Center for Science of Science

Thought leadership plays a crucial role in boosting team performance; thus, teams with more thought leaders may perform better. However, the impact of the number of thought leaders on team performance in a scientific context remains understudied. In this study, we consider the authors of a publication as a scientific team and define the authors responsible for conceptual tasks, i.e., “conceived and designed the experiments” (one of the tasks described in the PLOS contribution statements classification system), as thought leaders. Leveraging more than 140,000 papers from PLOS journals, we examine the relationship between the number of thought leaders and two aspects of team performance (i.e., team impact and team disruptiveness) from both correlational and causal perspectives. The results showed that (1) an inverted U-shaped relationship exists between the number of thought leaders and the team’s impact, and (2) teams with more thought leaders tend to produce less disruptive ideas. We also explored the impact of international collaboration, team size, and gender diversity together with the number of thought leaders on team performance and found that (3) international collaboration improves team impact but lowers the disruptiveness of team outputs. This study advances scholarly understanding of thought leadership in scientific teams and provides valuable insights for policymakers and team managers.

In this study, we examine the roles of dependency, reciprocity, and informal mentorship in the prediction of long-term research collaboration in five disciplines. We use co-authorship matrix-based multivariate time series features and interpretable machine learning to train long-term collaboration prediction models and interpret the feature importance of trained models. Overall, long-term research collaboration that is defined using various standards was rare across the examined disciplines, and the prediction results were moderate to good. We found dependency, reciprocity, and informal mentorship to have different roles in different disciplines. Among the three, informal mentorship was important in predicting long-term research collaboration in Agriculture, Geology, and Library and Information Science. Reciprocity, which measures the interdependence between two researchers was important to prediction in the fields of Agriculture and Geology. Finally, dependency was important in all the disciplines with varying degrees of importance.

Acknowledging individuals in research articles is known to be a personal and private expression of appreciation compared to other types of acknowledgment, such as financial support. Early studies have demonstrated the significant relationship between acknowledgement, coauthor, and citation. Little did we know to what extent of these relationships and which prompt what to some degree among them. We adopt a series of multivariate analyses, Bayes’ theorem, statistical analysis, and “before and after” matched-group studies to illustrate the acknowledgement patterns in 6323 research articles of 196 Nobel Prize laureates (NPL) from 2008 to 2018. Acknowledgment is consistently proved to significantly relate to co-authorship and citation where co-authorship and citing have an approximately 10% increasing effect on acknowledgement behavior. Our study is the first to state the order of such triangle: acknowledgement is significantly ahead of co-authorship and arguably occurs before citing behavior. Moreover, acknowledgement strengthens more than half of NPL on their co-authorship for 11% and citation for 72% after they acknowledge others. We verify the substantive possibility of co-authorship and citing behavior from acknowledgement and introduce a formation of a new norm of scholarly communication. This will greatly contribute to the matter of evaluation metrics and social network detection.

Coauthorship prediction applies predictive analytics to bibliographic data to predict authors who are highly likely to be coauthors. In this study, we propose an approach for coauthorship prediction based on bibliographic network embedding through a graph-based bibliographic data model that can be used to model common bibliographic data, including papers, terms, sources, authors, departments, research interests, universities, and countries. A real-world dataset released by AMiner that includes more than 2 million papers, 8 million citations, and 1.7 million authors were integrated into a large bibliographic network using the proposed bibliographic data model. Translation-based methods were applied to the entities and relationships to generate their low-dimensional embeddings while preserving their connectivity information in the original bibliographic network. We applied machine learning algorithms to embeddings that represent the coauthorship relationships of the two authors and achieved high prediction results. The reference model, which is the combination of a network embedding size of 100, the most basic translation-based method, and a gradient boosting method achieved an F1 score of 0.9 and even higher scores are obtainable with different embedding sizes and more advanced embedding methods. Thus, the strengths of the proposed approach lie in its customizable components under a unified framework.

The automatic summarization of scientific articles differs from other text genres because of the structured format and longer text length. Previous approaches have focused on tackling the lengthy nature of scientific articles, aiming to improve the computational efficiency of summarizing long text using a flat, unstructured abstract. However, the structured format of scientific articles and characteristics of each section have not been fully explored, despite their importance. The lack of a sufficient investigation and discussion of various characteristics for each section and their influence on summarization results has hindered the practical use of automatic summarization for scientific articles. To provide a balanced abstract proportionally emphasizing each section of a scientific article, the community introduced the structured abstract, an abstract with distinct, labeled sections. Using this information, in this study, we aim to understand tasks ranging from data preparation to model evaluation from diverse viewpoints. Specifically, we provide a preprocessed large-scale dataset and propose a summarization method applying the introduction, methods, results, and discussion (IMRaD) format reflecting the characteristics of each section. We also discuss the objective benchmarks and perspectives of state-of-the-art algorithms and present the challenges and research directions in this area.