Figure 2.

Classification of the citing document using cited references. The MedlineRanker algorithm was used to rank the citing document with respect to random ones using the references cited in the full document or its sections. Ranks were calculated by MedlineRanker for each document of a test set of 10,000 documents. T: total (or full document), I: introduction, M: methods, R: results, D: discussion, C: conclusion, and I+D: introduction and discussion.

Ortuño et al. BMC Bioinformatics 2013 14:113   doi:10.1186/1471-2105-14-113
Download authors' original image