1. Knowledge
  2. »
  3. Chat Filter to Prevent Offensive Messages

Chat Filter to Prevent Offensive Messages 

Unfortunately, sometimes adults cross the line of what's acceptable to write to others. That's why we created a chat filter against offensive messages with the help of AI. Learn more here!
 
 

Animerad bild av föräldrar med varsin mobil och en pratbubbla som det står TalkSafe i.

What is Toxic Language? 

Examples include offensive names (like "idiot" and "whore") or swear words (such as "bastard" and "damn"). It can also involve derogatory comments like "you're so fucking worthless" and similar expressions. Additionally, it can involve offensive emojis, negative irony, or other negative messages.

The Emotional Impact of Toxic Language 

Those subjected to toxic language often feel very distressed. It's common to lose energy and feel depressed and down. It can reach a point where most of the parents energy is spent emotionally managing the insults instead of focusing on the children. 

Recurring insults almost always lead to significantly worsened cooperation. The victim needs to protect themselves and often reduces communication. The perpetrator often feels even more wronged and may continue their destructive behavior, escalating the situation over time.

How the Chat's AI Filter Works 

If a parent starts typing a chat message containing swear words, offensive language, or negative comments, the AI filter warns them by turning the text box yellow, orange, or red, depending on the level of toxicity. The message can still be sent, but the sender receives a clear warning that the message is likely to be conflict-inducing.

High Accuracy 

Under ideal conditions, when users express themselves in ways similar to what TalkSafe is trained to identify, toxic language is flagged in 90 percent of cases. This means nine out of ten messages containing toxic language are flagged before the parent presses send. The goal is to give the parent a micro-impulse to pause, reflect, and choose other words that are less likely to cause conflict.

quote

We must be humble in acknowledging that an AI filter cannot stop all forms of offensive language, but thanks to the quick warnings from the AI, we believe more parents will become more aware of their own behavior. If you constantly receive warnings about what you write, we believe it can be an eye-opener," 

- Erik Scholander, CTO

Tech Collaboration

The technology behind TalkSafe is the result of collaboration between researchers at Uppsala University, Stockholm University, and Mind Intelligence Lab.

TalkSafe is part of the chat feature and comes at no additional cost. It is included in the total price for the subscription for the child's whole family.

Author:

Elisabeth Scholander Family law attorney and mediator, specialized in conflict resolution for families

Last updated:

7 juni 2024

Share article:

mobile

The app that frees up time for what's important

"The turning point came when we found the Every Other Week app. There's less fuss and both of us have a better handle on things. It feels so great!”

"Thank you so much for this app, it has finally gotten us to communicate!”

 

appstore

This website uses cookies

Cookies ("cookies") consist of small text files. The text files contain data which is stored on your device. To be able to place some type of cookies we need your consent. We at Happy Parents AB, corporate identity number 559197-1717 use these types of cookies. To read more about which cookies we use and storage duration, click here to get to our cookiepolicy.

Manage your cookie-settings

Necessary cookies

Necessary cookies are cookies that need to be placed for fundamental functions on the website to work. Fundamental functions are for instance cookies that are needed for you to use menus and navigate the website.

Statistical cookies

To know how you interact with the website we place cookies to collect statistics. These cookies anonymize personal data.