See reports

How to Turn Google Reviews Into an AI Action Plan

To turn Google reviews into insight, point the Google Reviews Insights actor at the output of a Google Maps reviews scraper (a datasetId) or hand it Maps place URLs and let it fetch the reviews first. It finds recurring praise and complaint themes, tracks how ratings move over time, and writes a ranked action plan per place. In compare mode it adds a competitor table and a where-you-win / where-you-lose readout. It never reproduces full reviews or reviewer names.

Steps
  1. Get a reviews dataset (or gather URLs). Run any Google Maps reviews scraper (e.g. compass/google-maps-reviews-scraper) and copy its dataset ID into 'datasetId' - one review per item. Alternatively, skip that and just collect the Google Maps place URLs you want analyzed.
  2. Open the actor and provide one input. Open noniner/google-reviews-insights on Apify and set either 'datasetId' (your scraped reviews) or 'placeUrls' (Maps URLs). If you pass placeUrls, this actor runs the Maps scraper for you - note that scraper run is billed separately to your own Apify account.
  3. Choose single or compare mode. Set 'mode' to 'single' to analyse each place on its own, or 'compare' to also build a competitor table and a where-you-win / where-you-lose readout for the first place in your list. Set maxReviewsPerPlace (default 300, newest first) and outputLanguage (e.g. en, sv).
  4. Run it. Click Start. The actor groups reviews by place, computes ratings, per-quarter trends and owner-response stats in code, then uses OpenAI to summarise themes and write the ranked action plan.
  5. Read and export the insights. Each place record returns topPraises, topComplaints (each with an approximate share and a short paraphrased example), a trend with per-quarter ratings, unansweredNegativeShare, a ranked actionPlan and an executiveSummary. Export to JSON, CSV or Excel, or pull via the API.
Frequently asked questions

Does this actor scrape the reviews itself?

It can either way. Pass a datasetId from any Google Maps reviews scraper and it just analyses those, or pass placeUrls and it will run compass/google-maps-reviews-scraper for you first. In the second case that scraper run is billed separately to your own Apify account.

Will it quote reviews or expose reviewer names?

No. By design it never reproduces a full review verbatim and never includes a reviewer's name - reviewer names are dropped before anything is sent to the AI, and all examples are short paraphrases.

How do I compare my business against competitors?

Set mode to 'compare' and list your business first followed by 2-4 rivals (as placeUrls, or as places within your dataset). You get an extra record with a comparisonTable across places plus whereYouWin and whereYouLose for the first place.

Why is the trend or unansweredNegativeShare empty?

Trend buckets need dated reviews; if the source data lacks dates or has too few, trend.byQuarter is empty and the summary says so. unansweredNegativeShare requires the scraper to include owner-response fields - otherwise it is null.

What does it cost?

Pay-per-event: a 'place-analyzed' event once per place that produces a full report, plus a 'reviews-processed' event per 100 reviews sent to the AI (rounded up). Prices are tuned to cover the OpenAI token cost with margin on gpt-4o-mini; any Maps scraper run you trigger is billed separately.

Related
Try it now

Run it on Apify — no install, results in minutes.

Open on Apify