Detect influencer fraud and fake followers with Instagram, X, TikTok and Claude

Description

Analyzes influencer profiles and scores authenticity before brand partnership approval. Detects fake followers, bot accounts, and suspicious engagement patterns using AI-powered behavioral analysis.

🎯 How It Works

Simple 7-Node Workflow:
Input → Submit influencer username and platform (Instagram/Twitter/TikTok)
Fetch → Retrieve complete profile data and engagement metrics
Analyze → Examine follower patterns, ratios, growth velocity, engagement
AI Check → Deep behavioral analysis with Claude AI
Report → Generate comprehensive fraud assessment
Notify → Send detailed email report to partnership team
Log → Save to database for tracking

📊 Detection Capabilities

Follower Authenticity**: Analyzes follower-to-following ratio (red flag if < 0.5)
Engagement Quality**: Calculates engagement rate (industry avg: 1-5%)
Growth Patterns**: Detects suspicious rapid follower spikes
Content Consistency**: Evaluates posting frequency and regularity
Profile Completeness**: Checks verification, bio, activity
AI Behavioral Analysis**: Deep pattern recognition for sophisticated fraud

⚙️ Setup Instructions

1. Configure API Access
Social Platform APIs:
Instagram**: Get Graph API access token from Meta for Developers
Twitter**: OAuth 2.0 credentials from Twitter Developer Portal
TikTok**: Business API credentials (optional)

AI Analysis:
Anthropic Claude API**: Get key from console.anthropic.com
Used for advanced behavioral fraud detection

2. Setup Notifications
Configure SMTP in "Send Report" node
Update recipient email ([email protected])
Customize HTML template if needed

3. Database (Optional)
Create PostgreSQL table (schema below)
Add database credentials to final node
Skip if you don't need historical tracking

Database Schema
CREATE TABLE partnerships.influencer_fraud_reports (
id SERIAL PRIMARY KEY,
report_id VARCHAR(255) UNIQUE,
username VARCHAR(255),
platform VARCHAR(50),
profile_url TEXT,
followers BIGINT,
following BIGINT,
posts INTEGER,
verified BOOLEAN,
authenticity_score INTEGER,
risk_level VARCHAR(50),
final_decision TEXT,
partnership_recommendation VARCHAR(100),
ai_verdict VARCHAR(50),
ai_confidence VARCHAR(20),
red_flags JSONB,
fake_follower_estimate VARCHAR(20),
detailed_analysis JSONB,
created_at TIMESTAMP
);

🚀 How to Use

Webhook Endpoint: POST /webhook/influencer-fraud-check

Request Body:
{
"username": "influencer_handle",
"platform": "instagram" // or "twitter", "tiktok"
}

Example:
curl -X POST https://your-n8n.com/webhook/influencer-fraud-check \
-H "Content-Type: application/json" \
-d '{"username":"example_user","platform":"instagram"}'

📈 Scoring System

Overall Authenticity Score (0-100):
80-100**: LOW RISK → Approved for partnership
60-79**: MEDIUM RISK → Requires manual review
40-59**: HIGH RISK → Caution advised
0-39**: CRITICAL RISK → Rejected

Weighted Components:
Follower Quality (25%)
Engagement Quality (35%)
Content Consistency (15%)
Growth Pattern (15%)
Profile Completeness (10%)

Final Score = 70% Automated + 30% AI Analysis

🚩 Red Flags Detected

Following-to-follower ratio > 2:1
Engagement rate < 0.5%
Rapid growth (>50K followers/month)
Large following with <10 posts
No verification with >100K followers
Bot-like comment patterns
Suspicious audience demographics

💰 Cost Estimate

Instagram/Twitter API**: Free tier usually sufficient
Claude AI**: ~$0.10-0.20 per analysis
Estimated**: $5-10/month for 50 checks

💡 Best Practices

Always verify HIGH and MEDIUM risk profiles manually
Cross-reference with other influencer databases
Request media kit and past campaign results
Trial campaigns before large commitments
Monitor performance metrics post-partnership
Update detection thresholds based on your findings

🎯 What You Get

Detailed Report Includes:
Overall authenticity score (0-100)
Risk level classification
Partnership recommendation (APPROVE/REVIEW/REJECT)
Engagement quality analysis
Fake follower percentage estimate
AI behavioral insights
Specific red flags and concerns
Next steps and recommendations