Geographic Information Retrieval and Text Mining on Chinese Tourism Web Pages

  • Authors:
  • Ming-Cheng Tsou

  • Affiliations:
  • National Kaohsiung Marine University, Taiwan

  • Venue:
  • International Journal of Information Technology and Web Engineering
  • Year:
  • 2010

Quantified Score

Hi-index 0.00

Visualization

Abstract

The World Wide Web WWW offers an enormous wealth of information and data, and assembles a tremendous amount of knowledge. Much of this knowledge, however, comprises either non-structured data or semistructured data. To make use of these unexploited or underexploited resources more efficiently, the management of information and data gathering has become an essential task for research and development. In this paper, the author examines the task of researching a hostel or homestay using the Google search web service as a base search engine. From the search results, mining, retrieving and sorting out location and semantic data were carried out by combining the Chinese Word Segmentation System with text mining technology to find geographic information gleaned from web pages. The results obtained from this particular searching method allowed users to get closer to the answers they sought and achieve greater accuracy, as the results included graphics and textual geographic information. In the future, this method may be suitable for and applicable to various types of queries, analyses, geographic data collection, and in managing spatial knowledge related to different keywords within a document.