Corporate social network analysis : a deep learning approach

Identifying inter-firm relationships is critical in understanding the industry landscape. However, due to the dynamic nature of such relationships, it is challenging to capture corporate social networks in a scalable and timely manner. To address this issue, this research develops a framework to build corporate social network representations by applying natural language processing (NLP) techniques on a corpus of 10-K filings, describing the reporting firms’ perceived relationships with other firms. Our framework uses named-entity recognition (NER) to locate the corporate names in the text, topic modeling to identify types of relationships included, and Bidirectional Encoder Representations from Transformers (BERT) to predict the types of relationship described in each sentence. As a result of the framework, we can construct corporate social networks that capture the directionality of inter-firm relationships and the variety of relationship types, including alliance, competition, ownership and personal connection. To show the value of the network measures created by the proposed framework, we conduct two empirical analyses to see their impacts on firm performance. The first study shows the predictive power of the network measures in estimating future earnings. The result reveals that competition relationship and in-degree measurements increase the predictive power of the model. The second study focuses on the difference between individual perspectives in an inter-firm social network. Such difference is measured by the direction of mentions and is an indicator of a firm’s success in network governance.Business, Sauder School ofManagement Information Systems, Division ofGraduat