Time: Friday，October 23，12:00-13:00

Location: Main Building 418

Presenter: Chen Hongshu, Associate Professor, School of Management and Economics, Beijing Institute of Technology

Speaker Profile:

Chen Hongshu, Ph.D. in Management, Beijing Institute of Technology, and Ph.D. in Information Systems, Sydney University of Science and Technology, is now in the Department of Management Science and Logistics, School of Management and Economics, Beijing Institute of Technology. He is an assistant professor and special associate researcher. His main research interests are text mining, metrology, innovation management and science and technology evaluation. More than 20 papers have been published in international journals such as IEEE Transactions on Cybernetics、Technological Forecasting and Social Change、IEEE Transactions on Engineering Management、Knowledge-Based Systems and Portland International Conference on Management of Engineering &Technology, and have served as reviewers of many SCI/SSCI international journals.

Introduction:

China has entered an important period of alternating between the 13th Five-Year Plan and the 14th Five-Year Plan. The huge demand for source innovation from various fields, such as economic and social development and national security, has been released, and it is urgent to improve the energy efficiency of the transformation of the achievements of the innovation system. The process of innovation greatly drives the generation and accumulation of corresponding scientific and technological text data, and implies important knowledge and competitive intelligence such as core technology, key elements and potential cooperation opportunities. In the environment of big data, how to extract the technical topics from the perspective of machine learning, abstract complex relationships, and then explore these hidden knowledge, is becoming one of the important research issues that the academic and industrial circles pay attention to. Based on recent related studies, the speaker introduces the basic concepts and methods of topic model and word embedding, exchanges on technical topic identification and topic network analysis, and discusses the future research topics in related fields.