Google Maps Reviews Analyzer – AI Insights & Replies

Paste Google Maps place URLs (or an existing reviews dataset) and this actor returns AI insights per place: top complaints, top praises, sentiment trend by month and a prioritised action list. It also drafts owner replies in each review’s language, ready to edit and post.

Give it a Google Maps place link. For each place you get a report that names the top complaints, the top praises, the sentiment trend by month, an action list for the owner and reply drafts for the worst recent reviews. Each reply is written in the same language as the review it answers (English, Spanish, Russian, German, French and more).

It suits restaurants, hotels, clinics, shops, agencies that handle local SEO and reputation, and anyone comparing competitors on Google Maps.

How it works

1. Reviews in. Use one of these:
   • Google Maps place URLs. The actor calls the public Apify Store actor compass/google-maps-reviews-scraper on your account, which bills its own small usage fee. Reviewer personal data is switched off.
   • A dataset ID from a reviews-scraper run you already have, which means no new scraping.
   • Review JSON or pasted review texts.
2. AI analysis. One AI call per place reads up to 120 of the newest reviews. The prompt only allows statements backed by those reviews, and every quote is taken word for word.
3. One dataset item per place comes out. You can export it as JSON, CSV or Excel, or send it through the API, webhooks, Make or Zapier.

Run it with empty input {} to see a demo on built-in sample reviews.

Example input

{
  "startUrls": [{ "url": "https://www.google.com/maps/place/?q=place_id:ChIJk_s9Z_aipBIRhLyH9BPgsXA" }],
  "maxReviewsPerPlace": 50,
  "reviewsLanguage": "es",
  "outputLanguage": "auto",
  "replyDrafts": 5
}

Example output (shortened)

{
  "placeName": "Demo Café",
  "reviewsAnalysed": 50,
  "averageStars": 3.9,
  "starDistribution": { "1": 6, "2": 4, "3": 5, "4": 12, "5": 23 },
  "ownerReplyRatePct": 12,
  "sentimentTrend": [{ "month": "2026-09", "reviews": 18, "averageStars": 3.6 }, { "month": "2026-10", "reviews": 32, "averageStars": 4.1 }],
  "summary": "Guests love the croissants and the terrace, but slow service at peak times drives most of the low ratings.",
  "topComplaints": [{ "theme": "Slow service and long waits", "mentions": 9, "severity": "high", "exampleQuote": "We waited 40 minutes for two coffees" }],
  "topPraises": [{ "theme": "Excellent croissants", "mentions": 14, "exampleQuote": "Best croissants in town" }],
  "sentimentDirection": "improving: October reviews are clearly more positive",
  "actionList": [{ "priority": 1, "action": "Add a second barista on weekend mornings", "why": "Slow service and long waits" }],
  "replyDrafts": [{ "language": "es", "stars": 1, "reviewText": "Pedí leche sin lactosa y me la sirvieron normal...", "reply": "Hola, sentimos mucho lo ocurrido con su pedido sin lactosa..." }]
}

Input fields

Field	What it does
startUrls	Google Maps place URLs
maxReviewsPerPlace	Number of newest reviews per place, 5–300 (default 50)
reviewsLanguage	Language code passed to the scraper
datasetId / reviews / reviewTexts	Reviews you supply yourself
outputLanguage	auto (the majority language) or a fixed language for the analysis. Reply drafts always follow the language of each review.
replyDrafts	Number of reply drafts per place, 0–15
llmApiKey	Optional. Your own DeepSeek key; when you use it, the AI-analysis fee is not charged.

Notes and limits

• The AI insights can contain mistakes. Check every reply draft before you post it. This actor never posts anything to Google.
• The actor only reads reviews that are publicly shown on Google Maps, and leaves out reviewer names.
• Not affiliated with Google.

Use cases

• Local SEO agencies: a review audit per client or prospect location in one run.
• Multi-location restaurants and hotels: compare branches by top complaints and monthly trend.
• Competitor analysis: what customers dislike about the 5 competitors next door.
• Reputation management: ready reply drafts for the worst recent reviews, in the reviewer's language.

Pricing

$0.25 per place analysed + $0.05 per place when our built-in AI key is used (free with your own DeepSeek key). Reviews are fetched with compass/google-maps-reviews-scraper on your account, which has its own small fee. Our 2-place test (15 reviews each) cost about $0.02 in scraper/platform usage. Prices apply from 4 Nov 2026.

FAQ

Can I analyse competitors? Yes. Add several place URLs and you get one report per place. Weekly tracking? Schedule the actor in Apify Console and connect a webhook or an email integration.

More questions

Do I need a Google API key? No. Reviews come from the public Apify scraper; AI uses our key unless you add yours.

Can I analyse reviews I already scraped? Yes: pass a datasetId, JSON review items or pasted texts; then no scraper fee.

Which languages? Insights in EN/ES/RU/DE/FR/IT/PT/PL; reply drafts always follow each review's language.

Pairs with

• restaurant-review-insights
• osm-business-leads
• menu-allergen-translator

Reports from Revunda

Prefer a finished document for a client or owner? Revunda Google profile audit turns a Maps profile into a PDF with 10 fixes ranked by impact (free sample report on the page). Profile suspended? See ProfileRescue. Free: Do AI assistants recommend this business?

More questions (FAQ)

How do I do sentiment analysis of Google Maps reviews?

Paste the place URL, run, and open the per-place summary with sentiment by month and grouped complaints.

Can it write replies to Google reviews?

It drafts replies for the owner to review and post manually; it never posts anything.

Can I use reviews I already scraped?

Yes. Pass the dataset ID from compass/google-maps-reviews-scraper or similar.

Which languages?

English, Spanish, Russian and other common languages; replies follow the review language.