Automation Development
Google Maps → Find Businesses with Unreplied Negative Reviews (For Review Removal Service)
Built an n8n automation that identifies businesses with recent negative Google reviews they never responded to — creating highly qualified leads for a review-removal service.
Google Maps → Find Businesses with Unreplied Negative Reviews (For Review Removal Service)
/
Background
The client ran a service focused on fixing and removing negative Google reviews, but prospecting required hours of manual searching across Google Maps. I designed a full automation that scrapes local businesses via Apify, reads and analyzes review patterns, detects low ratings and unanswered negative feedback, ranks the highest-risk profiles, and stores everything neatly in Google Sheets for targeted outreach — so instead of guessing, the team now focuses only on businesses clearly struggling with reputation issues and most likely to convert.
1
2
3
4
5
6
Challenges
Google Maps data is massive and noisy, so the system had to detect only recent, unreplied negative reviews, avoid duplicates across runs, keep Google Sheets clean for non-technical sales teams, and continuously filter leads in a cost-efficient way while ignoring low-value profiles that already received responses.
Audit & System Review
Before building, I mapped the lifecycle — prospect discovery, review scoring, detection of unreplied negative reviews, and export to outreach sheets — then studied Apify’s Google Maps scraper fields (totalScore, reviews, reviewsDistribution, placeId, googleMapsUrl, etc.) to define filters, thresholds, and exactly which data needed to be stored for later decisions.
Solution Architecture
Built with n8n, Apify’s Google Maps scraper, custom JavaScript filters, and Google Sheets, the workflow runs automatically — scraping businesses, processing datasets, qualifying prospects based on negative reviews, and saving prioritized leads with context for outreach.
Implementation
I built qualification logic that pulls only businesses with 10+ reviews, isolates 1–3 star feedback, removes cases where the owner already replied, sorts leads by the newest negative review, and outputs two synchronized datasets — a Business sheet (name, location, rating, total reviews, link, worst recent review summary, price, contact data) and a Reviews sheet (business, review text, stars, link, date, city). Businesses are upserted to prevent duplicates, while reviews are appended historically for context.
Documentation & Handover
I delivered step-by-step documentation, explained each node, showed how to change locations, categories, and niches, covered cost-control settings, and trained the sales team on how to use the data — so the client can now modify the workflow and operate it confidently without needing engineering support.
Results & Impact
The automation shifted the business from guesswork to targeted outreach — instead of wondering who might need help, the team now instantly sees which businesses have multiple fresh 1-star reviews with no replies, making sales conversations more relevant, lead generation predictable, and overall prospect quality dramatically higher.
Project Scope
Identify businesses with 1–3 star reviews without owner responses, extract leads, and organize actionable outreach data.
By the Numbers
Discover the impact of our projects through measurable results, showcasing the improvements in user engagement, conversion rates, and overall user satisfaction.
70%
Time Saved
35%
Productivity Increase
30%
Money Saved
30%
Increase in User Retention