Is SPAM harmful in WL forums ?

There have been *suggestive sexual implicit pictures* on the **OFF-TOPIC** forums those last days. Now, I see threads spam by *FAKE* Irony.

What measures can be taken to reduce spam ? Do Forum Users do not report enough ?


Link Guides to Internet Behavior Re-Orientation :



http://www.wisekids.org.uk/collaboration.htm

http://www.albion.com/netiquette/

USENET ETIQUETTE

http://www.ptd.net/help-desk/general/internet-etiquette

http://www.dmoz.org/Computers/Internet/Etiquette/

https://www.uttyler.edu/online/files/netiquette.pdf

http://www.udel.edu/interlit/chapter5.html

https://tools.ietf.org/html/rfc1855

https://www.cs.indiana.edu/docproject/zen/zen-1.0_6.html

http://linux.sgms-centre.com/misc/netiquette.php

http://www.imagescape.com/helpweb/news/newsnet.html


http://www.computerhope.com/jargon/e/etiquett.htm

Greatest site on technology AND Computer


https://support.microsoft.com/en-us/kb/178294

https://support.microsoft.com/en-us/kb/178294


-----------------------------------------------

Some gaming sites also have clear etiquette rules like Kongregate.


Links are : articles, guides, university sites, awereness, encyclopedias (links/topics on etiquette)...

Is there any Warlight WIKI section for etiquette ? It seems important.

I will format main post for netiquette links/guides/discussion/tutorials/quizzes/games...



Fizzer needs a bot. I can make one in javascript even if I am the worst programmer. :(

Or find one. Some large sites use FREE solutions OPEN source to moderate behavior on forums with bots.


Setting up a forbidden world list would solve cursing.

As for image, there are many tools. I really believe there is a free solution.

You can by example:
- use google image reverse search
- Find "the original"
- Look at tags/description from site
- If image description is porn => BAN


Also : https://news.ycombinator.com/item?id=6559071. Some solutions are described.

I have developed an algorithm to detect such images, based on several articles published by research teams all over the world (it's incredible to see how many teams have tried to solve this problem!).
I found out that no single technique works great. If you want an efficient algorithm, you probably have to blend different ideas and compute a "nudity score" for each image. That's at least what I do.
I'd be happy to discuss how it works. Here are a few techniques used:
- color recognition (as discussed in other comments)
- haar-wavelets to detect specific shapes (that's what Facebook and others use to detect faces for example)
- texture recognition (skin and wood may have the same colors but not the same texture)
- shape/contour recognition (machine learning of course)
- matching with a growing database of NSFW images
The algorithm is open for test here: http://sightengine.com It works OK right now but once version 2 is out it should really be great.

Google is in theory crowdsource. You can suggest description for images and bot learns. All images receive some kind of description when bot indexes them. Description is stored in Google Servers. This is how you can search for images by words.





Note : I am lazy *internet* navigator/searcher/investigator. Search skills nul. This is why it is not organized.


----------------------------------------

https://market.mashape.com/explore

Mashape is a really good site to find all kind of librairies.


Free *nudity* bot detector : http://www.patrick-wied.at/static/nudejs/

Edited 10/1/2015 23:34:41

Noone's going to read this because noone playing Warlight is on kindergarten.

<---- Middle school student interested in programming a forbidden word list :)