5

Forgive me if this is poor-protocol but I am cross-posting from Cross Validated Meta because it was recommended there that this 'feature-request' belongs on this meta. I had done considerable work posing the arguments and I would rather reuse those arguments than start fresh.

I had posted it there because it contains anecdotes and examples that possibly only a statistics educated SE user can appreciate. The feature request portion however had broad application and I agree that it belongs here. Therefore here is the post for your thoughtful consideration.

I've noticed that it is difficult to get questions migrated from SO to CV. I've already read that this doesn't occur often 'in the wild' but as 'Big Data' and 'Analytics' become trendy in the software industry I would not be surprised to see an increasing trend of migration worthy question appearing on SO.

Anecdotally I have found that there is an increasing number of people in Silicon Valley/ Bay Area that did a quick MOOC, or read one of many machine learning/ data mining survey books (k-means/OLS/LogReg/DT/SVM/RF), that only describe the most common machine learning techniques as plug-and-play software tools in R and doesn't leave them with a sense of how much more they ought to learn. For instance I listened to a talk by a chief data scientist at a social gaming company that explained his investigation of a problem as 'trying a bunch of things' and settling on a linear regression fit because the R-Squared 'was good'. I have other anecdotes as well, for example the emerging trend of 'advanced analytics' vs 'analytics' to mean statistical/machine learning techniques because so much of what people call analytics in the software community is just average/max/min (without acknowledging population vs sample) and various elementary mathematical calculations called 'key performance indicators'(KPI).

I'm not sure how I would show that there is an inflation of claims to understand statistical/ machine learning topics given the data we have but I strongly suspect that it is occurring and if this is true, evidence should be mounting somewhere within SO. The challenge is that well-meaning SO moderators may not know how to identify these.

For example I have flagged 4 SO questions as migration candidates to CV with the most recent flag occurring more than a week ago.

  1. One of them, a feature selection, question was rejected because 'declined - a moderator reviewed your flag, but found no evidence to support it' and at the same time one of the close-voters, AGS, has commented on it 'This question appears to be off-topic because it is about machine learning theory / stats, and not programming related'. That looks like it is some evidence.
  2. One flag that has been open for 11 days now is about computing prediction intervals after using cross-validation.
  3. Another 11 day open flag is about hyperparameters in a Gaussian Process.
  4. The first flag of this kind that I have raised was about selecting an anomaly detection model. It wasn't until I demonstrated that it was CV worthy by answering it as one that it was migrated.

To recap, from my extremely limited sample size of 4 flags, the only successful migration was the one that was subsequently demonstrated to be a CV question by providing a CV answer first. I attribute this to the limited experience of SO moderators in CV topics.

As a solution I would propose the idea of a bridge moderator. Where I went to school for my undergraduate there was the concept of a bridge faculty. For instance there is a bridge faculty member for Math/CS and one for Stat/CS and both are able to liaison between their bridge disciplines. At my job which has many full time statisticians and full time software engineers, I act in a similar liaison capacity between Stat/Engineering, though this is a relatively new idea here. Since moderator level reputation may be rare enough in one discipline, let alone two, I would propose that a moderator level reputation on the migrate-to side and some lower threshold reputation on the migration-from side might be sufficient to strike a balance. Perhaps there are better ideas.

I believe that we can certainly continue to demonstrate the migration-worthiness of questions by first answering them but I also believe that it is an inefficient way to crowdsource this problem when cross topic contention will only increase with the increasing portfolio of SE topics. I would ask the community to consider more efficient options.

  • 2
    My first reading of the title was wondering why you needed more moderators in the bridge - aren't there enough there already? But then again, thats probably one where it can't hurt to have some more... – user213963 Jun 19 '14 at 19:14
  • 2
    BTW: if you actually write the word "migrate" in your flags, they stand a better chance of being processed along with other migration requests. That doesn't necessarily mean they'll be migrated though. – Shog9 Jun 19 '14 at 19:49
  • @Shog9 Thanks I'll keep that in mind. – Meadowlark Bradsher Jun 19 '14 at 19:53
6

I understand your reasoning for wanting a "Bridge moderator" but I'm not sure if it is something that we really need. We already have lines of communication between mods on different sites and we can ask them about questions flagged for migration.

The important thing to remember when migrating questions is "We don't migrate crap". If a question is not well-written or doesn't appear to be on-topic for a target site, then we tend to hesitate in migrating it.

As a Stack Overflow mod, I'll speak to your flags that you are bringing attention to.

