Return to Revisions

For few recent months, I've got a habit of downvoting answers which quality doesn't look OK to me.

https://i.sstatic.net/HlC8e.png

These probably can be generally described as low effort and/or these lacking relevance to question asked.

• ^{Opinionated slogans, claims that are not backed up by appropriate references or by compelling presentation of personal experience, posts that appear to ignore prior answers covering same grounds, stuff like that...}

As far as I can tell, many (probably most) of my downvotes go to answers in "hot questions".

While I downvote maybe one of the answers to 5-10 "regular" questions, I noticed that almost every question with views over 2K brings answers that look bad to me.

"Hot garbage waves" in the answers appear to happen once or twice a week on average, frequent enough to feel the connection between these and respective questions making their way into SE collider list.

Is that something to worry about?

My particular concern is the poisonous effect these mis-answers have on questions, making interesting and well presented problems look the same as non-constructive popularity contests.

• _{"Oh look: 'my guess is fairly prosaic. Git is brilliant...' - with upvoted answer like that it can't be a real question".}

What is especially depressing is that regular ways to deal with this kind of issues just don't work. It's typically not difficult to edit the question to repel garbage answers, I can easily name a handful of active regulars who can and do just that.

Thing is though, it takes some time to figure how to clean up ambiguous wording while preserving the essence of original. In regular questions this works like a charm, but when editing a hot one, I often find out that when I'm done with edit, someone already posted an answer that invalidates my edit. And answer that exploits another minor ambiguity. And yet another, and so on, until my brain explodes!

• ^{It feels like all one gets is just like 60 seconds to figure protective edit to cover every word and letter in the question that could possibly be misinterpreted by some random passer-by and exploited for their senseless cheap shots. That's just... impossible. And more, it feels quite unfair to over-police text of such questions: per my observations "hotness algorithm" have been smart enough to pick questions that have reasonably good wording as-is.}

The way how things work now helps to attract new contributors but I would appreciate if achieving this important goal ^{1, 2, 3} would somehow be less damaging for good, highly visible questions.

protect your own users from scale ...human interaction, many to many interaction, doesn't blow up like a balloon... (A Group Is Its Own Worst Enemy )

Here are some additional observations based on discussions that followed posting this question.

• Low quality answers in hot questions likely contribute to the fact that currently, it is hard for users to understand site standards, which results in posting many "bad" questions.

^{Taking into account that these are highly visible posts, with thousands of views, it is pretty possible for them to be a steady source of misguided contributors... There are... broken windows... "why can't I post X when Y exists".}

• Until recently, low quality answers also threated to penalize contributors who post good ones because when piled on in hot questions, garbage answers trigger CW which consequently turns all the upvotes given to good answers into zero reputation for their authors.

more than 1700 answers scored 25+ turned community wiki

For the sake of precision, note that number 1700 above is only indicative since search does not exclude answers turned CW for other reasons. Also note some of the answers could be high-voted "unfairly": per analysis 10+ voted answers in sampled questions (below), this could happen, although rather infrequently.

##Background research

For a little data to back up what was written above, I quickly went through few sampled questions with more than 10K views asked for last half year.

Please bear in mind that below list only partially represents the issue: it would be hard to do similar walkthrough for questions with over 2K views since these appear about 10x more frequently.

• http://programmers.stackexchange.com/questions/156722/how-does-learning-assembly-aid-in-programming
  20 answers total, I'd downvote about 7-8
  _{Of 5 answers scored 10 or above, 3-4 look OK to me.}

• http://programmers.stackexchange.com/questions/158640/why-cant-the-it-industry-deliver-large-faultless-projects-quickly-as-in-other
  protected, 27 answers, I'd downvote about 12-13
  _{Of 7 answers scored 10 or above, all look OK to me.}

• http://programmers.stackexchange.com/questions/159637/what-is-the-mars-curiosity-rovers-software-built-in
  protected, 2 answers, all look OK
  _{Both answers are scored above 10 (way above:).}

