In Search of Gender Analysis Tool for Television
October 8, 2017 2:01 PM
I'm looking for some kind of tracking/analysis tool to be used as a way to track gender in television. How many times does which gender propose any idea, bust down a door, solve a case, get threatened with violence, etc. I'd like to not have to reinvent the wheel, and I'm assuming someone somewhere has down this based on articles and studies I've read (but regrettably not bookmarked for their footnotes).
I watch and rewatch a particular television show, and I'm interested in the topic, and I have my own opinions, so I figure if I'm going to watch it anyway, why not take the time to do an actual analysis? Yes, I'm a geek.
Any thoughts? Google is not my friend thus far. If nothing surfaces here, I will indeed go to my local library and possibly university, so those can be excluded as suggestions. Thank you!
I watch and rewatch a particular television show, and I'm interested in the topic, and I have my own opinions, so I figure if I'm going to watch it anyway, why not take the time to do an actual analysis? Yes, I'm a geek.
Any thoughts? Google is not my friend thus far. If nothing surfaces here, I will indeed go to my local library and possibly university, so those can be excluded as suggestions. Thank you!
Sounds like you might want to do your own research, but the Geena Davis Institute on Gender and Media might have some good resources and research.
https://seejane.org
posted by forkisbetter at 2:51 PM on October 8, 2017
https://seejane.org
posted by forkisbetter at 2:51 PM on October 8, 2017
Geena Davis started an organization to strengthen the portrayal of women in media. Her See Jane site has a research and resources page.
That page led me to this recent report from the Center for the Study of Women in Television and Film at UCSD.
The paper summarizes counts of things you are interested in, but does not describe methodology for counting. The director's email is at the end of the paper.
It would be cool to train an AI to do this tagging. It may still be manual. If I had more time, I'd volunteer.
Good luck with your project!
posted by rw at 2:55 PM on October 8, 2017
That page led me to this recent report from the Center for the Study of Women in Television and Film at UCSD.
The paper summarizes counts of things you are interested in, but does not describe methodology for counting. The director's email is at the end of the paper.
It would be cool to train an AI to do this tagging. It may still be manual. If I had more time, I'd volunteer.
Good luck with your project!
posted by rw at 2:55 PM on October 8, 2017
Microsoft has a computer vision API for recognizing things in video.
https://azure.microsoft.com/en-us/services/cognitive-services/computer-vision/
Kairos attempts to determine age/gender/etc from video feeds.
https://www.kairos.com
posted by endquote at 6:55 PM on October 8, 2017
https://azure.microsoft.com/en-us/services/cognitive-services/computer-vision/
Kairos attempts to determine age/gender/etc from video feeds.
https://www.kairos.com
posted by endquote at 6:55 PM on October 8, 2017
Dang, I thought I'd be a hero by suggesting Geena Davis. It's good to know that her work is getting recognized.
posted by jennstra at 7:36 PM on October 8, 2017
posted by jennstra at 7:36 PM on October 8, 2017
« Older What paper weekly planner meets my qualifications? | How can I change this very short butch haircut? Newer »
This thread is closed to new comments.
"ANVIL is a free video annotation tool, developed by Michael Kipp. It offers multi-layered annotation based on a user-defined coding scheme. During coding the user can see color-coded elements on multiple tracks in time-alignment. Some special features are cross-level links, non-temporal objects, timepoint tracks, coding agreement analysis, 3D viewing of motion capture data and a project tool for managing whole corpora of annotation files."
Pretty sure that could be used encode as you watch, and record how many times a man bursts through a door vs. a woman, and then let you compare one episode to another, or to a different show, etc. This may be overkill, YMMV.
posted by SaltySalticid at 2:21 PM on October 8, 2017