Skip to main content

Table 10 A test example highlighting the extracted side effects obtained by CNN-NEAT’s Attention versus baselines

From: Neural side effect discovery from user credibility and experience-assessed online health discussions

  1. In the Post content column, the correct and incorrect side effects are highlighted in blue and red, respectively. The extracted side effects of UMLS Tagging, Neural Extractor and CNN-NEAT’s Attention are followed by <U>, <X>, and <N>, respectively. The Cluster’s side effects column shows the list of common side effects in user 8420’s cluster