An architecture for dynamic location description generation from the web for human way-finding

  • Authors:
  • JaeJeung Kim;JaeHoon Cho;Jung-hee Ryu

  • Affiliations:
  • KAIST Institute for IT Convergence, Gwahak-ro, Yuseong-gu, Daejeon, Korea;GSCT, KAIST, Gwahak-ro, Yuseong-gu, Daejeon, Korea;GSCT, KAIST, Gwahak-ro, Yuseong-gu, Daejeon, Korea

  • Venue:
  • Proceedings of the 7th International Conference on Advances in Mobile Computing and Multimedia
  • Year:
  • 2009

Quantified Score

Hi-index 0.00

Visualization

Abstract

People obtain location information through on/offline activities and they are represented into a 'verbal description' in their daily communication. The description of a certain location is shared by people through blogs, e-mails, and many other forms of communication. However the location descriptions may vary among people due to different perception, unlike explicit forms as street names or address numbers. In this paper, we propose an architecture for retrieving and generating location descriptions from the blogosphere. The location descriptions are dynamically generated harnessing the wisdom of crowds, by aggregating the fragmented descriptions into an accurate and objective one for human way-finding. The experimental results of this study showed that in a comparison of the official address as well as the location descriptions of random bloggers, the recognition of the location description created with the proposed scheme showed a higher level of accuracy