Skip to main content

Table 3 Affiliation parsing performance

From: An automatic method to generate domain-specific investigator networks using PubMed abstracts

 

Country

Institution

 

Parsable*

Accuracy†

Parsable

Accuracy

General PubMed test data

92.1%

94.0%

91.3%

86.8%

HuGE PubMed test data

97.0%

91%

94.2%

87.0%

  1. *Parsable: number of abstracts that have country or institution information/number of abstracts that have affiliation information.
  2. †Accuracy: number of abstracts that have correct country or institution information/number of abstracts that have affiliation information.
Back to article page

BMC Medical Informatics and Decision Making

ISSN: 1472-6947

Contact us