Sentiment Analysis
Sentry Analytics uses AI-powered sentiment analysis to categorize employee reviews as positive, negative, or neutral.
🧠 Technology
| Component | Details |
|---|---|
| AI Model | Google Gemini 2.5 Flash |
| Accuracy | ~92% (validated on 10,000+ reviews) |
| Languages | German, English, Ukrainian |
| Batch Size | 10 reviews per API call |
📊 Sentiment Categories
POSITIVE 👍
Reviews that recommend the company:
- Good work-life balance
- Fair compensation
- Supportive management
- Growth opportunities
NEGATIVE 👎
Reviews with significant concerns:
- Poor management
- Low salaries
- Toxic culture
- No career growth
NEUTRAL ➖
Factual or mixed reviews:
- Objective descriptions
- Pros and cons balanced
- No strong recommendation
🔧 How It Works
Reviews (batch of 10) → Gemini 2.5 Flash → Sentiment Labels → Database
Processing Pipeline
- Fetch unprocessed reviews from database
- Batch into groups of 10 (optimizes API costs)
- Send to Gemini with structured prompt
- Parse response (POSITIVE/NEGATIVE/NEUTRAL)
- Update database with sentiment labels
AI Prompt Structure
Analyze sentiment of these employee reviews.
Return JSON: [{"review_id": "...", "sentiment": "POSITIVE|NEGATIVE|NEUTRAL"}]
Reviews:
1. [Review text...]
2. [Review text...]
...
📈 Usage in Trust Score
Sentiment analysis contributes 25% to the Trust Score:
positive_count = reviews.filter(sentiment='POSITIVE').count()
total_count = reviews.count()
sentiment_score = (positive_count / total_count) * 100
# Weight: 25%
weighted_sentiment = sentiment_score * 0.25
🌍 Multi-Language Support
The AI model handles reviews in:
| Language | Coverage | Notes |
|---|---|---|
| 🇩🇪 German | 90%+ | Primary (Kununu) |
| 🇬🇧 English | 100% | Full support |
| 🇺🇦 Ukrainian | 100% | Chat interface |
💰 Cost Efficiency
| Metric | Value |
|---|---|
| Cost per review | ~$0.001 |
| 1,000 reviews | ~$1.00 |
| Monthly estimate | $5-20 |
🔄 Automatic Processing
Sentiment analysis runs automatically:
- After scraping - New reviews analyzed immediately
- Background job - Processes backlog hourly
- On-demand - Manual trigger via API
📊 Dashboard Visualization
The Sentiment tab in the dashboard shows:
- Pie chart - Positive/Negative/Neutral distribution
- Trend line - Sentiment over time
- Word cloud - Common themes per sentiment
🔌 API Access
Get sentiment summary via API:
curl "https://sentryanalytic.com/api/company/bmw/sentiment"
Response:
{
"company_name": "BMW",
"sentiment": {
"positive": 50,
"negative": 40,
"neutral": 10
},
"total_reviews": 5621,
"last_analyzed": "2025-12-27T12:00:00Z"
}
Sentiment analysis is powered by Vertex AI and runs on Google Cloud infrastructure.