search

algorithmwatch / 2020-monitoring-instagram-analysis

Data analysis for the Monitoring Instagram project
https://algorithmwatch.org/en/story/instagram-algorithm-nudity/
GNU General Public License v3.0
2 stars 1 forks source link

Controlling for the number of previous likes at the moment of encounter #2

Open Auerlu opened 3 years ago

Auerlu commented 3 years ago

Did you get a chance to control for the number of likes a post had when your donors encountered it? If I understood correctly, you successfully proved that racy/nude posts are displayed more often. However, Facebook and Instagram are known to feature posts with higher interaction rates. Thus this might be a case of a "chicken or egg" problem: If posts showing bare skin are more successful in generating likes/interaction among the users who first encounter the post, said posts will consequently most likely be more heavily featured in other users' newsfeed. Note that the reason for this would then not be that they show bare skin but that they have proven to be more popular/"relevant" to other users so far.

n-kb commented 3 years ago

Many thanks @Auerlu for your comment.

Short answer: No, but our tool (and our code for analysis) now has this feature. We'll take that into account in our upcoming work.

Longer answer: It's only a chicken-and-egg problem if you consider that user preferences are entirely independent of FB. It could be the case that exposure to FB's products changes the behavior of users, which is in part why the absolute numbers are valuable as such, and why any analysis of FB must take into account the sociological and historical background of their automated systems.