Innovation has long been considered as a crucial criterion for scholar performance assessment. Current studies focus on the statical measurement of innovation while evidence about innovative potential from the perspective of the time dimension is still scarce. Using novel and unique data collected from the Microsoft Academic Graph, this paper first builds dual layer network (co-authorship network and citation network) to investigate the impact of social capital on innovation and proposes an integrative method by combining deep learning and scientometrics to predict scholars’ innovative potential in the future. The preliminary results validate that our proposed model has an effective prediction performance in innovative potential. This paper fills up the research void of existing studies on scholars’ innovation prediction and lays some practical contribution for entrepreneurs, university and government to build a talent pool through high innovative potential scholars’ prediction in early career.
Yin, Dehu; Zhang, Xi; and Zhao, Hongke, "Understanding and predicting innovative potential of scholars based on deep learning method" (2022). PACIS 2022 Proceedings. 219.
When commenting on articles, please be friendly, welcoming, respectful and abide by the AIS eLibrary Discussion Thread Code of Conduct posted here.