SCIENCE@home

Review content and customer satisfaction: a textual analysis of Yelp restaurant reviews

Emitis Alikhani,Hassan F. Gholipour,Hossein Abbasinejad,Ramtin Rafat Nezhad

Published 2025 in British Food Journal

ABSTRACT

This study aims to pinpoint which observable restaurant attributes most influence customer satisfaction, captured through review sentiment and star ratings. We analyze 580,000 Yelp reviews from 36,000 US restaurants (2019). Seven feature groups – services, ambience, amenities, alcohol, payment, menu breadth and entertainment – are regressed on average Valence Aware Dictionary and Sentiment Reasoner scores, AFINN (a sentiment lexicon used to evaluate emotional tone in text by assigning numerical values to individual words)-based positivity odds and mean star ratings, using restaurant, city and state fixed effects. Adding one core service (delivery, table service) lifts average sentiment by ˜ 0.02 points and star ratings by ˜ 0.10 stars. Modest ambience upgrades also help, though less. Extra amenities, wider payment menus, or broader food lists yield no further gains once basics are covered; in a few cases, they slightly depress ratings. The results show clear threshold benefits and sharp diminishing returns, aligning with utility theory for experience goods. Restaurants should invest in reliable service and a pleasant setting rather than piling low-impact extras. Review platforms and regulators might spotlight these core indicators instead of long attribute checklists. This is the first national-scale evidence linking verified feature flags to both text sentiment and star ratings while jointly testing threshold and diminishing-return effects in dining markets.

PUBLICATION RECORD

CITATION MAP

EXTRACTION MAP

CLAIMS

  • No claims are published for this paper.

CONCEPTS

  • No concepts are published for this paper.

REFERENCES

Showing 1-28 of 28 references · Page 1 of 1

CITED BY

  • No citing papers are available for this paper.

Showing 0-0 of 0 citing papers · Page 1 of 1