A web personalized service based on dual GAs

  • Authors:
  • Zhengyu Zhu;Qihong Xie;Xinghuan Chen;Qingsheng Zhu

  • Affiliations:
  • Computer College of Chongqing University, Chongqing, P.R. China;Computer College of Chongqing University, Chongqing, P.R. China;Computer College of Chongqing University, Chongqing, P.R. China;Computer College of Chongqing University, Chongqing, P.R. China

  • Venue:
  • ICNC'05 Proceedings of the First international conference on Advances in Natural Computation - Volume Part III
  • Year:
  • 2005

Quantified Score

Hi-index 0.00

Visualization

Abstract

In this paper, a different Web personalized service (PS) based on dual genetic algorithms (Dual GAs) has been presented. Firstly, to distinguish the importance of each keyword to a user, we have introduced a new concept called influence-gene and a user profile model UP=(I, C), which includes not only the user's keyword-weights vector I but also a user's influence-genes vector C. Secondly, based on C, we have introduced a w-cosine similarity, which is an improver of the traditional cosine similarity. Finally, we have discussed how to design our Dual GAs to automatically discover and adjust the UP. The comparison tests show that the Dual GAs can discover the user profile more accurately and improve the precision of information recommendation.