Yelp reviews are one of the most useful resources people rely on in their hunt for cuisines, dishes and restaurants. Yu et al. [1] mentions independent restaurants can expect almost 59% bump in revenue with a 1-star increase in rating. Natural language processing and machine learning can be applied to extract actionable insights from the customer reviews about their experiences. If restaurant owners can gauge user sentiment about their restaurant, areas where their business is lacking, which dishes are doing well and what users are saying about their competitors - they can take appropriate steps to improve their business.
TL;DR
- Negative Aspect modeling
This project aims to analyze restaurant reviews on Yelp via topic modeling to determine aspects of restaurant that users dislike. - Restaurant Segmentation
We will also try to capture segments of restaurants in a city based on cuisines, restaurant attributes, popularity and customer sentiment using clustering techniques.
Read this writeup for more info
Link to the Tableau Dashboard
- Yu, Boya, Jiaxu Zhou, Yi Zhang, and Yunong Cao. “Identifying Restaurant Features via Sentiment Analysis on Yelp Reviews.” arXiv preprint arXiv:1709.08698 (2017).
Please reach out to arsaikia@iu.edu for questions and feedback.