The first question you flagged, was already closed, downvoted and answered when you raised the flag. Based on the following wording:

suggest me some good Feature Selection technique or the number of features that I'm supposed to consider.

I made the decision that the question seemed too broad for CrossValidated and since it was already closed, the flagged was declined

For Question 2 and Question 3. The flags are in the review queue for the Stack Overflow mods to review. Currently, we have approximately 1.5k+ flags that need to be reviewed by us most of these are custom flags like yours. They tend to take time to research and resolve. Please be patient and we will get to them. If we feel they are good candidates, then we will migrate. If we are unsure, then we will reach out to the CrossValidated mods.

The last question was migrated after we reviewed it.

I'm guessing that most of the mods on SO (including myself) probably don't have experience in stats/CV but as I said we already have a way to communicate with the mods on the other sites. I'm not sure a bridge moderator would necessary help.

We do migrate a lot of questions to CrossValidated, in the last 90 days CrossValidated is in the Top 5 sites that we migrate to and we've only had 5% of the posts rejected. But we don't just blindly migrate questions when they are flagged, we need to make sure the questions are off-topic for Stack Overflow and are on-topic for CrossValidated, unfortunately this takes time.

While CV is in the Top 5 of sites being migrated to, during that 90 day period we only migrated 54 questions which is not many considering the top site had 4 times as many questions being sent over. At this time, this is too few to have a full-time person to manage these migrations.

While CV is still growing, I'd suggest that if you find something that is a good fit for CrossValidated, go to the chat room on stats and engage other users to flag the posts. Or even ask a moderator on CrossValidated to reach out to a Stack Overflow mod to migrate it.

  • 3
    I've found it useful to sometimes point out credentials on the target site so that when a mod does see it they don't think "random 1k rep flagging, move to next one" but rather "someone with 20k rep on the target is asking for this question..." which can sometimes increase the likelihood of a prompt migration... oh, and limericks work better than haikus to get the attention of a mod. – user213963 Jun 19 '14 at 19:17
  • 2
    @MichaelT That is extremely helpful when we are going through flags. One of the first things I do is check to see if the person flagging has any rep on the target site. It is also helpful to see a note in the flag that says "I'm a mod on this site, please move it" - anything helps us in making these decisions. – Taryn Jun 19 '14 at 19:20
  • 1
    Thanks for the direct account of the flag reviewing process. It helps me to understand the context within which these moderation events are occurring since the context is invisible to me. With regard to the first question, I suppose the reject reason may have been automated since it doesn't explain the order of events (closed->flagged->flag-rejected) but offers 'no evidence' instead. Lastly I'm not excited about the prospect of hunting down a CV moderator or high rep CV individual each and every time I see a CV question in SO. I probably will only flag and answer at best. – Meadowlark Bradsher Jun 19 '14 at 19:43
  • 1
    @MeadowlarkBradsher The first one was rejected manually because it was already closed on SO and it seemed too broad for CV. Custom flags don't get processed automatically a moderator always has to review them and make a decision. – Taryn Jun 19 '14 at 19:46
  • 1
    @bluefeet. I only meant by automation that the published reason for rejection was an automated reason code and not a string you typed in manually. That would account for not seeing something like 'already closed' vs. 'no evidence'. – Meadowlark Bradsher Jun 19 '14 at 19:52
  • 1
    @MeadowlarkBradsher Oh, yes that is a standard reason... sorry I missed that. :) – Taryn Jun 19 '14 at 19:53
  • 1
    If CV is a top 5 now, maybe you mods could reconsider this feature request. That would help with the migration process, since we would not need to leave custom flags. (cc/ @MeadowlarkBradsher). – Andre Silva Jun 19 '14 at 22:15
  • @AndreSilva Stats is nowhere near a top 5 migration destination from SO nowadays. – hairboat Jun 19 '14 at 23:54
  • @AbbyT.Miller, tks. Is this the total number of migrations or does it consider the last 90 days? My comment was motivated by the info posted on this answer. – Andre Silva Jun 20 '14 at 0:04
  • @AbbyT.Miller What is the timeframe on those stats? I pulled the Top 5 from the migration stats which is 90 days. – Taryn Jun 20 '14 at 0:30
  • Mine's 120 days, @bluefeet. ...I think. Let me check on that. – hairboat Jun 20 '14 at 4:51
  • 1
    meta.stackoverflow.com/questions/261072/…. Just to connect the follow up of this post. – Andre Silva Jun 20 '14 at 13:23

You must log in to answer this question.

Not the answer you're looking for? Browse other questions tagged .