An Efficient Personalized Web Search Mechanism using BinRank Algorithm
T.D. Khadtare1, P.R. Thakare2, S.A.J. Patel3
1Prof. T.D. Khadtare, Department of Information Technology, Sinhgad Institute of Technology and Science, University of Pune (Maharashtra), India.
2Prof. P.R. Thakare, Department of Information Technology, Sinhgad Institute of Technology and Science, University of Pune (Maharashtra), India.
3Prof. S.A.J. Patel, Department of Information Technology, Sinhgad Institute of Technology and Science, University of Pune (Maharashtra), India.
Manuscript received on 12 March 2013 | Revised Manuscript received on 21 March 2013 | Manuscript Published on 30 March 2013 | PP: 285-289 | Volume-2 Issue-4, March 2013 | Retrieval Number: D0602032413/13©BEIESP
Open Access | Editorial and Publishing Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Dynamic authority-based online keyword search algorithms, such as Object rank and personalized page rank leverage semantic link information to provide high quality, high recall search in databases and the web. Conceptually, these algorithms require a querytime page rank style iterative computation over the full graph. This computation is too expensive for large graphs and not feasible at query time. Alternatively, building an index of precomputed results for some or all keywords involves very expensive processing. We introduce BinRank, a system that approximates ObjectRank results by utilizing a hybrid approach inspired by materialized views in traditional query processing. We materialized relatively small subsets of the data graph so that any keyword query can be answered by running ObjectRank on only one of the subgraphs. BinRank generates the subgraph by partitioning all the terms in corpus based on their cooccurence, executing ObjectRank for each partition using the terms to generate a set of random walk starting points, and keeping only those objects that receive negligible score. We demonstrate that Binrank can achieve subsecond query execution time on the English Wikipedia data set, while producing high-quality search results that closely approximate the results of Object Rank on the original graph. Our experimental evaluation investigates the trade-off between query execution time, quality of results, and storage requirements of Bin Rank.
Keywords: Bin Rank, Object Rank, Online Keyword Search, Page Rank .
Scope of the Article: Web Algorithms