Recently, much research effort has been devoted to the discovery and analysis of online social networks. However, relatively little research has been done for business network discovery and analysis. Although named entity recognition (NER) tools are available to identify basic entities in texts, there are still challenging research problems, such as co-reference resolution and the identification of abbreviations of organization names. Guided by the design science methodology, the main contribution of this paper is the design and development of a novel semi-supervised method for the identification of business entities (e.g., companies) and their relationships. Based on the automatically mined business networks, financial analysts can then predict the business prestige of companies for better financial investment decision making. Initial experiments show that the proposed business entity identification method is more effective than other baseline methods. Moreover, the proposed semi-supervised business relationship mining method is more effective than the state-of-the-art supervised machine learning classifier when a large number of manually labeled training examples are not available. The managerial implication is that business managers can apply the design artifacts to promptly identify potential business partners and competitors, and hence improve their strategic business decision marking processes.
Zhang, Wenping; Cai, Yi; Y.K. Lau, Raymond; S. Liao, Stephen; and C.W. Kwok, Ron, "Semi-Supervised Text Mining For Dynamic Business Network Discovery" (2012). PACIS 2012 Proceedings. 138.