• http://programmers.stackexchange.com/questions/159813/do-i-need-to-use-an-interface-when-only-one-class-will-ever-implement-it
  13 answers, I'd downvote about 6-8
  _{Of 4 answers scored 10 or above, 3-4 look OK to me.}

• http://programmers.stackexchange.com/questions/161794/is-it-a-good-idea-to-design-an-architecture-thinking-that-the-user-interface-cla
  17 answers, I'd downvote about 8-9
  _{Of 5 answers scored 10 or above, 3-4 look OK to me.}

• http://programmers.stackexchange.com/questions/162643/why-is-clean-code-suggesting-avoiding-protected-variables
  12 answers, I'd downvote about 6-7
  _{Of 3 answers scored 10 or above, all look OK to me.}

• http://programmers.stackexchange.com/questions/163185/torvalds-quote-about-good-programmer
  17 answers, I'd downvote about 7-8
  _{Of 5 answers scored 10 or above, 3-4 look OK to me.}

• http://programmers.stackexchange.com/questions/165380/how-can-i-really-master-a-programming-language
  protected, 14 answers, I'd downvote about 8-9
  _{Of 3 answers scored 10 or above, 2-3 look OK to me.}

• http://programmers.stackexchange.com/questions/167305/what-functionality-does-dynamic-typing-allow
  protected by mod notice, 16 answers, I'd downvote about 8-9
  _{Of 4 answers scored 10 or above, all look OK to me.}

• http://programmers.stackexchange.com/questions/168751/is-the-use-of-utf8-preferable-to-utf8-true
  protected, 3 answers, I'd downvote 2 (especially the one where author didn't even bother to format their code, <meta charset="URF-8">)
  _{The only answer scored above 10 is one that looks OK to me.}

• http://programmers.stackexchange.com/questions/173441/what-triggered-the-popularity-of-lambda-functions-in-modern-mainstream-programmi
  12 answers, I'd downvote 2-4
  _{Of 5 answers scored 10 or above, all look OK to me.}

• http://programmers.stackexchange.com/questions/176113/does-having-a-higher-paid-technical-job-mean-you-do-not-get-to-code-any-more
  protected, 4 answers, I'd downvote 1-2
  _{There's only one answer scored 10 or above; it looks OK to me.}

• http://programmers.stackexchange.com/questions/176582/is-there-an-excuse-for-short-variable-names
  protected, 16 answers, I'd downvote about 8-9
  _{Of 4 answers scored 10 or above, all look OK to me.}

• http://programmers.stackexchange.com/questions/177875/why-is-the-sudden-increase-in-number-of-git-submitters-on-debian-popcon-graph-in
  protected, 11 answers, I'd downvote about 6-7
  _{Of 4 answers scored 10 or above, 2 look OK to me.}

• http://programmers.stackexchange.com/questions/180948/why-arent-user-defined-operators-more-common
  12 answers, I'd downvote about 4-6
  _{Of 5 answers scored 10 or above, 4 look OK to me.}

For the sake of completeness, note that besides 199 answers reviewed above, there are also 19 answers deleted in 16 questions listed above. These answers are visible only to moderators and to users with sufficient privileges. Of these 19, 9 are deleted by moderators, the rest has been deleted by owners. Of 10 answers deleted by owners, I would downvote 7-8.

URL used to get above questions is:
http://programmers.stackexchange.com/search?tab=newest&q=views%3a10000%20closed%3a0

_{Note I wrote "I'd downvote" above since I did not really do that to all the answers I checked because of voting limits.}

Summing up, I would downvote about 101-118 of 218 answers I reviewed per above research.

###update

Some data related to recently added observations on community wiki status.

• Questions with 2K+ views - about 25% are CW, 307 of total 1247

• Questions with 10K+ views - about 60% are CW, 62 of total 101

Quoting self, wow. Just... wow.