Topical Prescriptive Analytics System for Automatic Recommendation of Convergence Technology

Abstract

This study applies text mining in scientific articles for discovery of interdisciplinary convergence technology between biotechnology (BT) and information and communication technology (ICT). For in-depth interpretation of the technologies without domain experts’ review, a topic modeling method, Latent Dirichlet allocation (LDA), was used to propose an automatic recommendation system. We also applied prescriptive analytics with an option for users to select appropriate recommendation process of items. Our findings are as follows. First, LDA was efficient to facilitate the analysis of a large collection of documents by decreasing the dimension of the data. Second, the automatic recommendation method with various selectable options that could overcome limitations from that domain experts review the entire set of numerous topics. Finally, as a result of investigation of the final convergence technology candidates, it was proved that the system we propose here is more cost/time-effective compared to a method of reviewing all of the topic associations. Overall, a new methodology to support experts’ final decision by LDAand prescriptive analytics-based automatic recommendation system was successfully developed to discover convergence technologies between BT and ICT, which was also proved by several examples of applications.