[ SmokeDetector | MS ] Bad keyword in body, bad keyword in title, blacklisted website in body, link at end of body, pattern-matching website in body, +1 more: How Deos work Junivive Cream? by sklheli on superuser.com
[ SmokeDetector | MS ] URL-only title, blacklisted website in body, blacklisted website in title, link at end of body, pattern-matching website in body, +2 more: risingsupplements.com/alpha-rx/ by ggggg on askubuntu.com
[ SmokeDetector | MS ] URL in title, bad keyword in body, bad keyword in title, blacklisted website in body, blacklisted website in title: fornatgaex.com/anibolx/ by Himmalts on graphicdesign.SE
@Rob yep - but it also has a big donate button and it's still really a bizarre link to put in - unregistered user - today - only post - I consider it spam
[ SmokeDetector | MS ] Bad keyword in body, bad keyword in title, blacklisted website in body, link at end of body, pattern-matching website in body, +1 more: How to take Follicle Rx by folliclerxusa on superuser.com
More or less. weaveinc\.org would be what you intended, as a . matches every character. But this is not a real problem if the rest of the regex is specific enough.
E.g. if we decide to watch http://t.me/ (a link shortener for Telegram), !!/watch t.me would give problems because it will match every post with the words time, tame or tome in it.
@suraj Body - Position 138-141: kys, Position 193-196: kys, Position 521-524: kys, Position 1306-1309: kys, Position 1366-1369: kys, Position 1764-1767: kys, Position 2046-2049: kys, Position 2059-2062: kys, Position 2600-2603: kys, Position 2723-2726: kys
CI on 5406698 succeeded. Message contains 'autopull', pulling...
[ SmokeDetector | MS ] Bad keyword in body, blacklisted website in body, link at end of body, pattern-matching product name in body, pattern-matching website in body: The Best Supplement by Telkonimronita on gaming.SE
[ SmokeDetector | MS ] URL in title, blacklisted website in body, blacklisted website in title, pattern-matching website in body, pattern-matching website in title, +1 more: risingsupplements.com/alpha-rx/ by user249724 on apple.SE
Interesting. I could try and see if I could maybe build a Deep Learning system that works? Maybe using Watson? (ibm.com/watson, requires no coding for the machine learning end)
Is there any public dataset of spam that SmokeDetector provides?
Sure, you're welcome to try. Metasmoke has an API which allows you to read posts, but only those reported by Smokey (or manually by our users). So expect that to be heavily biased towards spam.
You can use the Stack Exchange API to download 'normal' posts which shouldn't be reported.
@TajyMany I'm not sure, I've only used one operation so far. All posts do contain information about whether they are true positives (is_tp) and/or false positives (is_fp).
@TajyMany have you already registered on metasmoke?
I'd like to report this: https://aviation.stackexchange.com/questions/42513/would-a-helicopter-with-the-blades-on-the-bottom-fly-the-same-if-at-all/42531#42531 It seems spam, it does not answer the question.
Actually, I can't give you access to the data explorer right away as it requires a higher level of privilege than I originally thought, but I'm assuming that the DB dump should be adequate anyway?
[ SmokeDetector | MS ] Bad keyword in body, blacklisted website in body, blacklisted website in title, pattern-matching website in body, pattern-matching website in title: gomusclebuilding.com/skin-balance/ by mattiebaker on graphicdesign.SE
!!/test Do you wish to know if your spouse cheating on you? spy on your or your online partner? You guys can contact me on via; Email: hackmandarin@protonmail.com Tel: +1 (747) 231 0271
> Bad keyword with email in body, bad keyword with email in title, pattern-matching email in body, pattern-matching email in title, phone number detected in title ---------- Title - Phone number: 1 747 231 0271 Title - Keyword *cheating* with email hackmandarin@protonmail.com Title - Pattern-matching email hackmandarin@protonmail.com Post - Keyword *cheating* with email hackmandarin@protonmail.com Post - Pattern-matching email hackmandarin@protonmail.com
[ SmokeDetector | MS ] Bad keyword in body, blacklisted website in body, pattern-matching product name in body, pattern-matching website in body, repeated URL at end of long post: gives clearly better apexes by Beent king on graphicdesign.SE
