Proceedings of the 18th ACM/IEEE on Joint Conference on Digital Libraries
Welcome to the 2018 ACM/IEEE-CS Joint Conference on Digital Libraries (JCDL) in Fort Worth, Texas!
It is our great pleasure to present the proceedings of the 18th JCDL. This year's conference theme -- From Data to Wisdom: Resilient Integration across Societies, Disciplines, and Systems -- reflects the progress of digital libraries into a mature research field. JCDL has always invited a broad range of reporting on research, development, and best practices, ranging across theories, systems, services, and applications in the field. This year's call focused on inviting contributions from many different disciplines (also newcomers and associated disciplines) and different stakeholders (researchers and practitioners), with the intent to showcase the diverse methods and research mix in the DL community.
We believe that this goal has been achieved. This year's sessions cover topics about different object types (e.g., text, multimedia), different domains (science, archives), different digital library development stages (collection building, indexing and access, use), and different analysis approaches (citation analysis, topic modelling, linking).
The call for papers attracted submissions from 29 countries on four continents. The program committee reviewed and accepted 26 full research papers (from 71 reviewed), 13 short research papers (from 38 reviewed), 4 tutorials, 5 workshops (from 7 reviewed), 45 posters and 3 demonstrations (from 68 reviewed). The doctoral consortium, which looks to assist and mentor young scholars in the investigation and research of digital libraries, received 20 submissions and accepted 11 for presentation at JCDL. This proceedings volume contains the full text of the papers, as well as abstracts of the keynotes, tutorials, workshops, panels, demonstrations, and posters.
All paper submissions went through a rigorous reviewing process with three individual reviewers on each paper and a meta-review by a fourth expert from the DL community, which prepared the discussion for the program committee meeting in February 2018. With over 160 PC committee members from three continents, the program committee met virtually to discuss all submitted papers and the conference schedule. Posters and demos were accepted in two rounds of submissions: first, in an open, public call, as well as a second, invitation-only round for converting longer submissions into poster form.
As in the past, we will be awarding three honors: the Vannevar Bush Best Paper Award, the Best Student Paper Award, and the Best Poster/Demo Award. During the opening session of the conference, the nominees for the two Best Paper Awards will be announced. The prizes will be presented at the banquet. We hope you will be inspired by the high quality and creativity of these award-winning papers.
Co-authorship networks contain hidden structural patterns of research collaboration. While some people may argue that the process of writing joint papers depends on mutual friendship, research interests, and university policy, we show that, given a temporal co-authorship network, one could predict the quality and quantity of future research publications. We are working on the comparison of existing graph embedding and feature engineering methods, presenting combined approach for constructing co-author recommender system formulated as link prediction problem. We also present a new link embedding operator improving the quality of link prediction base don embedding feature space. We evaluate our research on a single university publication dataset, providing meaningful interpretation of the obtained results.