Discovering Emerging Research Topics Based on SPO Predications

• Published in: Knowledge Management in Organizations Vol. 1027; pp. 110 - 121
• Main Authors: Hu, Zhengyin, Zeng, Rong-Qiang, Peng, Lin, Pang, Hongseng, Qin, Xiaochu, Guo, Cheng
• Format: Book Chapter
• Language: English
• Published: Switzerland Springer International Publishing AG 2019; Springer International Publishing
• Series: Communications in Computer and Information Science
• Subjects: Community detection; Emerging research topics; Hypervolume-based selection; Stem cell; Subject-Predication-Object
• ISBN: 3030214508; 9783030214500
• ISSN: 1865-0929; 1865-0937
• DOI: 10.1007/978-3-030-21451-7_10

With the rapid growth of scientific literatures, it is very important to discover the implicit knowledge from the vast information accurately and efficiently. To achieve this goal, we propose a percolation approach to discovering emerging research topics by combining text mining and scientometrics methods based on Subject-Predication-Object (SPO) predications, which consist of a subject argument, an object argument, and the relation that binds them. Firstly, SPO predications are extracted and cleaned from content of literatures to construct SPO semantic networks. Then, community detection is conducted in the SPO semantic networks. Afterwards, two indicators of Research Topic Age (RTA) and Research Topic Authors Number (RTAN) combined by hypervolume-based selection algorithm (HBS) are chosen to identify potential emerging research topics from communities. Finally, scientific literatures of stem cells are selected as a case study, and the result indicates that the approach can effectively and accurately discover the emerging research topics.