The number of scholarly documents produced by academics, researchers, and practitioners worldwide is increasing at an unprecedented speed. The term big scholarly data is coined for this rapidly growing scholarly source of information. Many large collections of scholarly data including digital libraries, search engines, repositories, knowledge bases, Wikipedia, and the Web have already covered millions of journal articles, conference proceedings, degree theses, books, patents, technical reports, tutorials, course materials, etc. For instance, the Microsoft Academic Graph contains scientific publication records, citation relationships between those publications, as well as authors, institutions, journals, conferences, and fields of study. The DBLP bibliography now lists more than 5000 conference and workshop series, as well as more than 1500 journals in computer science, which involve more than 4 million publications by more than 2 million authors.
Big scholarly data bring about new opportunities and challenges with respect to knowledge discovery, data mining, science of science, and education. It is imperative and vital for scholars to drive their knowledge towards the innovative generation of values from big scholarly data. New knowledge can be extracted by analyzing and mining big scholarly data to, e.g., better understand research dynamics, scientific collaboration and success, identify new directions of research, assess the quality of science, and enable personalized teaching and learning. To achieve these goals, however, a lot of challenges facing big scholarly data acquisition, storage, management, processing and usage must be addressed.
This workshop aims at bringing together academics and practitioners from diverse fields to share ideas and experience with management, analysis, mining, and applications of big scholarly data. Topics of interest include (but not limited to):
-New approaches to search, crawling and integration of scholarly data from various data sources
-Methods for storing, indexing, and query processing for big scholarly data
-Practices for scholarly data management and sharing
-Big scholarly data analysis, mining, and visualization
-Network science for scholarly data analytics
-Graph and text mining in big scholarly data
-Measuring the impact of publications, funding, courses, individuals, teams, etc.
-Computational behavioural sciences in research and education
-Academic social network analysis and mining
-Understanding and predicting success in research and education
-Design of next generation platforms and systems for research and education
-Novel services and applications for research and education