🛡️ AI Text Moderation Actor

This Apify Actor uses Sentinel Moderation's AI-powered API to classify and flag potentially harmful or inappropriate text content. It detects a wide range of categories including harassment, hate speech, sexual content, illicit activity, self-harm, and violence.

Use this actor to help protect your platform and maintain community guidelines by automating content moderation at scale.

---

📥 Input Schema

The actor accepts a simple JSON input:

1{
2  "apiKey": "your-sentinelmoderation-api-key",
3  "content": "Text to analyze goes here..."
4}

• apiKey (string, required): Your API key from SentinelModeration.com.
• content (string, required): The text you want to classify for moderation.

---

📤 Output

The actor returns an array containing one moderation result object with the following structure:

1[
2  {
3    "flagged": false,
4    "categories": {
5      "harassment": false,
6      "harassment/threatening": false,
7      "sexual": false,
8      "hate": false,
9      "hate/threatening": false,
10      "illicit": false,
11      "illicit/violent": false,
12      "self-harm/intent": false,
13      "self-harm/instructions": false,
14      "self-harm": false,
15      "sexual/minors": false,
16      "violence": false,
17      "violence/graphic": false
18    },
19    "category_scores": {
20      "harassment": 0.000048,
21      "harassment/threatening": 0.0000066,
22      "sexual": 0.000039,
23      "hate": 0.0000142,
24      "hate/threatening": 0.0000008,
25      "illicit": 0.000022,
26      "illicit/violent": 0.000019,
27      "self-harm/intent": 0.0000011,
28      "self-harm/instructions": 0.0000010,
29      "self-harm": 0.0000020,
30      "sexual/minors": 0.000010,
31      "violence": 0.000016,
32      "violence/graphic": 0.0000056
33    },
34    "error": "NOTE: THIS IS A SAMPLE RESPONSE, AN API KEY FROM SENTINELMODERATION.COM IS REQUIRED TO GET REAL RESULTS FOR THIS ACTOR."
35  }
36]

• flagged: true if any category crosses the internal moderation threshold.
• categories: A breakdown of category flags (true/false).
• category_scores: Raw probability scores for each category (0.0 - 1.0).
• error: A message shown when a valid API key is not provided.

---

🧠 Categories Detected

This actor checks for content under the following moderation categories:

• Harassment
• Threatening language
• Sexual content (general & involving minors)
• Hate speech (general & threatening)
• Illicit activity (including violent)
• Self-harm (intent, instructions, general)
• Violence (including graphic imagery)

---

🔐 Getting an API Key

To use this actor with real moderation results, you need an API key from Sentinel Moderation:

1. Go to sentinelmoderation.com
2. Sign up and generate your API key
3. Use the key in the apiKey field of the input

---

✅ Example Use Cases

• Moderating user comments or posts
• Screening support messages for abuse
• Filtering harmful prompts in AI chat systems
• Pre-checking user-generated bios or profile content