Detect hate speech, slurs and profanity in iMessage
Pick up on discriminatory language, slurs, or rhetoric that suggests conversations are headed in a dangerous direction.
Joey keeps an ear out for hateful or radicalizing language, not to censor kids but to help families address biases, self-harm talk, or outright calls to violence.
Get Joey Smart AlertsWhat this alert monitors
- Surfaces patterns of profanity, slurs, or degrading language that intensify over time.
- Highlights tone shifts toward threats or self-harm language so you can respond early.
- Signals what matters without requiring you to read every message.
Profanity detection for kids messages
Profanity detection for kids messages helps you spot when chats include slurs, degrading language, or aggressive rhetoric that can harm a child or normalize hate.
Parent note
This was the first Alert I used as a parent to open a conversation with my son. The talk didnt go so well, but the second attempt about use of language, reading you audience, nuance of language, and thinking about how our use of language represents us. Since then, we are so proud of our son and how he communicates now.
Joey looks for language patterns and changes in tone so you can coach, not spy. No spyware. No keylogging. Signals, not surveillance.
Use the alert as a prompt to ask what happened, how it felt, and what a safer response looks like.
Examples of language this alert can surface
- Slurs or hateful terms aimed at identity groups
- Repeated put-downs or demeaning nicknames
- Self-harm or “you should hurt yourself” language
- "You are disgusting / nobody likes you" type insults
- Aggressive threats or intimidation
- "We should jump him" or similar violence phrasing
- Dog piling language that targets one person
- Escalating rhetoric after a conflict or break-up
Joey in action: what this alert looks like
Alerts dashboard summary
Joey's Alerts dashboards listing all Red and Yellow flags for parents to review by Alert category.
Critical alerts example
From the Kezza data set, we have real world messages in this data set that shows the type of alerts Parents can expect when using Joey to keep their kids safe online - signals so you can step in early.
Coaching next steps
Every family conversation is different. Treat these ideas as starting points and add your own context, values, and tone.
FAQ: profanity and hate speech alerts
What is profanity detection for kids messages?
It flags patterns of risky or harmful language in chats so you can step in early. You get enough context to coach without reading every message.
Is this the same as hate speech detection for child safety?
They overlap, but hate speech detection for child safety focuses on targeted slurs or dehumanizing language. Profanity detection is broader, and both help you protect your child.
Will Joey read every message?
No. Joey surfaces signals and summaries instead of full transcripts. It does not use spyware or keylogging.
Keep exploring
See all Smart Alert categories
Each alert has its own landing page with context, scripts, and screenshots. Head back to the Smart Alerts overview to browse every category at once.