Google Maps Reviews Analyzer (AI)

Turn Google Maps reviews into a report a business owner can act on: what customers love, what they complain about, what to fix first, how it is trending, and polite reply drafts for unanswered negative reviews. Every quote is copied word for word from a real review.

No setup and no AI account needed. Run it with no input to get a free demo report on sample reviews.

Open the full sample report: 40 fictional reviews of a demo café, with themes, a monthly trend and reply drafts.

What you get

🧭 Fix-first list	Complaint themes ranked by how often, how badly and how recently customers mention them, with a rising / steady / falling trend
💬 Themes with real quotes	Top praise and complaint themes with counts, share of reviews and up to 3 verbatim quotes each, linked to the review (or the place)
📈 Month by month	Review volume and average stars per month
🏪 Location comparison	Side-by-side table when you analyze several places
🚨 Needs attention now	Reviews about illness, safety, discrimination, fraud or legal threats
✍️ Reply drafts	Specific, polite drafts for recent unanswered negative reviews, in the review's language
📄 Three outputs	A client-ready HTML report, a short JSON summary for code and AI agents, and one dataset row per review

How to use it

1. With place URLs: paste Google Maps place URLs or place IDs and click Start. We scrape the newest reviews with Google Maps Reviews Scraper on your account first, then analyze them.
2. With a dataset you already have: put the dataset ID from a Google Maps Reviews Scraper or Google Maps Scraper run (with reviews) in Dataset ID.
3. Automatically after every scrape: open your scraper (or its saved task), go to Integrations, add Google Maps Reviews Analyzer (AI). The scraper's dataset is passed in automatically, so each scheduled scrape produces a fresh report.

Then open the Report tab of the run for the HTML report, or the Summary tab for JSON.

How much does it cost

You pay per result. Running the Actor itself costs you nothing extra: no compute or proxy charges.

Event	Free & Starter	Scale	Business and up
Review analyzed (per 1,000)	$1.20	$1.00	$0.80
Report generated (per run)	$0.05	$0.05	$0.05
Reply draft (each)	$0.01	$0.01	$0.01

Never charged: the demo run, star-only reviews with no text (they still count toward stars and trends), reviews we could not analyze, and runs that find no reviews.

Examples on the Free and Starter plans:

• One place with 250 reviews: $0.30 + $0.05 report = $0.35, plus up to $0.25 for reply drafts ($0.10 on Free).
• 1,000 reviews: $1.20 + $0.05 = $1.25, plus up to $0.25 for reply drafts ($0.10 on Free). Apify's free $5 monthly credit covers about 3,700 reviews a month, or 4,000 with reply drafts off.
• An agency reporting monthly on 20 locations with 250 reviews each: about $7 a month, plus up to $5 for reply drafts ($0.25 per location).
• If you give place URLs, scraping is billed separately by Google Maps Reviews Scraper (about $0.60 per 1,000 reviews on the Free plan).

Reply drafts are on by default. Each run drafts replies to up to 25 unanswered negative reviews (10 on the Free plan) at $0.01 each: up to +$0.25 per run on paid plans and up to +$0.10 on Free. To skip that cost, turn off Draft replies (draftReplies: false) or lower Max reply drafts (maxReplyDrafts).

Free-plan runs analyze up to 1,000 reviews and draft up to 10 replies each. Your run's spending limit is always respected: if it is lower than the full job, we analyze what fits and tell you in the status message.

Output

JSON summary (the OUTPUT record), shortened, from a real run on 50 Yellowstone National Park reviews:

{
  "coverage": { "reviews": 50, "analyzed": 27, "noText": 23, "skipped": 0 },
  "overall": {
    "avgStars": 4.94,
    "topPraise": [{ "name": "Breathtaking scenic landscapes", "count": 10, "share": 0.37, "quote": "The wonders of nature" }],
    "topComplaints": [{ "name": "Crowded on weekends and October", "count": 2, "share": 0.07, "quote": "Wochenende und Feiertage meiden." }],
    "fixFirst": [{ "name": "Disgusting bathrooms", "score": 0.249, "negativeCount": 1, "shareOfNegative": 0.2, "trend": "up" }]
  }
}

Dataset, one row per review: place, stars, date, language, text, owner replied, analysis status, sentiment and score, aspects, phrases with verified excerpts, urgent flag and reason. Export it to Excel, CSV or JSON from the Storage tab.

