There is a possibility of showing suggested tags after the body of a question is filled in. These suggestions are based on the body of the question. More details can be found in these posts:

I will quote part of one of the answers, which gives a reasonable summary.

  1. It uses similar-to-Bayesian reasoning on the text from the title and body of a post
  2. It has been trained on older questions
  3. A minimum of around 20k questions are required for accurate results
  4. There is no substitute for material to learn from, so it can't be rolled out to all sites

If I understand this correctly, this feature is used on Stack Overflow.1 (In one of the post you can see also a screenshot.) But it can be added to any site which has sufficiently many old questions for training the algorithm. (Ideally, most of the questions should be correctly tagged.)

Still, it seems that some non-trivial work is involved when such a feature is added to a site.

Question. Do you think feature like would be useful on Mathematics Stack Exchange? Should we request Stack Exchange staff to add the feature also to our site?

1 Based on the comments on one of the linked posts it seems that this was implemented on SO at some point in 2013. I am not really sure whether this feature is implemented also on some other sites.)

  • 1
    $\begingroup$ I have asked a similar question also on Meta Mathoverflow: Should MathOverflow request suggested tags feature? If you think that it would be better to ask this here later, I might delete the question here and repost it later. (To me it seemed more logical to ask it on both sites at the same time - it is basically the same topic and there is some overlap between userbases.) $\endgroup$ Commented Mar 15, 2018 at 9:13
  • 1
    $\begingroup$ Still if several users think it is better to wait and see first how the discussion on MO goes and whether some useful insights could be gained from the discussion there - we might postpone the discussion on this site for later. (This feature can be by no means considered urgent.) $\endgroup$ Commented Mar 15, 2018 at 9:14
  • 1
    $\begingroup$ I think this can be interesting here. But I would like to know what the suggested tags are at first. Namely, I want to be able to test this algorithm before we unleash it on the unsuspecting newcomers. $\endgroup$
    – Asaf Karagila Mod
    Commented Mar 15, 2018 at 9:18
  • 6
    $\begingroup$ If that algorithm can be trained to be more intelligent than our noobs (who often pick tags containing familiar sounding words), then this would be GREAT! $\endgroup$ Commented Mar 15, 2018 at 10:06
  • $\begingroup$ Since on SO this feature is available since 2013, maybe we could find out whether it works there well enough. Although I am not sure where and whom to ask. (Of course, even if there is satisfaction with the suggestions on another site, there is no guarantee that it will be the same here. But experience from sites which already have this feature is probably the only data point we have at the moment.) $\endgroup$ Commented Mar 15, 2018 at 10:11
  • 3
    $\begingroup$ @Jyrki: So you want to tell me that not every question involving sets is set theory? Poppycock! $\endgroup$
    – Asaf Karagila Mod
    Commented Mar 15, 2018 at 14:10
  • $\begingroup$ @AsafKaragila I guess that must be frustrating to you, since I'm guessing you are focussing on set theory questions. $\endgroup$
    – user370967
    Commented Mar 23, 2018 at 17:51


You must log in to answer this question.

Browse other questions tagged .