Restaurant Review Analyzer – Google Maps Complaints AI

Give this actor a restaurant’s Google Maps reviews (a reviews dataset ID from a Google Maps reviews scraper, JSON items or pasted text) and it tags every review by issue (service, wait time, food, price, cleanliness, allergens, staff, noise, booking) with sentiment and severity. The summary ranks the top complaints with real example quotes, so an owner or agency sees what to fix first.

Find out exactly why guests leave bad reviews. This Actor takes Google Maps reviews (for example the output of the popular Google Maps Reviews Scraper) and tags every review with complaint types, sentiment and severity, then writes a summary record with the top issues, their share and real example quotes.

Built for restaurant owners, multi-location groups, hospitality consultants, agencies and review-management tools.

What it detects

Issue	Examples
Service	forgotten orders, inattentive service
Wait time	"waited 45 minutes", slow kitchen
Food quality	cold, bland, undercooked dishes
Price / value	overpriced, small portions, bill errors
Cleanliness	dirty toilets, sticky tables
Allergens / dietary	gluten, vegan, allergy mistakes
Staff attitude	rude or unfriendly staff
Noise / atmosphere	loud music, can't talk
Booking / reservations	lost reservations, no table

Severity: none, low, medium, high, critical (health, safety or allergen incidents). Works on reviews in any language. AI classification uses TypeSafe Jev; a multilingual keyword engine (EN/ES/FR/DE/IT/PT/PL) is the fallback.

Input

• Reviews dataset ID: paste the dataset ID from a Google Maps reviews scraper run. Fields used: text, textTranslated, stars, title, placeId, reviewId, reviewUrl, publishedAtDate.
• Review items (JSON): the same items pasted directly.
• Pasted reviews: plain texts, one per line.
• Run with empty input to see a demo on sample reviews.

AI classification with the built-in key is capped at 300 reviews per run (the rest use keyword rules). Add your own TypeSafe API key to lift the cap and skip the AI fee.

Output

One record per review:

{"type":"review","placeName":"Demo Tapas Bar","stars":1,"sentiment":"negative","severity":"critical",
 "issues":["service","allergens_dietary","staff"],"issueProbabilities":{"allergens_dietary":0.97,"...":0},
 "text":"Pedí sin gluten y me trajeron croquetas normales...","method":"ai"}

Plus one summary record (also in the key-value store as SUMMARY): total reviews, average stars, sentiment and severity counts, and topIssues with count, sharePct, shareOfNegativePct, criticalCount and example quotes.

Use cases

• Monthly review report for a restaurant or chain
• Benchmark competitors' weak spots before opening
• Feed a dashboard or alert on new critical (allergen, hygiene) reviews

Pricing

$20 per 1,000 reviews classified (pay-per-event, from 4 Nov 2026), plus a tiny per-run start fee.

FAQ

Does it scrape Google? No. It only analyses reviews you provide or that another Actor already collected. Is it accurate? AI tags come with per-issue probabilities so you can set your own threshold. Check a sample for your use case.

More questions

Where do the reviews come from? Pass the dataset of any Google Maps reviews scraper run (e.g. compass/google-maps-reviews-scraper), JSON items or pasted texts.

Which languages? AI handles any language; the keyword fallback covers EN/ES/FR/DE/IT/PT/PL.

Need a per-place summary with reply drafts instead? Use Google Maps Review Insights (nebulosa/google-maps-review-insights).

Pairs with

• google-maps-review-insights
• osm-business-leads
• menu-allergen-translator

Reports from Revunda

Prefer a finished document for a restaurant owner? Revunda Google profile audit gives a PDF with 10 fixes ranked by impact (free sample report on the page). Free: AI visibility check for restaurants.

More questions (FAQ)

How do I analyze my restaurant’s Google reviews?

Scrape the reviews with a Google Maps reviews scraper (e.g. compass/google-maps-reviews-scraper), pass the dataset ID here, and open the summary for the ranked issues. To fetch reviews from a place URL in one step, use nebulosa/google-maps-review-insights.

Does it work in Spanish and other languages?

Yes, reviews in any common language are classified.

Can I analyze only negative reviews?

Yes. Turn on "Only reviews with 1-3 stars".