Re: [OSM-talk] OSM SPAM detector

Hi Blake, yes,  I messed up something. :( saturday morning i asked my mail provider to fix that problem, but they didn't do anything. it's weekend :( time to change the provider. Regards walter Am 11.03.2018 um 01:33 schrieb Blake Girardot: Hi Walter, No, the subject of this thread

Re: [OSM-talk] OSM SPAM detector

Hi Walter, No, the subject of this thread about spam related to OSM changesets, it has nothing to do with email. Your rejection notice is because it seems OSM's email servers make use of a service that "block lists" other email servers that have an alleged reputation of sending spam. However you

Re: [OSM-talk] OSM SPAM detector

is that the reason for that? This message was created automatically by mail delivery software. A message that you sent could not be delivered to one or more of its recipients. This is a permanent error. The following address(es) failed: tagg...@openstreetmap.org: SMTP error from remote server

Re: [OSM-talk] OSM SPAM detector

Awesome! Great work! On Mar 6, 2018 00:47, "Frederik Ramm" wrote: > Hi, > > On 03/05/2018 07:03 PM, Jason Remillard wrote: > > getting a diverse set of changeset from many people will insure that the > > algorithm is not biased relative to where the consensus is in the > >

Re: [OSM-talk] OSM SPAM detector

Hi, On 03/05/2018 07:03 PM, Jason Remillard wrote: > getting a diverse set of changeset from many people will insure that the > algorithm is not biased relative to where the consensus is in the > project Well strictly speaking it will ensure that the algorithm follows the opinion of those who

Re: [OSM-talk] OSM SPAM detector

It would help to add a comment column to motivate flagging changeset/object content has a spam (SEO marketing description/infos, etc.).   Pierre Le lundi 5 mars 2018 13:05:41 HNE, Jason Remillard a écrit : Hi Dave, The detector needs to be "trained" on

Re: [OSM-talk] OSM SPAM detector

Hi Dave, The detector needs to be "trained" on what a spam changeset looks like versus what a normal changeset looks like. Training really means programming the detector by example. Once we have a good set of example changesets, going forward, it will find them on its own. Rather than having me

Re: [OSM-talk] OSM SPAM detector

Struggling to understand this If users are expected to send you changeset ids, how does it "detect spam"? In what way are users informed of spammy changesets? DaveF On 05/03/2018 14:06, Jason Remillard wrote: Hi, This weekend I put together a SPAM detector for OSM changesets.

Re: [OSM-talk] OSM SPAM detector

most but not all cases: undiscussed imports get reverted and when they get the go ahead they would be marked as spam. Very bad way to train the dataset vs ground truthed spam identification. On Mar 5, 2018 9:50 AM, "Michał Brzozowski" wrote: Could we use something similar

Re: [OSM-talk] OSM SPAM detector

Could we use something similar to detect generic vandalism by training on reverted changesets? Many of them have "this changeset was reverted fully or in part..." comments. Also, analyzing object history or detecting created_by=reverter;JOSM * would give you more examples to train on. *

[OSM-talk] OSM SPAM detector

Hi, This weekend I put together a SPAM detector for OSM changesets. https://github.com/jremillard/osm-changeset-classification You don't need to be a developer to contribute, send over any SPAM'y changesets you come across via a github issue, a pull request, or even an email to me. I just need