![adult chatbot adult chatbot](https://drudesk.com/sites/default/files/inline-images/Chatbots-for-business.jpg)
Mitsuku: Your face would make an onion cry. If anyone was being genuinely mean, her sarcastic replies often shocked them and many suddenly started being friendlier towards her: People enjoyed being abusive for fun to see her responses and most of them meant no harm. They could only see five of the responses before being banned.Īfter careful consideration, I decided to remove the banning system, as the number of visitors to started to fall, which also took a hit to my advertising revenue. Interestingly though, the banning system had an unusual side effect in that people were contacting me saying that they enjoyed seeing Mitsuku’s replies to their insults and regretted that they couldn’t talk to her any more. There were a few false positives where people had said innocent things and Mitsuku had classed them as insults but a bit of fine tuning easily corrected these. I was happy for her to insult them and be mean but I didn’t want her to use adult language, as a lot of schools and young people talk to her.Īfter I had implemented this system, I soon saw lots of people being banned and the quality of the chatlogs increased dramatically. However, one thing that was important to me was for Mitsuku not to swear at the user. Mitsuku gives a warning, produces a suitable reply and then classes them as an abusive user: Below is an example if someone says, “Let us f**k”. So instead of keywords, I decided to use a case by case method where I added a call to another category I created called ADDINSULT each time I saw an abusive message in Mitsuku’s chatlogs. I don’t want to warn the second user, as his question was innocent. (abusive) Second User: What sex are you? (genuine) For example, let’s take one of the most popular abusive keyword that Mitsuku receives (sex):įirst User: I want to have sex with you.
![adult chatbot adult chatbot](https://www.weston.ac.uk/sites/default/files/styles/letterbox_style/public/2020-11/Screenshot%202020-11-20%20at%2013.50.30.png)
However, this approach is flawed, as some of the keywords can be used quite innocently. The obvious answer was to check the input against a list of keywords. One of the issues I faced when setting up this system was what I should class as an abusive message. If someone abuses Mitsuku, they are warned five times with a siren before given a ban for a few days, which is hopefully enough time for them to cool down a little. None of this is of any use to me when improving her and so I decided to create a “5 strikes and you’re out” method of banning the unwanted users. Mitsuku’s warning system - 5 strikes and you’re out!Ībusive messages, swearing and sex talk account for around 30% of the input received by Mitsuku.