'Potential Scam' Detector (moderator/labeler)

What triggered the bot was a couple of posts sent to many accounts in a short span of time.

Your account was reviewed, and the label has been removed.

Basic marketing lingo normally does not trigger the bot.

However, if the message triggers the bot and passes the verification layers, then the system decides whether to label or not.

We work to fine-tune the bot every time we detect false positives happening.

It is not only based on terms, but it also tries to understand the context of the message and has more layers when a message initially triggers the bot.

They don't, since there are no functions on bsky to notify people automatically or send messages through the labeler labeler tools they provide yet. It is a missing feature for sure.

It happened only one time. We have a very low incidence of false positives, but if it occasionally happens you can always appeal, and we will review it.

We are always fine tunning the algorithmn to be more precise and have less false-positives. It is a continous work.

In reality, this is a voluntary project to help make the space safer and cleaner from spammers/scammers, since they use different tactics to steal from people.

There are no costs and there never will be.

We do our best to provide a fast response in case of appeals and review each case.

When you are labeled, you can also click on the label and select "appeal," then it will go straight to the dashboard to be reviewed.

Thanks for reporting it.

The labeler does not have a political view.

The account has been reviewed, and the label has been removed.

The issue was a message that used terms commonly used by scams to create fomo.

Your account has been reviewed, and the label has been removed.

The labeler does not have a political view.

The issue was a message that used terms commonly used by scams to create FOMO.

Your account has been reviewed, and the label has been removed.

Hello,

Just click on the label placed on your account and click "appeal". Then it will be sent to the dashboard for review.

Your account triggered the bot a few times by sending repeated messages in a short span of time.

We have reviewed and removed the label.

The account has triggered the bot by sending repeated text to multiple accounts in a short span of time.

It has been reviewed and removed on our side.

Also, the account is labeled as spam by the Bluesky service.

This account triggered the bot by sending a message multiple times in a short span of time.

The account has been reviewed, and the label has been removed.

This account triggered the bot by sending a message to multiple accounts in a short span of time.

The account has been reviewed, and the label has been removed.

Your account was reviewed, and the label has been removed.

That account triggered the bot on 23/3, by sending a message to multiple accounts in a short span of time.

The account was reviewed and the label was removed.

The label was triggered as a false positive on the first day of implementation of the labeler.

We reviewed and removed the label. Your account should not show it anymore.

If you believe you were mislabeled, please open an appeal for us to review your account and help to solve it.

The spam detector *does not* use AI. It evaluates how fast an account sends messages, or how quickly a message is spread among accounts (mostly bots broadcasting spam).

The scam detector *does* use AI. It evaluates the context of the message and then decides whether to label it or not.

Thanks for pointing that out!

I'll escalate this to the team to review the rules and find a better balance between handling spammers and organic account reposts.

Avoid getting scammed by the animal rescue scam The animal rescue scam starts with an invitation to follow a fake shelter on social media and donate for food and care for dogs in Uganda.

Thanks for sharing @thezoikkeli.bsky.social!

www.animal-kind.org/post/avoid-g...

I reviewed your account and the bot was triggered by a post about NFT, not the post you referred.

But anyway, it was a false positive. Thanks for reporting!

The label was removed already!

Sorry about the false positive. The bot was triggered by a "click here to win" message and wrongly labeled you.

The label has been removed already, and thank you for reporting.

Certainly it does not trigger the spam bot because it is driven only by the volume of the same message being sent (by one or multiple accounts).

Since it happened only once on your account, please report if it happens again, then we can review the case closely.

Unfortunately, yes.

The spam bot detector verifies messages under 2 rules, for quantity and span of time:

- The same message sent to many different accounts
- Multiple accounts posting the same message

When the bot is triggered, it starts monitoring and applies the label after some threshold.

The bot is not politically biased.

It was triggered by the same message being sent to multiple accounts in a short span of time on Jan, 22.

We have reviewed and removed the label.

Hello!

I reviewed each account and removed the labels.

Please consider reporting by clicking on the label and appealing. This method opens a ticket on the dashboard and makes the review process faster.

Thanks for reporting!

Hey, hello!

We reviewed and removed the label :)