Local Review Intelligence Monitor

Local Review Intelligence Monitor

Turn raw local-business reviews into complaint themes, praise themes, urgency scores, and owner-response actions. This Actor is designed for Google Maps, Yelp, TripAdvisor, Booking, Facebook, and other review records collected by Apify Actors or supplied inline.

Instead of returning another spreadsheet of review text, it gives agencies and operators a clean action dataset: what customers complain about, what they praise, which reviews need attention, and what to do next.

Workflow Hub

See the public review intelligence workflow for the scraper dataset -> analyzer path, demo story, and links across the review-intelligence Actors. Local SEO teams can start from the local review response queue use case. For the first run, use that sample path and the proof GIF showing local reviews becoming a response queue.

What You Learn

• Which reviews are positive, negative, or mixed
• Which themes keep appearing: service, wait time, price, quality, delivery, availability, and experience
• Which complaints deserve urgent follow-up
• Which positive reviews can become local landing-page or ad proof
• What action to take for each review

Use Cases

• Weekly reputation monitoring for local SEO clients
• Multi-location complaint triage for franchises
• Owner-response prioritization for agencies
• Local landing-page proof mining from positive reviews
• Review exports to Google Sheets, Slack, dashboards, or reporting decks

Input

You can provide reviews inline or pass an Apify datasetId from another review scraper.

{
  "businessName": "Northstar Dental",
  "sourceName": "Google Maps",
  "reviews": [
    {
      "rating": 1,
      "text": "The staff was rude and the wait was terrible.",
      "authorName": "Example Customer",
      "date": "2026-05-01"
    }
  ],
  "maxReviews": 100,
  "includeRawReview": true
}

Output

Each dataset item is one analyzed review:

{
  "status": "succeeded",
  "recordIndex": 1,
  "billingEventName": "local-review-analyzed",
  "businessName": "Northstar Dental",
  "sourceName": "Google Maps",
  "rating": 1,
  "sentimentLabel": "negative",
  "sentimentScore": -100,
  "detectedThemes": ["service", "wait_time"],
  "complaintThemes": ["service", "wait_time"],
  "urgencyScore": 95,
  "recommendedAction": "Audit staff response patterns for Northstar Dental; service complaints are driving visible review risk.",
  "analyzedAt": "2026-05-12T12:00:00+00:00"
}

The run also writes a SUMMARY key-value-store record with analyzed counts, sentiment counts, theme counts, and the charge event name.

FAQ

Does this scrape review sites?

No. It analyzes review records you provide inline or through an Apify dataset from another Actor. It is designed for Google Maps, Yelp, TripAdvisor, Booking, Facebook, and similar local-review records.

What input do I need for the first run?

Use the Store example with businessName, sourceName, and one or more review records. Review text is required; ratings improve sentiment and urgency scoring.

What do I get back?

One dataset item per analyzed review, including sentiment, detected themes, urgency, and recommended next action. The run also writes a SUMMARY record.

Who is this for?

Local SEO agencies, reputation managers, franchises, and multi-location operators that need recurring review triage and reporting.

When is it commercially chargeable?

The configured paid event is local-review-analyzed at $0.015, scheduled for 2026-05-26T21:05:10Z. Run a small paid smoke after activation before promoting high-volume use.

Pricing

Default monetization model: pay per event.

Recommended chargeable event:

• Event name: local-review-analyzed
• Event meaning: one successfully analyzed review
• Store price: $0.015 per analyzed review
• Pricing activation: scheduled for 2026-05-26T21:05:10Z

Successful rows are pushed only after the charge path allows the event. Run a paid smoke after the scheduled activation time before promoting the listing.

Limitations

• This MVP analyzes review records; it does not scrape Google Maps, Yelp, TripAdvisor, or Booking directly.
• Review source schemas vary. The Actor recognizes common fields such as text, reviewText, rating, stars, authorName, and date.
• Theme detection is deterministic and intentionally explainable. It is built for reliable monitoring, not black-box sentiment theater.

Automation And Agent Use

• Run a review scraper first, then pass its dataset ID to this Actor.
• Schedule weekly analysis for each client or location group.
• Send negative high-urgency reviews to Slack or a ticketing queue.
• Append sentimentLabel, detectedThemes, and recommendedAction to Google Sheets for client reporting.

Local Development

python3 -m pip install -r requirements.txt
ACTOR_TEST_PAY_PER_EVENT=true apify run --purge --input-file examples/smoke-input.json