Evaluating human versus machine learning performance in classifying research abstracts

HIGHLIGHTS

• who: Yeow Chong Goh from the School of Mechanical and Aerospace Engineering, Nanyang Technological University, Singapore, Singapore have published the Article: Evaluating human versus machine learning performance in classifying research abstracts, in the Journal: (JOURNAL)
• what: The study shows that ML classification algorithms trained on an existing mapping of abstracts onto fixed discipline groups outperform human research assistants at classifying new abstracts into these discipline groups. For the purpose of the study , the existing panel classifications are considered the ground truth that the authors do not question. As the authors are primarily interested in the . . .
  

   

  

  If you want to have access to all the content you need to log in!

  Thanks :)

  Username or E-mail:

  If you don't have an account, you can create one here.