Evaluating importance of websites on news topics

  • Authors:
  • Yajie Miao;Chunping Li;Liu Yang;Lili Zhao;Ming Gu

  • Affiliations:
  • School of Software, Tsinghua University, Beijing, China;School of Software, Tsinghua University, Beijing, China;School of Software, Tsinghua University, Beijing, China;School of Software, Tsinghua University, Beijing, China;School of Software, Tsinghua University, Beijing, China

  • Venue:
  • PRICAI'10 Proceedings of the 11th Pacific Rim international conference on Trends in artificial intelligence
  • Year:
  • 2010

Quantified Score

Hi-index 0.00

Visualization

Abstract

In this paper, we study a novel problem which we refer to as News Website Evaluation (NWE). Given a collection of news articles, NWE is primarily concerned with evaluating the importance of their websites with respect to specific news topics. This general problem subsumes many interesting applications including news tracking and website ranking. To solve this problem, we first propose a Topic-oriented Website Evaluation Model (TWEM) which exploits various forms of information and combines them in a unified computation framework. Then, considering the special characteristics of news articles, we incorporate an article merging operation into TWEM and present the merge-TWEM model. The experimental results show that the proposed models perform significantly better than competitive baseline systems, and can serve as effective solutions to the News Website Evaluation problem.