Question: Moderate questions with machine learning.

Aleksi12358 asked on July 08, 2018 17:58
54 | 1 answers | shortlink


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.




spam machine learning

question:website



2 Comments

This was also auto-posted over at https://github.com/publiclab/plots2/issues/3009 -- thank you!


This was auto-posted over at https://github.com/publiclab/plots2/issues/3009 -- thank you!

On Sun, Jul 8, 2018 at 1:54 PM \<notifications@publiclab.org> wrote:

Public Lab contributor Aleksi12358 just posted a new research note entitled ' Moderate questions with machine learning.':

Read and respond to the post here: https://publiclab.org/notes/Aleksi12358/07-08-2018/moderate-questions-with-machine-learning


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.



You received this email because you are subscribed to some or all of the following tags: .

To change your preferences, please visit https://publiclab.org/subscriptions.

Report spam and abuse to: moderators@publiclab.org

Check out the blog at https://publiclab.org/blog | Love our work? Become a Public Lab Sustaining Member today at https://publiclab.org/donate

Is this a question? Click here to post it to the Questions page.


Log in to comment

1 Answers

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.


Log in to comment

Sign up or Login to post an answer to this question.