Downloads: 110 | Views: 199

Research Paper | Computer Science & Engineering | India | Volume 3 Issue 12, December 2014

Enhanced Approach for Construing & Reorganizing User Search Result Using Feedback Session

Sultana N. Sayyad | Deepak S. Tamhane

Abstract: As different users may have different search goals or different search queries for same search results. There may be broad topic or ambiguous query which user wants to search through search engine. The reconstruction and analysis of user search results can be very useful in improving search engine relevance & user experience. In this paper we propose a enhanced approach to construe user search goals by analyzing search engine query logs. Primarily we propose a framework to find out different search results for a query by grouping the proposed feedback session. Feedback session is generated from no of clicks per query logs (click through logs) and can efficiently reflect need of user. Second we propose a enhanced approach to generate duplicated document or pseudo document to represent the result of grouping, n last we propose a new criterion Classified Average Precision (CAP) to conclude the performance of construing user search results. Concluded Results are presented using click-through logs from a commercial Search Engine to verify and validate the effectiveness of our proposed methods.

Keywords: Web mining, pseudo documents, information retrieval, Web text analysis, searching, grouping

Edition: Volume 3 Issue 12, December 2014,

Pages: 2651 - 2657