Understanding Customer Perceptions: Topic Modeling Analysis of Toronto Specialty Coffee Shop Online Reviews
Bibliographic record
Abstract
The specialty coffee shop market in Toronto has become increasingly competitive, making it essential for business owners to understand the factors that drive customer satisfaction and differentiation.This study aims to identify the main themes expressed in Google Maps reviews of Toronto's specialty coffee shops over the past year, providing actionable insights for entrepreneurs and industry stakeholders.Over 5000 customer reviews were analyzed using BERTopic (Bidirectional Encoder Representations from Transformers Topic), a state-of-the-art topic modeling approach that leverages contextual language understanding to extract clear and meaningful topics from large volumes of text.The analysis revealed distinct positive themes, such as cozy atmospheres and high-quality coffee, as well as negative aspects like unfriendly service and poor value for money.By correlating these topics with review ratings, the study highlights specific opportunities for improvement and differentiation in the market.These findings offer practical value for business planning, enabling coffee shop owners to make data-driven decisions and enhance customer experiences in a crowded urban landscape.Beyond its local insights, this research introduces a scalable analytical framework that can be applied to market research, business planning, and feasibility studies in diverse sectors, empowering others to extract actionable intelligence from large volumes of unstructured textual data.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.002 | 0.010 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.003 | 0.003 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.002 | 0.001 |
| Open science | 0.000 | 0.001 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".