Industry Review Complaint Analyzer | Dental & Restaurant AI

Turn customer reviews into actionable business intelligence. Find the problems customers mention most, rank them by priority, and get evidence-based recommendations.

The Problem This Solves

Businesses can have hundreds or thousands of reviews. Reading them manually is slow. Generic sentiment analysis only tells you "70% positive, 30% negative" — which isn't actionable.

This Actor answers the real questions:

• What are customers complaining about?
• How frequently does each problem occur?
• How serious is each problem?
• What should the business prioritize?
• What actions should the business take?

Who Is It For?

• Dental clinic owners — identify operational issues before they hurt your reputation
• Restaurant managers — pinpoint food quality, service, and ambience problems
• Marketing agencies — provide actionable review analysis to your clients
• Business consultants — use data-driven insights for operational audits
• Reputation management firms — go beyond sentiment to specific complaint categories

How It Works

Customer Reviews
       ↓
Cleaning & Validation
       ↓
Duplicate Detection
       ↓
Industry-Specific Classification (12-13 categories per industry)
       ↓
Sentiment Analysis (keyword + rating augmented)
       ↓
Priority Calculation (frequency × severity × rating)
       ↓
Recommendation Generation (evidence-based)
       ↓
Structured JSON Output

The Actor uses a hybrid deterministic architecture — keyword-based industry classification with no external LLM API calls. This means:

• Zero AI API costs (deterministic analysis)
• Sub-millisecond per-review processing (0.23ms/review)
• Explainable results (every detection is traceable to keywords)
• Consistent output (no LLM hallucination risk)

Supported Industries

Dental Clinics (12 categories)

Category	What it detects
waiting_time	Long waits, delays, waiting room complaints
appointment_availability	Booking difficulty, no availability
treatment_cost	Expensive, overpriced, insurance issues
unexpected_cost	Hidden fees, surprise charges
pain_discomfort	Pain, soreness, sensitivity, swelling
dentist_communication	Explanation quality, rushed, didn't listen
staff_behavior	Rude receptionist, friendly staff, professional
cleanliness	Clean/dirty, hygienic, spotless
treatment_quality	Filling/crown quality, procedure outcomes
billing_problem	Overcharged, claim denied, wrong amount
booking_problem	Online system issues, no reminders
location_parking	Hard to find, no parking, inconvenient

Restaurants (13 categories)

Category	What it detects
food_quality	Delicious, bland, fresh, stale
food_temperature	Cold food, not hot, reheated
food_portion	Small portions, generous, tiny
food_price	Overpriced, affordable, good value
waiting_time	Slow service, long wait, quick
staff_behavior	Rude waiter, friendly server, attentive
customer_service	Complaint handling, manager response
cleanliness	Dirty tables, filthy bathroom, spotless
delivery	Late delivery, cold on arrival, missing items
order_accuracy	Wrong order, missing dishes, mixed up
menu_availability	Out of stock, sold out, unavailable
ambience	Loud, noisy, cozy, romantic
parking_location	No parking, hard to find, convenient

Input

{
  "industry": "dental",
  "reviews": [
    {
      "text": "I waited for an hour and the staff were rude. The dentist was good though.",
      "rating": 2
    },
    {
      "text": "Excellent service, very clean and professional.",
      "rating": 5
    }
  ],
  "businessName": "Smile Dental Clinic",
  "analysisMode": "balanced",
  "includeRecommendations": true
}

Required fields

Field	Type	Description
industry	string	"dental" or "restaurant"
reviews	array	List of review objects with text (required) and rating (optional, 0-5)

Optional fields

Field	Type	Default	Description
businessName	string	—	Business name for the report
language	string	"en"	Language code
analysisMode	string	"balanced"	fast, balanced, or deep
includeRecommendations	boolean	true	Generate actionable recommendations

Output

The Actor pushes two types of items to the dataset:

1. Summary item (first row)

{
  "business_name": "Smile Dental Clinic",
  "industry": "dental",
  "analysis_mode": "balanced",
  "generated_at": "2026-08-29T12:00:00Z",
  "summary": {
    "total_reviews": 200,
    "processed_reviews": 195,
    "skipped_duplicates": 3,
    "skipped_invalid": 2,
    "positive_reviews": 110,
    "neutral_reviews": 30,
    "negative_reviews": 55,
    "avg_rating": 3.8
  },
  "top_problems": [
    {
      "category": "waiting_time",
      "label": "Waiting time",
      "mentions": 42,
      "percentage": 21.5,
      "priority": "HIGH",
      "avg_rating": 2.3,
      "example_themes": ["...I waited for an hour...", "...long wait..."]
    }
  ],
  "top_positive_themes": [
    {
      "category": "treatment_quality",
      "label": "Treatment quality",
      "mentions": 88,
      "percentage": 45.1
    }
  ],
  "recommendations": [
    {
      "issue": "Waiting time",
      "category": "waiting_time",
      "priority": "HIGH",
      "recommendation": "Review appointment scheduling and staffing during peak hours. Consider implementing a patient notification system for delays.",
      "evidence": "Found in 42 review(s) (21.5% of total). Priority: HIGH. Example themes: ...I waited for an hour..., ...long wait...."
    }
  ]
}

2. Per-review analysis items (subsequent rows)

{
  "type": "review_analysis",
  "industry": "dental",
  "review": "I waited for an hour and the staff were rude.",
  "rating": 2,
  "sentiment": "negative",
  "sentiment_score": -0.65,
  "categories": ["waiting_time", "staff_behavior"],
  "confidence": 0.667
}

Priority System

Each problem is assigned a priority based on:

Factor	Weight	Description
Frequency	40%	What percentage of reviews mention this problem
Negative sentiment	35%	What percentage of mentions are negative
Rating severity	25%	How low the average rating is for this problem

Priority	Score range	Meaning
CRITICAL	≥ 0.70	Address immediately — high frequency, very negative
HIGH	0.50–0.69	Significant issue affecting many customers
MEDIUM	0.25–0.49	Notable but manageable issue
LOW	< 0.25	Minor issue or isolated incidents

Performance

Reviews	Time	Per review
100	26ms	0.26ms
500	118ms	0.24ms
1,000	234ms	0.23ms

Pricing

This Actor uses pay-per-event pricing:

Event	Price	Charged when
review-analyzed	$0.002 per review	For every review successfully analyzed

Example costs:

• 100 reviews = $0.20
• 1,000 reviews = $2.00
• 5,000 reviews = $10.00

This is competitive with generic sentiment analyzers ($1/1000) while providing significantly more value through industry-specific categorization, priority ranking, and recommendations.

Use Cases

1. Operational audits — Identify the top 3 issues affecting a dental clinic or restaurant
2. Competitive analysis — Compare your review profile to competitors
3. Customer experience optimization — Prioritize which issues to fix first
4. Reputation monitoring — Track complaint categories over time
5. Business acquisition due diligence — Analyze a target business's reviews before buying

Limitations

• English only (MVP) — keyword dictionaries are in English
• Two industries (MVP) — dental and restaurant; more can be added
• No scraping — this Actor analyzes reviews you provide; it does not scrape Google Maps or Yelp
• Keyword-based — uses deterministic keyword matching, not LLM inference (this is a feature: explainable, fast, and free of API costs)

Privacy

• Your review data is processed within the Apify platform
• No data is sent to external LLM APIs
• No credentials are stored
• Results are stored in your Apify dataset

License

MIT