Intelligent location-based mobile news service system with automatic news summarization

  • Authors:
  • Chih-Ming Chen

  • Affiliations:
  • Graduate Institute of Library, Information and Archival Studies, National Chengchi University, No. 64, Sec. 2, ZhiNan Rd., Wenshan District, Taipei City, 116 Taiwan, ROC

  • Venue:
  • Expert Systems with Applications: An International Journal
  • Year:
  • 2010

Quantified Score

Hi-index 12.05

Visualization

Abstract

The accelerated rapid development of wireless network and mobile computing technologies has increased the convenience of mobile information services for obtaining useful information in our daily lives. The technology has thus become an essential research issue. In particular, location-based services (LBSs) on mobile devices can convey location related information to individual users, thus helping users to obtain helpful and adaptive information. Accordingly, this study presents an intelligent location-based service system to provide local news with summaries to personal handheld PDA (Personal Digital Assistant) device based on the user's location. First, this study proposes a novel multi-document news summarization scheme based on fuzzy synthetic evaluation. This scheme identifies a key paragraph in a news story as a summary based on three evaluation scores, in order to dispatch news information to mobile devices with small screens. Furthermore, to sense a user's location precisely, the study also develops a practicable location-awareness scheme based on GPS (Global Positioning System) signals to identify the position of a user in the Taiwan area. Finally, an intelligent location-based mobile news service system with automatic news summarization for location-based news services was implemented by combining the proposed multi-document news summarization and user location schemes. The proportion of satisfactory news summaries is up to 86%, and the accuracy of the user location-awareness scheme is up to 90%, according to experimental results in multi-document summarization and user location identification. These experimental results show that the proposed system can be successfully applied in real-world applications for personalized location-based news services.