Can confirm this. +13 accounts can talk Turkish at least in an understandable way but <13 accounts literally can’t say almost anything in Turkish.
Any accounts under the age of 13 can barely talk in any language(except maybe Spanish) I tried typing Thai letters in roblox on a alt under 13 and they got tagged.
2 Likes
At the same time, in many languages (for example Polish) there’s lots of swear words that don’t get filtered at all. I believe filter would work best if it could somehow detect what language user is talking in and prioritize filtering based on that.
3 Likes
Exactly same for Turkish again. It usually tags normal words but doesn’t tag swear words.
1 Like
Same goes for Dutch. A normal Dutch conversation is not really possible, lots of tagging, except for swearwords, those do get trough.
2 Likes
The biggest reason as to why the filter does not work for other languages really well is because of an issue known as the Scunthorpe Problem. Basically the letters that make up a word the filter sees it as a swear since it does not care about the context. Named because of the fact that word filters would not let you set “Scunthorpe” as your town name (Scunthorpe is a town in England.) More info on this can be found at Wikipedia here: Scunthorpe problem - Wikipedia
1 Like
Roblox’s filter is specifically designed to minimize the impact of this problem. But I’m not really sure that’s what’s causing the issues here; it’s way too prevalent and often impacts messages that don’t even contain anything remotely inappropriate looking.
1 Like
Filtered on 13+ accounts.
I think this is a big problem.
2 Likes
You can also do this with spanish and even bypass some very bad words. Roblox has to fix this filter
1 Like
This is valid for every language, sometimes even English. This gets a lot worse if you try talking in a different language than the one chosen in your settings.
1 Like
This issue can be solved with NLP RNNs. These networks can semantically classify and even translate sentences. I’ve seen datasets that have classifications of toxic tweets and such, if not Roblox can make their own dataset because they basically have millions of players chatting at the same time = unlimited data. This also means the network can be trained on incorrect classifications reported by users and be perfected over time. Furthermore, it is possible for Roblox to exploit this and find suspicious players by classifying messages and analysing patterns and frequency.
1 Like
Roblox uses a service called CommunitySift which works as you describe but they would rather have players frustrated rather than having something slip through followed by bad press. It could definitely stand to use some improvement though.
2 Likes
As a Russian speaker, I have noticed that the Carilic Alphabets that languages like Serbian, Bulgarian, Ukranian and Russian use is often filtered whilst offensive words in these languages can be let through the filter.
An example is: блать
In latinised form, it is blyat, which is the f word in russian,
It is filtered when blyat is said, but not when блать is.
But a lot of other words in carilic languages get filtered, possibly because it is carilic? I don’t know.
1 Like
A lot of people use cyrillic to bypass when trying to swear on Roblox. I wouldn’t be surprised if Roblox blocked it just because of this.
1 Like
But to be honest, detecting a language, translating it to english and then checking for bypasses would be a far better method than filtering half of a language.
I am not aware with Google’s translate’s API, but I am certain that it can easily be connected to Roblox.
Of course not all translations are accurate, but it would be a far better method than just blocking anything that looks like an english offensive word.
1 Like
There are many cases on where translating something harmless on one language through a translator becomes an extremely harsh slur, automatic translation is definitely not a good idea.
3 Likes
Are you just using google translate in the screenshots you showed?
1 Like
Yes, it would not be the best solution, but it would be a better filtering method that Roblox has.
Although if an english offensive word is detected as another language and translated into a ‘friendly’ word that lets it through the filter, that may cause some issues.
1 Like
Even whilst not trying to bypass, simple things like this happen:
Что вы делатри эта лета? → Chto vi dyelatri eta leta? → what are you doing this summer?
And the filtered part of this is just ‘Что вы’ or ‘what you(formal)’.
Whilst other offensive russian words like p*z**ts or in english: c**t do not get filtered at all.
Roblox has to get their filter to actually filter slavic languages like Russian, Ukrainian, Serbian and Polish correctly.
Possibly because it is how the slavic languages work that make it seem like a bypass? I don’t know.
I also can partially speak German and I tested out speaking every-day german words and the filter was more accurate.
It seems to be that turkic and slavic languages are effected the most.
2 Likes
So the solution is the filter understanding those languages better, not arbitrarily translating the text to English and checking for profanity. (I’m also able to use some profane language in Catalan that isn’t translated at all to English)
Currently, the female form of dog in Spanish (perra) translates to something more extreme in English…
3 Likes