How accurate is it

On a hand-labeled test set of 60 reviews in 8 languages (2026-10-17):

Check	Result
Overall sentiment matches the label	96.7% to 98.3%
Aspects found (F1)	0.87 to 0.88
Urgent reviews caught	100%
Quotes that are word for word from the review	100% (enforced by code: anything else is dropped)

The AI only labels reviews. Every count, share, score and trend is computed by code from those labels, so the numbers add up.

What it does not do: it does not read review photos, does not detect fake reviews, and cannot analyze star-only reviews (they still count in stars and trends). AI labels can be wrong on sarcasm or very short reviews, which is why every theme shows its quotes.

For AI agents and automations

• Free demo: call it with {} to get a full sample report and JSON summary at no cost.
• Minimal input: { "placeUrls": ["https://www.google.com/maps/place/..."] } or { "datasetId": "<dataset id>" }.
• Read the result: the OUTPUT record is a short JSON summary designed to fit in one tool call (under 20,000 characters; with many places, per-place detail is shortened first, and with many reply drafts only the first ones are kept): coverage, average stars, sentiment split, top 3 praise and complaint themes with one quote each, fix-first list, monthly trend, reply drafts and a link to the HTML report.
• Never charged: no reviews found, star-only reviews, and reviews that could not be analyzed. The status message says why.
• Works through Apify's MCP server, the Apify API and SDKs, and Make, Zapier or n8n.

FAQ

Which languages does it support? Reviews in any language. Theme names are in the language you choose (reportLanguage, default English) and report headings are in English. Quotes and reply drafts stay in each review's own language.

Does it collect reviewer names? No. When we scrape for you, personal data collection is switched off. Reviewer names, profile links and photos are removed from any dataset you give us before anything else happens, and never appear in the output.

Where is review text processed? By the Anthropic API (Claude). SignalSift keeps nothing after the run; your results stay in your Apify storage.

Is it legal? It analyzes publicly available reviews. You are responsible for how you use the results and for complying with the laws that apply to you, including GDPR when you handle personal data.

Something is wrong or missing? Open an issue on the Issues tab. We read every one.

Changelog

• 0.1.11 (2026-10-18): Reply drafts never greet a reviewer by a name taken from their review, such as a signature (such a draft is dropped and not charged). Catch-all themes read "Other complaints" instead of "Other other complaints". The same place given twice is scraped and budgeted once.
• 0.1.10 (2026-10-18): If the platform restarts a run after its reply drafts were charged, the drafts already paid for are delivered again without a second charge, even when the AI cannot write them again: drafts are now saved in the run's storage (the REPLY_DRAFTS record) before they are charged. With many reply drafts, the JSON summary keeps the first ones and says how many it left out, to stay under 20,000 characters (the report has them all).
• 0.1.9 (2026-10-18): A run restarted by the platform waits for the scrape it already started instead of paying Google Maps Reviews Scraper twice. Text from your dataset is trimmed of surrounding spaces.
• 0.1.8 (2026-10-18): Fixed: a batch of reviews was sometimes reported as not analyzed when the AI rated an aspect as mixed; dataset rows can now show mixed for an aspect. The status message no longer says "(0 with stars only)". Line breaks in quoted reviews show as " — " instead of running sentences together. On the Free plan, a run restarted by the platform stays within 1,000 reviews. With many places, the JSON summary shortens per-place detail to stay under 20,000 characters (the report keeps everything).
• 0.1.6 (2026-10-18): When the AI cannot analyze the reviews, the run stops early and says so instead of retrying until it times out (reviews that were not analyzed are never charged). The status message lists reply drafts when they were charged. Reply drafts in the JSON summary no longer repeat the place link (the report and the dataset still have it), which keeps a default one-place summary under 20,000 characters. The cost examples include reply drafts.
• 0.1 (2026-10-17): First release. Place URLs, datasets and integrations; themes with verified quotes; fix-first list; monthly trend; location comparison; urgent flags; reply drafts; HTML report and JSON summary; free demo.

---

SignalSift is not affiliated with or endorsed by Google, Amazon, TikTok, Meta or YouTube. Their logos only show which platform each Actor works with.