Written one- and two-star Google reviews of at least five words, up to 60 per business, from high-review-count pest control companies in eight US metros. A language model, with no human-coded check, classified the main reason in 5,451 of them: 76.7 percent how the business is run, 21.8 percent the pest treatment itself, 1.5 percent unclear.
The study covers 5,455 written one- and two-star Google reviews of at least five words, drawn from the up-to-60 lowest-rated reviews retrieved per business, from 270 high-review-count pest control companies in Phoenix, Dallas, Atlanta, Charlotte, Columbus, Denver, Tampa and Kansas City. In each metro, up to 200 listings were screened and, after filters including a cap of two locations per brand, the 40 businesses with the most Google reviews were sampled. Exclusions then left 303 businesses, of which 270 have reviews in the corpus. Review dates run from 2009-09-23 to 2026-09-30. A separate multi-label model pass assigned at least one business-process label to 88.4 percent of the 5,455 reviews.
Every figure below states its denominator. None of them is a share of customers.
The model-classified main reason
The main-reason pass was run by a language model, Claude Haiku 4.5, which chose between how the business is run, the pest treatment itself, and unclear. It classified 5,451 of the 5,455 reviews.
| Model-classified main reason | Share of the 5,451 reviews labelled by the main-reason pass |
|---|---|
| How the business is run | 76.7% |
| The pest treatment itself | 21.8% |
| Unclear | 1.5% |
A second model, Claude Sonnet 4.5, classified 200 of the same reviews. On the binary question of how the business is run against every other main reason, the two models agreed on 93.5 percent of the 200, with a Cohen’s kappa of 0.845 (95 percent confidence interval 0.76 to 0.92). It is not validation against human coding, and no sample was checked against human coding.
Process and the treatment, counted label by label
A separate pass assigned theme labels, and a review can carry more than one. Some describe the business process, such as communication, billing or scheduling. Others describe the treatment and the service visit. A single review can carry both kinds.
| What the labels cover | Share of the 5,455 reviews |
|---|---|
| A business-process label only | 44.5% |
| Both a process label and a core-service label | 43.8% |
| A core-service label only | 8.9% |
| Neither a process nor a core label | 2.7% |
The model assigned at least one core-service label to 52.8 percent of the 5,455 reviews. The multi-label pass and the main-reason pass answer different questions. One asks what a review mentions, the other asks what the model classified as the main reason, and the two are not reconciled review by review.
The model-assigned themes
The table lists every label in the taxonomy. These are themes a model assigned to what reviewers wrote, not verified events. A review can carry several labels. The shares overlap and are not summed.
| Model-assigned theme | Share of the 5,455 reviews |
|---|---|
| Communication failure | 40.6% |
| Service quality | 36.0% |
| Billing and pricing | 30.9% |
| Treatment effectiveness | 30.9% |
| Scheduling reliability | 28.7% |
| Sales conduct | 23.6% |
| Contract and cancellation | 22.0% |
| Staff conduct | 14.7% |
| Other | 5.0% |
Communication failure
The model assigned the communication failure label to the largest share, 40.6 percent of the 5,455 reviews. It is also one of the two catch-all process labels in the taxonomy. The two excerpts quoted here describe calls that were not returned or not answered.
“I called twice to have them put back up and was told a manager would call me back. I never received a call back”
“When I tried calling their office as an existing customer, no one would pick up.”
In both quoted excerpts, the reviewer describes trying to reach the company and not getting a response.
Billing and pricing
The model assigned the billing and pricing label to 30.9 percent of the 5,455 reviews. In the two examples here, one reviewer describes a promised refund and the other describes price increases without notice.
“they admitted that they had not done the service and promised a refund. A month later, they broke that promise and refused to provide a refund.”
“we always have an issue with billing, prices increase and no notifucation on my bill”
The study did not check any bill or account. These are the reviewers’ accounts of what happened.
Contract and cancellation
The model assigned the contract and cancellation label to 22.0 percent of the 5,455 reviews. The quoted excerpts describe a charge to end a contract and an attempted charge after a written cancellation.
“the company charged me $181 to end the contract”
“attempted to continue charging me- even after I had cancelled my membership in writing”
The amount in the first quote is the reviewer’s own figure. The study did not read any contract and makes no finding about contract terms.
Sales conduct
The model assigned the sales conduct label to 23.6 percent of the 5,455 reviews. The label covers sales contact at the door or by phone. Both quoted excerpts describe a sales approach that continued after the reviewer said no.
“Keep coming to my door when I tell them I’m not interested and have a no solicitation sign.”
“I stated several times that we were not interested in pest control services, yet the representative continued the sales pitch”
The study did not measure how many of these reviewers were customers of the company they reviewed.
Disclosure: this study was produced by Sales Roadmaps, which sells operations consulting services. About the operations consulting service
The number that keeps this honest
The 303 businesses sampled after exclusions hold 342,511 lifetime Google reviews between them. Of those, 13,118, or 3.8 percent, are one or two stars, and 93.0 percent are five stars. Of the 303, 270 have at least one review in the corpus studied here.
Percentages in this study use the denominator stated with each figure. Main-reason shares are of the 5,451 reviews the main-reason pass labelled. Label shares are of all 5,455 reviews. The base rate and the five-star share are of all 342,511 lifetime reviews. None of them is a share of customers.
