Additional Resources
Automating annotations of the cognitive neuroimaging literature using ATHENA

Riedel MC, Salo T, Hays J, Turner MD, Sutherland MT, Turner JA, Laird AR, INCF Neuroinformatics (2018).


We sought to develop classifiers for automatically annotating neuroimaging research articles with labels from the Cognitive Paradigm Ontology. We examined classifier performance when varying corpus (abstract-only vs full-text), feature space (bag-of-words vs Cognitive Atlas), classifiers (BnB, knn, lr, svm). The most optimal classification performance across labels utilized full-text with bag-of-words and the logistic regression algorithm. When only considering abstract-text, the Cognitive Atlas features outperformed the bag-of-words features. We also found that anatomical terms dominated the features used for classification/