Abstract
<p class="Abstract"><span lang="EN-US">Searching for information on the Internet is not only an activity newly rediscovered, but also a strategic tool to achieve a wide variety of information. Indeed, it’s extremely important to know how to find the information quickly and efficiently. Unfortunately, the Web is so huge and so little structured, that gathering precise, fair and useful information becomes an expensive task. In order to define an information retrieval tool (meta search engine) that brings together multiple sources of information search, interest must be credited to the merger phase of search engines results. On the other hand, information search systems tend primarily to model the user with a profile and then to integrate it into the information access chain, to better meet its specific needs. </span></p><p class="Abstract"><span lang="EN-US">This paper presents a custom fusion method based on Borda method and values retrieved from the user profile. We evaluated our approach on multiple domains and we present some experimental results.</span></p>
Highlights
Search engines are the most visited sites on the web, they are used by 85% of users (Schwartz, 1998)
This paper presents a custom fusion method based on Borda method and values retrieved from the user profile
We propose a fusion method based on Borda voting system, it regards the fusion of search engines results as a poll to vote for a collection of candidate documents by order, which voters are search engines. it was already processed in this area, on the other hand, the population of voters was not considered
Summary
Search engines are the most visited sites on the web, they are used by 85% of users (Schwartz, 1998). Search engines provide a score representing the similarity degree between the request and the document This strategy is called "fusion by score"'. Analysis of user's behavior reveals a particular importance It is by knowing perfectly how the user is going to develop its information retrieval strategies that it will be possible to propose significant information for his research. We propose a fusion method based on Borda voting system, it regards the fusion of search engines results as a poll to vote for a collection of candidate documents by order, which voters are search engines. In order to properly apply the method of Borda, we need to know the popularity of each search engine which represents its weight relative to the request This value depends heavily on the specific user needs, so we assign for each search engine a weight based on the user profile. The first section presents the most used fusion method, the second section presents some work in personalized information retrieval, the third section presents our approach with its different axes, the fourth section presents some experimental results evaluating the performance of our approach and in the last section, was completed by a conclusion and an overview on our perspectives
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callMore From: International Journal of Recent Contributions from Engineering, Science & IT (iJES)
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
