Scope

In the era of 4th industrial revolution, the availability of an enormous amount of unstructured data from various different sources creates both enormous opportunities and significant challenges. In biomedicine, for instance, the results of experiments or clinical trials are often only discovered long after they are first published, and this long-elapsed time may lead to failure of timely translation of research results into clinical practice or missed hypotheses for effective new drugs or treatments. Literature-based discovery (LBD) enabled by text mining aims to address this problem by leveraging what is already known from research, as published in the literature, to make connections and generate new research questions through inference. Although LBD originated in the biomedical domain, we have observed that it is being actively explored in other domains including psychology, economics, and climate science.

Text-mining and Literature-based Discovery invites papers addressing emerging challenges in a range of approaches that take a body of research literature as the input, apply a series of computational, manual, or hybrid processes, and finally generate hypotheses that are potentially novel and meaningful for further investigations.

The section is particularly interested in papers on:
•         Natural language processing
•         Entity extraction and relation extraction
•         Intelligent or semantic search
•         Full-text mining
•         Entity linking
•         Text-based hypothesis generation
•         Mining clinical texts
•         Evaluation and validation, and trust and privacy as it is relevant to text mining

High quality papers that go beyond these topics or integrate them in novel ways are equally welcome.

Submission

Copyright Statement