Visualizing web site comparisons
Proceedings of the 11th international conference on World Wide Web
Mining product reputations on the Web
Proceedings of the eighth ACM SIGKDD international conference on Knowledge discovery and data mining
Mining and summarizing customer reviews
Proceedings of the tenth ACM SIGKDD international conference on Knowledge discovery and data mining
The role of e-marketplaces in relationship-based supply chains: a survey
IBM Systems Journal
Introduction to information extraction
AI Communications
Compare&contrast: using the web to discover comparable cases for news stories
Proceedings of the 16th international conference on World Wide Web
| Hi-index | 0.00 |
Relationships between companies and business events of company relation changing can act as the most important factors to conduct market analysis and business management. However, it is very difficult to track company relations and to detect the related events, because the relations change rapidly and continuously. Existing technologies are limited to analysis of non-temporal relations or temporal tracking web data in a single feature. Our work targets temporal and multiple-type relation mining. The proposed method automates relation instance extraction from the Web, temporal relation graph creation, and business event detection based on the created temporal graph. In the experiment, more than 70 thousand relation instances were extracted from 1.7 million English news articles, and a temporal relation graph of 255 companies from 1995 to 2007 was generated, and acquisition events and cases of competition relation evolution were detected. These results show our method is effective.