I don’t want my users to abuse my virtual postcards creation app, filling the form with words that are not allowed (mostly bad words). I already developed a system that can identify separate words from a phrase and compare them to an array of censored words and give me a TRUE or FALSE state that I can use to program the app response. But what if someone tries to write 1 single word that is a combination of 2 bad words (or 1 normal word and a bad word)? I can’t figure out how to “extract” the bad word from that invented word that combines the text. Here is an example: Let’s say that I don’t want anyone to use the word “BLUE”. If someone writes “You BLUE man” in the text input, I can detect it with my system. But if someone writes “combiningBLUEhere” I can’t. Any suggestions? Thanks in advance!

After trying different approaches, I am convinced that the best one is using OpenAI to do the job. It’s very easy to setup and with the right prompt it can do everything. My App is in 3 languages and I’m being able to filter any bad word from all the 3 languages with just this one setting. The previous approach was almost impossible. Very time consuming and it was only able to find isolated words from a giant list, that was not enough to prevent all the possible combinations in 3 languages. For now, I will leave it to OpenAI. :raised_hands:t2:

Take a look at this thread here. It worked for me. [image] Flag inappropriate words Ask for Help I used p1 to point to my text column. However, it removes all spaces from the sentance as well as the non-alpha chars. Thus if I split that using a space, it just does individual letters

Thanks Joe for that! If I understood that correctly, it is still a way to detect separate words. But I think it wont work if the “bad word” is part of a larger single word. Like, if “Blue” was a bad word in the list, this system would detect BLUE but not BLUEMAN. Maybe I can try something with the OpenAI integration. A bad words detector prompt that returns TRUE or FALSE… Other suggestions will be very welcome!

This has two sides to it though. I think there will be cases where you want to ban BLUEabc but not DefBLUE.

If I was going to do this, then I think I would definitely turn to OpenAI. But don’t just look for words, because blindly filtering keywords will never work and is easy to get around. Words on their own are not inherently good or bad. It’s the way that they are used and how they are combined that can cause offence. So ask the AI to do a bit of sentiment analysis and pick out phrases that could be considered offensive or harmful. I think what I would do is flag for moderation, rather than just rejecting outright. But that’s up to you of course.

Agreed. OpenAI is a very straightforward option.

Best approach to censor bad words in form input

Ask for Help

Joe_Gabriele June 4, 2023, 11:13pm 2

Take a look at this thread here. It worked for me.

Topic		Replies	Views
Filter innapropriate username / comment Ask for Help	1	146	April 21, 2024
Flag inappropriate words Ask for Help	8	377	April 12, 2023
Prevent certain words from being used Ask for Help	7	434	March 26, 2022
Prohibit profanity in usernames Ask for Help	5	307	June 2, 2024
🆕 Text Sentiment Plugin Ask for Help	5	470	October 24, 2021

Best approach to censor bad words in form input

Related topics