Due to necessary scheduled maintenance, the JMIR Publications website will be unavailable from Wednesday, July 01, 2020 at 8:00 PM to 10:00 PM EST. We apologize in advance for any inconvenience this may cause you.
Who will be affected?
Readers: No access to all 28 journals. We recommend accessing our articles via PubMed Central
Authors: No access to the submission form or your user account.
Reviewers: No access to your user account. Please download manuscripts you are reviewing for offline reading before Wednesday, July 01, 2020 at 7:00 PM.
Editors: No access to your user account to assign reviewers or make decisions.
Copyeditors: No access to user account. Please download manuscripts you are copyediting before Wednesday, July 01, 2020 at 7:00 PM.
Macri C, Bacchi S, Teoh SC, Lim W, Lam L, Patel S, SLee M, Casson R, Chan W
Evaluating the Ability of Open-Source Artificial Intelligence to Predict Accepting-Journal Impact Factor and Eigenfactor Score Using Academic Article Abstracts: Cross-sectional Machine Learning Analysis
Evaluating the ability of open-source artificial intelligence to predict accepting-journal impact factor and Eigenfactor score using academic article abstracts: a pilot study
Carmelo Macri;
Stephen Bacchi;
Sheng Chieh Teoh;
WanYin Lim;
Lydia Lam;
Sandy Patel;
Mark SLee;
Robert Casson;
WengOnn Chan
ABSTRACT
Background:
Strategies to improve the selection of appropriate target journals may reduce delays in the dissemination of research results.
Objective:
We sought to use open-source artificial intelligence to assist with this process.
Methods:
PubMed was searched for articles published between 2016 and 2021 using the medical subject headings (MeSH) ‘ophthalmology’, ‘radiology’, and ‘neurology’. Article titles, abstracts, authors and MeSH terms were extracted. These data were used to develop a series of models that predict the impact factor or Eigenfactor score of the accepting journal.
Results:
There were 10,813 articles included in the study. The bidirectional encoder representations from transformers (BERT) model achieved the highest classification accuracy in the prediction of accepting journal impact factor and Eigenfactor score tertile (75.0% and 73.6% respectively).
Conclusions:
Open-source artificial intelligence can predict the impact factor of accepting peer-reviewed journals. Further studies examining the effect on publication success and time to publication of such recommender systems are required.
Citation
Please cite as:
Macri C, Bacchi S, Teoh SC, Lim W, Lam L, Patel S, SLee M, Casson R, Chan W
Evaluating the Ability of Open-Source Artificial Intelligence to Predict Accepting-Journal Impact Factor and Eigenfactor Score Using Academic Article Abstracts: Cross-sectional Machine Learning Analysis