There is problem with spam questions that cause real questions to take long time to be approved. Could someone look into possibility of moderation of questions with machine learning algorithms? Most clear spam could be deleted straight away and not so clear could be left to moderators.
This would solve problem of slow approval time. Ideally it would be 1 hour.
I expected to get approval same day but I had to ask same question in chat next day and then someone was very helpful and did moderation of my question.
A quick googling for "bayesian spam filter ruby" brought up some interesting possibilities.
This article (http://rurounijones.github.io/blog/2014/08/11/bayesian-filter-performance-in-ruby/) is probably a good place to start, and he even has the Ruby code up on GitHub to start from.
https://github.com/rurounijones/dont_bayes_me_bro
Since the performance that PublicLab would need would probably be a lot less than 1000 submissions/second, it's probably a great place to start. Also, the existing database of comments, questions, and articles would be a good starting point for training the filter.
Reply to this comment...
Log in to comment
This was also auto-posted over at https://github.com/publiclab/plots2/issues/3009 -- thank you!
Reply to this comment...
Log in to comment
Is this a question? Click here to post it to the Questions page.
Reply to this comment...
Log in to comment