Classified Average Precision (CAP) To Evaluate The Performance of Inferring User Search Goals
Journal Title: International Journal of Research in Computer and Communication Technology - Year 2014, Vol 3, Issue 11
Abstract
The presumption and examination of user search goals can be very useful in getting better performance of search engine. To deduce user search goals by analyzing search engine query logs a novel approach is proposed. We suggest a novel approach to infer user search goals by analyzing search engine query logs. Initially we propose a framework to find out different user search goals for a query by clustering the proposed feedback sessions. Feedback sessions are created from user click-through logs and can resourcefully imitate the information needs of users. Second we propose a novel approach to produce pseudo-documents to better stand for the feedback sessions for clustering. Finally we propose a new criterion “Classified Average Precision (CAP)” to calculate the performance of inferring user search goals. We define user search goals as the information on different aspects of a query that user groups want to obtain. Information need is a user’s particular need to attain information to convince his/her need. User search goals can be considered as the clusters of information needs for a query.
Authors and Affiliations
H M Sameera, N Rajesh Babu
Keywords
Related Articles
- EP ID EP28106
- DOI -
- Views 280
- Downloads 0
Assemblage Statistics through Big Data in Cloud with Accredit Public Analyse
Cloud computing is constantly growing as a standard for sharing the information over the remote stockpiling in an online cloud server. Cloud administrations offers awesome enhancements for the clients to appreciate t...
Data Possession Of Multiple Replicas Across The Distributed Storage System By Third Party Auditor
Cloud computing has four models as Public cloud through which the service is obtainable to all public use. Private cloud through which service is accessible to private enterprise or organization. Community Cloud perm...
Optimum Loss Allocation in Radial Distribution Systems
In this paper, the proposed method has the advantage that no assumptions are made in the allocation of real power losses as opposed other algorithms available in the literature. A detailed comparison of the real loss...
Design of Dadda Algorithm based Floating Point Multiplier
In this paper area efficient floating point multiplier is developed using Dadda Algorithm . For improving the speed of mantissa multiplication Dadda multiplier is used by replacing Carry Save Multiplier. The use of pr...
Principled Probabilistic Methods To Integrate Information From The Query Workload Into The Data Annotation Process
The aspiration of CADS is to persuade and inferior the cost of crafting adequately interpreted documents that can be right away helpful for usually issued partially prearranged enquiries. Our solution ambition is to...