As videos are becoming important for qualitative studies, what are the best methods to analyse this type of data and particularly political tv shows? Could you share recent papers about this topic? Your insight is greatly appreciated.
Hi Malek!
It depends on the application I guess, for instance if you want to do action recognition from video you can start with the well known:
STIP
https://www.di.ens.fr/~laptev/interestpoints.html
Motion history images
http://web.cse.ohio-state.edu/~jwdavis/CVL/Research/MHI/mhi.html
https://www.youtube.com/watch?v=CfYidtvep7Y
In other types of application though (like content retrieval etc) I have no idea what they are using.
If you specify the application field it might make it easier to get relevant answers.
Best,
Anastasia
Thank you Anastasia for your response. I am interested in political tv shows.
So you would like for instance to detect deception?
One relevant paper I found recently is this:
http://proceedings.spiedigitallibrary.org/proceeding.aspx?articleid=2575928
It might be time consuming, but getting transcriptions of the most relevant interventions would allow you to get a "tag cloud" (automatically) of the terms that each participant used the most to assess who is paying more attention to what.
I'm not sure exactly what you're looking for, but you may be interested in the work of Sam Levine:
http://lav.io/2015/03/c-span-5/
https://vimeo.com/cspanfive
He's using a combination of tools that are open source and linked to on his website.
- Badges
- Science topic
- Similar topics
- Geoscience
- Cartography
- Mapping