A Comparative Analysis of Nuclear Energy Issue Frames in Press Releases and News Articles : A Topic Modeling Approach

2017 ◽  
Vol 17 (3) ◽  
pp. 172-229
Author(s):  
Taejun Lee ◽  
Seungbae Lee ◽  
Changdong Oh
2018 ◽  
Vol 22 (3) ◽  
pp. 109-134
Author(s):  
JIHYO KIM ◽  
Eon-Suk Ko

Author(s):  
Beth Lyall-Wilson ◽  
Nicolas Kim ◽  
Elizabeth Hohman

This paper describes the development and new application of a text modeling process for identifying human factors topics, such as fatigue, workload, and distraction in aviation safety reports. Current approaches to identifying human factors topic representations in text data rely on manual review from subject matter experts. The implementation of a semi-supervised text modeling method overcomes the need for lengthy manual review through an initial extraction of pre-defined human factors topics, freeing time for focus on analyzing the information. This modeling approach allows analysts to use keywords to define topics of interest up front and influence the convergence of the model toward a result that reflects them, which provides an advantage over classic topic modeling approaches where domain knowledge is not integrated into the generation of derived topics. This paper includes a description of the modeling approach and rationale, data used, evaluation methods, challenges, and suggestions for future applications.


2020 ◽  
Vol 10 ◽  
Author(s):  
Raffaele Sperandeo ◽  
Giovanni Messina ◽  
Daniela Iennaco ◽  
Francesco Sessa ◽  
Vincenzo Russo ◽  
...  

Sign in / Sign up

Export Citation Format

Share Document