Title:	RSR: RELATED SEARCH RECOMMENDATION WITH USER FEEDBACK SESSION
Author(s):	Sejal Desai, Vinuth Chandrasheker, Vijay Mathapati, Venugopal K. Rajuk, Sundaraja S. Iyengar, Lalit M. Patnaik
ISBN:	978-989-8533-39-5
Editors:	Ajith P. Abraham, Antonio Palma dos Reis and Jörg Roth
Year:	2015
Edition:	Single
Keywords:	Pseudo Document, Recommendation, Semantic Similarity, User Feedback Session
Type:	Full Paper
First Page:	19
Last Page:	27
Language:	English
Cover:
Full Contents:	click to dowload
Paper Abstract:	Keyword-based search on the Web is widely used approach for discovering information on the web. Web users usually suffer from the difficulties of arranging and formulating appropriate input queries due to lack of sufficient domain knowledge, hence the input queries are usually short and ambiguous. Query recommendation helps users to meet their information needs more clearly and suggest web queries that are related to their initial query. It also helps search engine to return appropriate answers and meet their needs. Users usually have some vague keywords to represent their information need in their minds. Hence, it is not a good idea to generate relation between user query keywords for recommendations. In this paper, we have presented Related Search Recommendation (RSR) framework, which locate keywords that appear in snippets clicked and un-clicked documents in feedback session. Pseudo documents are generated from feedback sessions which reflect what users wish to retrieve. Finally, semantic similarity is calculated between the terms present in pseudo document and used for recommendations. The proposed method provides semantically related search queries for the given input query. Simulation results show that the proposed framework RSR outperforms Snippet Click Model.
	Go Back