This guide is for the moderation we provide on the Essential plan. For advanced moderation and more customization options, check out our Reputation+ and Engage+ plans.
🔍 How Our AI-Powered Moderation Works
Our system identifies and hides unwanted, harmful, or off-brand comments to protect your brand’s reputation automatically.
Below are the moderation categories we use in the Essential Plan and what they include.
Moderation Categories
Spam
Used to block irrelevant or deceptive content, including:
Gibberish or random strings
Unrelated product/service offers
Donation requests or mass messages
Religious proselytizing
Financial spam and unrealistic promises
Clickbait (especially sexual), catfishing
External links unrelated to the brand
Clout-chasing (“follow me,” “sub to my channel,” etc.)
Sharing personal identifiable information (PII)
Offensive
Targets comments meant to attack, provoke, discriminate, or shock others:
Hate speech, slurs, or targeted insults
Discriminatory language
Aggressive or inflammatory remarks
Against Brand
Flags content that damages or discredits your brand:
Attacks or accusations against the brand
Criticism directed at brand ambassadors, employees, or ad characters
Complaints about products, services, or the brand in general
Inappropriate
Captures language/themes that are explicit, disturbing, or unsafe for public audiences:
Profanity or vulgar language
Sexual references or objectification
Scatological mentions (bodily fluids, gore, etc.)
Mentions of death, murder, suicide, abuse, etc.
Glorifying violence, drugs, addiction, or crime
🌍 Languages Covered
Our moderation models, combined with powerful translation capabilities, cover 109 languages—ensuring consistent protection across your global audience.
Languages supported include:
Afrikaans, Albanian, Amharic, Arabic, Armenian, Azerbaijani, Basque, Belarusian, Bengali, Bosnian, Bulgarian, Catalan, Cebuano, Chinese (Simplified), Chinese (Traditional), Corsican, Croatian, Czech, Danish, Dutch, English, Esperanto, Estonian, Filipino (Tagalog), Finnish, French, Frisian, Galician, Georgian, German, Greek, Gujarati, Haitian Creole, Hausa, Hawaiian, Hebrew, Hindi, Hmong, Hungarian, Icelandic, Igbo, Indonesian, Irish, Italian, Japanese, Javanese, Kannada, Kazakh, Khmer, Kinyarwanda, Korean, Kurdish, Kyrgyz, Lao, Latin, Latvian, Lithuanian, Luxembourgish, Macedonian, Malagasy, Malay, Malayalam, Maltese, Maori, Marathi, Mongolian, Myanmar (Burmese), Nepali, Norwegian, Nyanja (Chichewa), Odia (Oriya), Pashto, Persian, Polish, Portuguese (Portugal, Brazil), Punjabi, Romanian, Russian, Samoan, Scots Gaelic, Serbian, Sesotho, Shona, Sinhala (Sinhalese), Slovak, Slovenian, Somali, Spanish, Sundanese, Swahili, Swedish, Tajik, Tamil, Tatar, Telugu, Thai, Turkish, Turkmen, Ukrainian, Urdu, Uyghur, Uzbek, Vietnamese, Welsh, Xhosa, Yiddish, Yoruba, Zulu.
How Essential Moderation compares to Reputation+ and Engage+
Essential gives you strong, automatic protection with four broad categories that catch most harmful content at scale. Reputation+ and Engage+ build on that foundation with much deeper control, context, and coverage:
What Reputation+ and Engage+ include (that Essential doesn’t)
Brand-specific moderation (not generic)
Reputation+ and Engage+ bring context into every decision. They include post analysis (reading the creative/copy), brand context (your guidelines, product lines, competitors, and sensitivities), and the option to build bespoke models so moderation reflects your rules—not a one-size-fits-all approach.
Depth and breadth of categories
Reputation+/Engage+ include many more categories beyond Essential (e.g., brand critique vs. brand attack, personal attack/bullying, competitor promotion/mention, impersonation, PII, mild vs. extreme profanity, intoxicants, referral codes, sexual/toilet, socio-political, repeated behaviors, and more), plus industry-specific categories (entertainment, beauty/retail/e-commerce, gaming, health, food).Brand context to guide the model
We add your brand guidelines, product lines, competitors, sensitive topics, and custom rules so the moderation model understands your boundaries and makes smarter, brand-specific decisions.Post-aware moderation (post analysis)
Reputation+/Engage+ analyze the post/ad creative and copy to understand intent and nuance. This allows more accurate decisions (e.g., distinguishing a relevant “price” discussion under a promotional post from noise elsewhere).Bespoke models & customization
Build bespoke AI models, refine thresholds, or tune definitions for your specific use case.Asset- and platform-level controls
Customize which tags to hide for each profile, campaign, post, or platform. Turn specific categories on/off where they matter most.Better, configurable alerts with AI insight summary
Go beyond simple hiding with immediate alerts, volume-based thresholds, and spike (% growth) alerts for issues like severe events, self-harm, post issues, legal/IP risks, outages, and more—plus AI insight summaries via email.
Moderation Capability | Essential | Reputation+ & Engage |
Moderation approach (brand specificity) | General rules across brands | Brand-specific with post analysis, brand context, and bespoke models |
Auto-hiding core categories | ✅ Spam, Offensive, Against brand, Inappropriate | ✅ Includes all Essential |
Total category depth | Foundational (broad buckets) | Expanded (dozens incl. brand critique/attack, PII, impersonation, competitor, profanity tiers, socio-political, repeated, etc.) |
Industry-specific categories | — | ✅ (entertainment, beauty/retail/e-com, gaming, health, food) |
Add brand context to model | — | ✅ Provide brand rules, competitors, sensitivities |
Post-aware moderation (post analysis) | — | ✅ Creative/copy analyzed for intent |
Customize hide rules per profile/platform | — | ✅ Fully customizable |
Customize per asset/post/campaign | — | ✅ Fully customizable |
Immediate alerts | ✅ Basic | ✅ Critical issues in real time |
Volume-based alerts | ✅ Basic | ✅ Threshold-driven |
Spike alerts (% growth) | — | ✅ Anomaly detection |
AI alert insights via email | — | ✅ Summaries & context |
Bespoke AI models (build your own) | — | ✅ |
Languages covered | 109 | 109 |