Data Mining and Knowledge Engineering

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

A Novel Model for Web Mining


Affiliations
1 SOA University, Orissa, India
2 Konark Institute of Science & Technology, Bhubaneswar, Orissa, India
     

   Subscribe/Renew Journal


Aim of this paper is to propose a novel Web usage mining approach. The proposed approach is based on Latent Dirichlet Allocation (LDA) model. The experimental results on the selected
usage data set have shown that the proposed LDA-based Web usage mining is capable of revealing the latent task space and generating the user session clusters with better quality in comparison with other conventional Latent Semantic Analysis (LSA) based approaches.


Keywords

Web Usage Mining, LSA, LDA.
User
Subscription Login to verify subscription
Notifications
Font Size

Abstract Views: 286

PDF Views: 3




  • A Novel Model for Web Mining

Abstract Views: 286  |  PDF Views: 3

Authors

Monalisa Panda
SOA University, Orissa, India
Pradosh Ranjan Parida
Konark Institute of Science & Technology, Bhubaneswar, Orissa, India
Umesh Chandra Mishra
Konark Institute of Science & Technology, Bhubaneswar, Orissa, India
Siba Prasada Panigrahi
Konark Institute of Science & Technology, Bhubaneswar, Orissa, India

Abstract


Aim of this paper is to propose a novel Web usage mining approach. The proposed approach is based on Latent Dirichlet Allocation (LDA) model. The experimental results on the selected
usage data set have shown that the proposed LDA-based Web usage mining is capable of revealing the latent task space and generating the user session clusters with better quality in comparison with other conventional Latent Semantic Analysis (LSA) based approaches.


Keywords


Web Usage Mining, LSA, LDA.