Mendeley, a free reference manager and academic social network, is co-organizing the 3rd International Workshop on Mining Scientific Publications along with CORE, the Open University, Athena Research and Innovation Center, and the European Library/ Europeana.
The vast amount of content hosted by digital libraries nowadays poses new challenges to the research community. It is no longer enough to make publications available for human readers; enormous value can be derived from opening these catalogues of data to machine reading.
Data mining tools can be used to read scholarly articles, transforming them from lists of words and images into real-world information such as facts, opinions and hypothesis. This can be a great time-saver for researchers, helping them to find important information in huge corpora quickly and easily.
The 3rd International Workshop on Mining Scientific Publications, which is collocated with the ACM/IEEE Joint Conference on Digital Libraries (JCDL 2014) September 8 to 12 in London, will explore these possibilities by bringing together people from different backgrounds who are interested in analysing and mining databases of scientific publications. In addition, the conference is open to all those involved in developing systems to enable such analysis, designing new technologies to improve the way research is being done, and supporting the openness and free availability of publications and research data.
It is expected that the event will draw researchers from across academia and industry to work through the amazing possibilities and challenges around mining scientific content. Previous workshops have attracted contributions and participants from leading institutions such as the British Library, the Library of Congress, Elsevier Labs and the National Library of Medicine.
The audience for the workshop will be a mixture of cross-disciplinary researchers, practitioners from industry and government, open access enthusiasts, and digital library developers.
Keynote speakers will include Dr. C. Lee Giles, David Reese Professor of Information Sciences and Technology at the Pennsylvania State University, and Dr. Birger Larsen, Professor in Information Analysis and Information Retrieval at the Department of Communication at Aalborg University Copenhagen.
Different approaches to addressing the challenges of mining scientific publications will be discussed. The organisers are now inviting people to submit their papers online, for inclusion in the programme. Both long papers (up to eight pages in the ACM style) and short papers (not exceeding four pages) are welcome, as are practical demonstrations and presentation of systems and methods (demonstration submissions should consist of a two-page description of the system, method or tool).
The workshop will be structured around three main themes: The whole ecosystem of infrastructures, including repositories, aggregators, text-and data-mining facilities, impact monitoring tools, datasets, services and APIs that enable analysis of large volumes of scientific publications; Semantic enrichment of scientific publications by means of text-mining, crowdsourcing or other methods; and Analysis of large databases of scientific publications to identify research trends, high impact, cross-fertilisation between disciplines, research excellence etc.
This year, a CORE publications dataset containing a large array of publications from various research areas has also been put together. This includes full-text as well as enriched versions of metadata, with the aim of providing workshop participants with a framework for developing and testing methods and tools around the workshop topics. Interested parties may access this data through the CORE portal.
