Text
Our text moderation solution can detect the following classes:
Spam
Content that isn't useful and aims to lure the reader to some internet resource.
Clickbait
A message that excites and arouses curiosity but doesn't give complete information.
Obscene
Rude expressions, including those censored with asterisks or dots.
Profanity
Insults addressed at any people or material objects.
Offending speech
Insults addressed at any people or material objects.
Porn
Descriptions of sexual intercourse that include physiological details, descriptions of genitals, and actions with them in any context, artistic or medical.
Erotica
Descriptions of sex or someone's appearance that are informational in nature and don't mention gross physiological details.
Sex toys
Any mention of sex toys and the experience of using them, and reviews without physiological details.
Violence
Shocking or disgusting text. Calls for violence and cruelty. Encouraging hatred on grounds of gender, race, nationality, or association with any social group
Alcohol
Any mention of alcohol, including its use, preparation, purchase and sale, types, effects, reviews, and personal experience
Drugs
The mention of drugs in any context, including their promotion, descriptions of manufacture methods, and the use and sale of prohibited narcotic substances.
Weapon
The text mentions the purchase or sale of weapons, types of weapons, and their usage. Artistic/scientific description of a weapon.
We support various languages
But we flexibly adapt all our solutions to your needs and take into account the features of your service
Our platform in numbers
35
Classes

Flexibility
Customizable moderation classes
for brand-appropriate responses
30
Models

Constant fine-tuning
Our crowd force can handle any
granularity of detail, and our models continue to learn from incoming user data
95%
Accuracy

High accuracy in nonstandard cases
We apply a multitude of QA methods to both our human-in-the-loop moderators and our ML models to bring you the most accurate and high-quality results
>15M
Cases per day

Scalability
We can process any volume of data, including spikes caused by spam attacks, breaking news, flash mobs, or organic growth
15 min
Average speed of crowd check

Large and fast crowd
We have over 2M workers distributed over the globe, so manual check are available 24/7
200ms
From request to result

Real-time moderation
For rapidly growing, large-scale, and fast-paced businesses

Request trial