ICTACT Journal on Soft Computing

Open Access Open Access  Restricted Access Subscription Access
Open Access Open Access Open Access  Restricted Access Restricted Access Subscription Access

Classification of Query Recommendation Using Query Semantic Flow Graph Technique on Novel AOL LOG Method


Affiliations
1 Department of Computer Science, Rathnavel Subramaniam College of Arts and Science, India
     

   Subscribe/Renew Journal


Web mining is one among the thrust area of research in the data mining domain. The classification of query recommendation can be divided into two major classes that are document-based approach and log-based approach. Log-based method can get relatively good query recommendation and find query inner relation. Query flow graph is one of log-based method and get relatively good recommendation. However, query flow graph cannot get query semantic information. And there are many isolated nodes because of data sparseness. Therefore, word2vec is used to define the query semantic and add query semantic to query flow graph. That can be able to modify query transfer probability which is calculated by query flow graph. At the same time, we can get connection between the isolated queries that are related but no connection due to the data sparseness and the inaccuracy of session split. Empirical tests are conducted in accordance with the AOL log. From the results the efficiency of the approach in suggesting queries and F1 value is about 20% higher than the traditional query flow graph.

Keywords

Query Recommendation, Word2vec, Semantics, Query Flow.
Subscription Login to verify subscription
User
Notifications
Font Size

  • R. Kop, “The Unexpected Connection: Serendipity and Human Mediation in Networked Learning”, Journal of Educational and Technology Society, Vol. 15, No. 2, pp. 2-11, 2012.

  • R.W. White and G. Marchionini, “Examining the Effectiveness of Real-Time Query Expansion”, Information Processing and Management, Vol. 43, No. 3, pp. 685-704, 2007.

  • S. Noor and S. Bashir, “Evaluating Bias in Retrieval Systems for Recall Oriented Documents Retrieval”, International Arab Journal of Information Technology, Vol. 12, No. 1, pp. 53-59, 2015.

  • N.J. Belkin, C. Cool, J. Head, J. Jeng, D. Kelly, S. Lin and L. Lobash, “Relevance Feedback versus Local Context Analysis as Term Suggestion Devices: Rutgers TREC-8 Interactive Track Experience”, Proceedings of International Conference on Text Retrieval, pp. 565-574, 2000.

  • Z. Cheng, B. Gao and T.Y. Liu, “Actively Predicting Diverse Search Intent from User Browsing Behaviors”, Proceedings of International Conference on World Wide Web, pp. 221-230, 2010.

  • B. Zhang, B. Zhang, S. Zhang and C. Ma, “Query Recommendation based on Irrelevant Feedback Analysis”, Proceedings of International Conference on Biomedical Engineering and Informatics, pp. 644-648, 2016.

  • P. Boldi, F. Bonchi, C. Castillo, D. Donato, A. Gionis and S. Vigna, “The Query-Flow Graph: Model and Applications”, Proceedings of ACM Conference on Information and Knowledge Management, pp. 609-618, 2008.

  • I. Antonellis, H. GarciabMolina and C.C. Chang, “Simrank++: Query Rewriting Through Link Analysis of the Click Graph”, Proceedings of International Conference on World Wide Web, pp. 408-421, 2007.

  • D. Beeferman and A. Berger, “Agglomerative Clustering of a Search Engine Query Log”, Proceedings of ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 407-416, 2000.

  • H. Ma, H. Yang, I. King and M.R. Lyu, “Learning Latent Semantic Relations from Click through Data for Query Suggestion”, Proceedings of ACM Conference on Information and Knowledge Management, pp. 709-718, 2008.

  • S. Gupta and D. Garg, “Selectivity Estimation of Range Queries in Data Streams using Micro-Clustering”, International Arab Journal of Information Technology, Vol. 13, No. 4, pp. 396-402, 2016.

  • H.M. Zahera, G.F. El Hady and W.F. Abd El Wahed, “Query Recommendation for Improving Search Engine Results”, Lecture Notes in Engineering Computer Science, Vol. 2186, No. 1, pp. 45-52, 2010.

  • G.E. Hinton, “Learning Distributed Representations of Concepts”, Proceedings of 8th International Conference of the Cognitive Science Society, pp. 1-12, 1986.

  • J. Rygl and P. Sojka, “Semantic Vector Encoding and Similarity Search using Fulltext Search Engines”, Proceedings of Workshop on Representation Learning for NLP, pp. 81-90, 2017.

  • M.F.M. Chowdhury, V. Chenthamarakshan, R. Chakravarti and A.M. Gliozzo, “Query Focused Variable Centroid Vectors for Passage Re-ranking in Semantic Search”, Proceedings of International Conference on Knowledge Discovery and Data Mining, pp. 1-14, 2018.

  • J. Li, J. Li, X. Fu, M.A. Masud and J.Z. Huang, “Learning Distributed Word Representation with Multi-Contextual Mixed Embedding”, Knowledge-Based Systems, Vol. 106, No. 3, pp. 220-230, 2016.

  • J. Singh and A. Sharan, “Relevance Feedback-based Query Expansion Model using Ranks Combining and Word2Vec Approach”, IETE Journal of Research, Vol. 62, No. 5, pp. 591-604, 2016.

  • L. White, R. Togneri, W. Liu and M. Bennamoun, “How Well Sentence Embeddings Capture Meaning”, Proceedings of 20th Australasian Symposium on Document Computing, pp. 1-8, 2015.

  • X. Rong, “Word2vec Parameter Learning Explained”, Proceedings of International Conference on Computer Science, pp. 1-21, 2014.

  • Y. Li and K. Lyons, “Word Representation using a Deep Neural Network”, Proceedings of International Conference on Computer Science and Software Engineering, pp. 268-279, 2016.

  • W. Ling, C. Dyer, A.W. Black and I. Trancoso, “Two/Too Simple Adaptations of Word2Vec for Syntax Problems”, Proceedings of Conference on North American Chapter of the Association for Computational Linguistics - Human Language Technologies, pp. 1299-1304, 2015.

  • H. Tong, C. Faloutsos and J.Y. Pan, “Fast Random Walk with Restart and its Applications”, Proceedings of International Conference on Data Mining, pp. 613-622, 2006.


Abstract Views: 192

PDF Views: 1




  • Classification of Query Recommendation Using Query Semantic Flow Graph Technique on Novel AOL LOG Method

Abstract Views: 192  |  PDF Views: 1

Authors

R. Balakrishnan
Department of Computer Science, Rathnavel Subramaniam College of Arts and Science, India

Abstract


Web mining is one among the thrust area of research in the data mining domain. The classification of query recommendation can be divided into two major classes that are document-based approach and log-based approach. Log-based method can get relatively good query recommendation and find query inner relation. Query flow graph is one of log-based method and get relatively good recommendation. However, query flow graph cannot get query semantic information. And there are many isolated nodes because of data sparseness. Therefore, word2vec is used to define the query semantic and add query semantic to query flow graph. That can be able to modify query transfer probability which is calculated by query flow graph. At the same time, we can get connection between the isolated queries that are related but no connection due to the data sparseness and the inaccuracy of session split. Empirical tests are conducted in accordance with the AOL log. From the results the efficiency of the approach in suggesting queries and F1 value is about 20% higher than the traditional query flow graph.

Keywords


Query Recommendation, Word2vec, Semantics, Query Flow.

References