Identifying and Improving Dataset References in Social Sciences Full Texts

Scientific full text papers are usually stored in separate places than their underlying research datasets. Authors typically make references to datasets by mentioning them for example by using their titles and the year of publication. However, in most cases explicit links that would provide readers with direct access to referenced datasets are missing. Manually detecting references to datasets in papers is time consuming and requires an expert in the domain of the paper. In order to make explicit all links to datasets in papers that have been published already, we suggest and evaluate a semi-automatic approach for finding references to datasets in social sciences papers. Our approach doesn't need a corpus of papers (no cold start problem) and it performs well on a small test corpus (gold standard). Our approach achieved an F-measure of 0.854 for identifying references in full texts and an F-measure of 0.679 for finding correct matches of detected references in the da|ra dataset registry