Discovering latent commercial networks from online financial news articles

Abstract

Unlike most online social networks where explicit links among individual users are defined, the relations among commercial entities (e.g. firms) may not be explicitly declared in commercial Web sites. One main contribution of this article is the development of a novel computational model for the discovery of the latent relations among commercial entities from online financial news. More specifically, a CRF model which can exploit both structural and contextual features is applied to commercial entity recognition. In addition, a point-wise mutual information (PMI)-based unsupervised learning method is developed for commercial relation identification. To evaluate the effectiveness of the proposed computational methods, a prototype system called CoNet has been developed. Based on the financial news articles crawled from Google finance, the CoNet system achieves average F-scores of 0.681 and 0.754 in commercial entity recognition and commercial relation identification, respectively. Our experimental results confirm that the proposed shallow natural language processing methods are effective for the discovery of latent commercial networks from online financial news.

Keywords:

• commercial entity recognition
• commercial relation identification
• commercial networks
• text mining
• natural language processing

Acknowledgements

This work is partially supported by NSFC (No. 60703051) and MOST (No. 2009DFA12970). We thank the reviewers for the valuable comments.

Notes

1. AeroText: http://www.lockheedmartin.com/products/aerotext/

2. NetOwl: http://www.sra.com/netowl/

3. Google Finance: finance.google.com.cn

4. Google Dictionary: http://www.google.cn/dictionary

5. HIT Tonyici Cilin: http://ir.hit.edu.cn/

6. Graphviz: http://www.graphviz.org/