abstract

In this paper the information scent is used as pheromone in ACO for optimising the personalised web search based on clustered user search query sessions. It is realised that user's search for information on the web using information scent of the clicked URLs is analogous to that of ants searching for food using the pheromone in ACO. The user clicks to the personalised search results is used to update increase/decrease the information scent of the corresponding clicked URLs of the stored query sessions and the associated clusters dynamically. This regular updation of information scent optimises the relevant set of clicked URLs associated with the clusters and hence personalises the user's search effectively. An experimental study was conducted on the web user query sessions to test the effectiveness of the proposed approach and results shows the effective improvement in the precision of search results.