Current digital libraries collect and allow access to digital papers and their metadata – but mostly do not analyze the full-text of the materials they index. The scale of scholarly publications poses a challenge for scholars in their search for relevant literature. This special issue calls for new, unpublished article submissions on the analysis of scholarly publications and data, in the context of the explosion in the production of scientific literature and the growth of scientific enterprise. Articles in the issue will investigate how natural language processing, information retrieval, scientometric and recommendation techniques can advance the state of the art in scholarly document understanding, analysis and retrieval at scale. Researchers are in need of assistive technologies to track developments in an area, identify the approaches used to solve a research problem over time and summarize research trends. Digital libraries require semantic search, question- answering and automated recommendation and reviewing systems to manage and retrieve answers from scholarly databases. Full document text analysis can help to design semantic search, translation and summarization systems; citation and social network analyses can help digital libraries to visualize scientific trends, bibliometrics and relationships and influences of works and authors. All these approaches can be supplemented with the metadata supplied by digital libraries - such as the article title, journal or conference name, author information, language, datasets, keywords, section headers, citation relationships, topic terms - and even browsing and usage data, such as related search queries and download counts.