Original Research ARTICLE
Predictive Effects of Novelty Measured by Temporal Embeddings on the Growth of Scientific Literature
- 1Department of Information Science, College of Computing and Informatics, Drexel University, United States
Novel scientiﬁc knowledge is constantly produced by the scientiﬁc community. Understanding the level of novelty characterized by scientiﬁc literature is key for modeling scientiﬁc dynamics and analyzing the growth mechanisms of scientiﬁc knowledge. Metrics derived from bibliometrics and citation analysis were effectively used to characterize the novelty in scientiﬁc development. However, time is required before we can observe links between documents such as citation links or patterns derived from the links, which makes these techniques more effective for retrospective analysis than predictive analysis. In this study, we present a new approach to measuring the novelty of a research topic in a scientiﬁc community over a speciﬁc period by tracking semantic changes of the terms and characterizing the research topic in their usage context. The semantic changes are derived from the text data of scientiﬁc literature by temporal embedding learning techniques. We validated the effects of the proposed novelty metric on predicting the future growth of scientiﬁc publications and investigated the relations between novelty and growth by panel data analysis applied in a large-scale publication dataset (MEDLINE/PubMed). Key ﬁndings based on the statistical investigation indicate that the novelty metric has signiﬁcant predictive effects on the growth of scientiﬁc literature and the predictive effects may last for more than ten years. We demonstrated the effectiveness and practical implications of the novelty metric in three case studies.
Keywords: Predictive effects, Scientific novelty, Scientific growth, Temporal embedding learning, scientific dynamics
Received: 08 Sep 2017;
Accepted: 12 Feb 2018.
Edited by:Zaida Chinchilla-Rodríguez, Consejo Superior de Investigaciones Científicas (CSIC), Spain
Reviewed by:Trevor Cohen, University of Texas School of Biomedical Informatics, United States
Kun Lu, University of Oklahoma, United States
Copyright: © 2018 He and Chen. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
Mr. Jiangen He, Drexel University, Department of Information Science, College of Computing and Informatics, 3141 Chestnut Street, Philadelphia, 19104, Pennsylvania, United States, email@example.com
Prof. Chaomei Chen, Drexel University, Department of Information Science, College of Computing and Informatics, 3141 Chestnut Street, Philadelphia, 19104, Pennsylvania, United States, firstname.lastname@example.org