Operational questions these reviews raise
These are questions for an owner reviewing their own operation. They are not findings. The study reports what reviewers wrote and how models labelled those reviews. Related reading on Sales Roadmaps covers service agreements, membership programs and CRM setup.
Who owns the callback?
The model assigned the communication failure label to 40.6 percent of the 5,455 reviews. The quoted examples describe a callback that did not come and calls that went unanswered, and the study did not count those situations separately. An owner can ask who is assigned a promised callback and whether it is recorded.
How are price changes and refunds communicated?
The model assigned the billing and pricing label to 30.9 percent of the 5,455 reviews. The quoted examples describe a promised refund and a price increase without notice, situations the study did not count separately. An owner can ask how a price change or a refund promise is communicated and tracked.
What happens after a cancellation request or a refusal?
The model assigned the contract and cancellation label to 22.0 percent of the 5,455 reviews and the sales conduct label to 23.6 percent. The quoted examples describe an attempted charge after a cancellation and sales contact after a refusal. An owner can ask how cancellations and refusals are recorded.
How the study was done
Google reviews were retrieved through the DataForSEO business data API, sorted by lowest rating, up to 60 per business. In each of the eight metros, up to 200 listings were screened. After filters, the 40 businesses with the most reviews per metro were sampled, with at most two locations per brand. Seventeen businesses were excluded after their names were read: 15 wildlife-removal-only companies and 2 retail stores selling do-it-yourself products.
Excluding those companies did not remove all wildlife or trapping vocabulary. In 3.2 percent of the 5,455 reviews, 177 in total, the text still matches a case-insensitive keyword pattern for wildlife or trapping vocabulary (raccoon, squirrel, opossum, possum, bat, bats, snake, skunk, armadillo, trap, trapped, trapping). That is a keyword match, and what each of those reviews is about was not checked.
The corpus consists of the retrieved reviews rated one or two stars with at least five words, after exclusions and deduplication. Identical review texts posted under two listings were counted once, which removed 5 reviews. Candidate review-theme codes were proposed by a language model, Google Gemini 3.1 Flash-Lite, on a seeded sample of 200 reviews, and the research team consolidated them into a fixed label set.
Labels were then assigned by the same model. A second model, DeepSeek V3.2, relabelled 200 reviews and agreed on process against not process in 96.5 percent of them, with a kappa of 0.825. Each label was asked to carry a verbatim span from the review, and 96.0 percent of labels carry one. The rest are counted without a span.
As a label-based sensitivity test, which is not a main-reason result, the two catch-all process labels, staff conduct and communication failure, were ignored. On that basis, 72.0 percent of the 5,455 reviews still carry at least one process label. Reweighted by each business’s lifetime one- and two-star count, the any-label process share is 91.9 percent. With equal weight per business it is 86.1 percent.
The stored review data carry a business key, the star rating, the date, the text and an owner-reply flag only. No reviewer names were stored. No reviewer or reviewed business is named in this article, and the quotes carry no reviewer names, review dates or ratings.
Limitations
Google reviews are self-selected. The sample covers high-review-count businesses in eight metros: after filters including a cap of two locations per brand, the 40 businesses per metro with the most Google reviews among up to 200 listings screened, before exclusions. Review dates run from 2009-09-23 to 2026-09-30, and the sample is sorted by rating, not by date, so the study makes no claim about trends over time.
All labels and main reasons were assigned by language models, and no sample was checked against human coding.
Contact: Get in touch with Sales Roadmaps
Frequently Asked Questions
In this study, which model-assigned themes are most common?
Communication failure, which the model assigned to 40.6 percent of the 5,455 reviews studied. Service quality follows at 36.0 percent, and billing and pricing and treatment effectiveness at 30.9 percent each. A review could receive more than one label, so these shares should not be summed.
In this study, what share of reviews was classified as mainly about the pest treatment itself?
In the main-reason classification, 21.8 percent of the 5,451 labelled reviews were assigned to the pest treatment itself and 76.7 percent to how the business is run. At least one core-service label was assigned to 52.8 percent of the 5,455.
In this study, how often did the model assign the sales conduct label?
The model assigned the sales conduct label to 23.6 percent of the 5,455 reviews. The label covers sales contact at the door or by phone.
Among the businesses sampled, what share of all reviews are one or two stars?
Among the 342,511 lifetime reviews held by the 303 businesses sampled, 3.8 percent are one or two stars and 93.0 percent are five stars. That is a share of reviews, not of customers.
How closely did the models agree?
On the binary main-reason question, how the business is run against every other main reason, a second model agreed on 93.5 percent of 200 reviews, kappa 0.845. For the theme labels, process against not process, a separate second model agreed on 96.5 percent of 200 reviews, kappa 0.825. No sample was checked against human coding.
Does the study verify whether what reviewers wrote is true?
No. It reports what reviewers wrote and how often the model assigned each theme. No bill, contract or treatment was checked against company records.
Related studies
- The negative dental reviews study
- The negative plumbing reviews study
- The negative electrician reviews study
- The negative law firm reviews study
- The negative auto repair reviews study
- The HVAC profit benchmark review
- The negative veterinary reviews study
- The negative moving company reviews study
- The negative towing company reviews study
- The negative property management reviews study
- The negative gym reviews study
