Discussion: View Thread

I'm CJ, a PhD student in HKUST, currently engaged in a project involving a substantial volume of multiple videos featuring a speaker addressing an audience, over 1000 hours in total.

I'm seeking advice on primers, methods, or tools that could effectively and efficiently handle the coding and analysis of such large volumes of video data. Given the scale of the data, manual coding seems implausible.

Each video also contains distinct textual elements that are separate from the subtitles. Therefore, I'm seeking suggestions on tools or methods that can effectively analyze the speech, as well as extract and analyze these embedded textual elements from the videos, in conjunction with the speech data.

If you could kindly share your insights or experiences, please send an email to cj.rhee@connect.ust.hk.

Looking forward to learning from the community!

CJ Rhee
PhD Candidate, Department of Management, 
Hong Hong Univ. of Science & Tech. 

------------------------------
Changjoon Rhee
Clear Water Bay
------------------------------

CJ,

The following article (see attached page proofs) offers detailed advice regarding the use of video-based methods (including examples of articles that have used video-based methods recently and coded a large number of videos):

• Banks, G. C., & Aguinis, H. in press. Improving management theory and policymaking through innovative methods and data. Academy of Management Perspectives. https://doi.org/10.5465/amp.2022.0099

I hope this helps!

All the best,

--Herman.

------------------------------
Herman Aguinis, Ph.D.
Immediate Past President, Academy of Management
Avram Tucker Distinguished Scholar & Professor of Management
The George Washington University School of Business
Washington, DC
http://hermanaguinis.com/
------------------------------