A Look at New York City Restaurants

Manasa Godkhindi
Posted on Dec 15, 2017


Social data provides important, real-time insights on consumer opinion – on lifestyle, habits, brands, and preferences. Because these opinions are unsolicited, they provide genuine insight into consumer feelings, and, as such, they should be valued. Zomato, a research search and discovery website provides  information and reviews on restaurants. This blog provides an insights on the restaurant ratings and their services in Manhattan neighborhood.

I obtained data scraping data from Zomato. Data from dynamic web pages were fetched using Selenium. Data cleansing was done in python. Visualization and analysis including sentiment analysis was done using R. Analysis was portrayed using an interactive app built in shiny.

Research Questions

1. Does location have an impact on the pricing of the food?
2. Impact of rating based on reviews.
3. Customer opinion based on the reviews.
4. Emotions of customers towards restaurants.
5. What are the major concerns of customers?


Analysis - Cost, Rating, Location

Overall rating of restaurants are binned into 3 categories of excellent,good and average. Below plot is the representation of top 30 restaurants in Manhattan neighborhood based on their ratings.

Restaurants neighborhood do  have a say in the cost of the restaurants.Midtown and Gramecy-Flatiron neighborhood have high priced restaurants. Midtown is heart of abundant activity and a tourist heaven which justifies the high pricing.

Based on the analysis, Michelin starred restaurants and restaurants with added features like full bar,  private lounge also attributed to the high costs.

Sentiment Analysis

Sentiment Analysis, also known as opinion mining, is the process of determining whether a text unit is positive or negative. It can have a wide range of applications such as automatically detecting feedback towards products, news and characters or improving customers’ relation model.

To further analyze the sentiments of the customers, sentiment analysis was performed on the review.Words in each review were separated and the punctuation were removed so that a “bag of words” was generated for each review. Finally, we stemmed and filtered out the stop words.

Reviews were scored for different emotions like happy, sad, anger, frustration and also the polarity(positive and negative).

From the negative word lists, it can be observed that wait and crowd is really a taboo when it comes to restaurants. In addition, we can also conclude that restaurants should improve on their hospitality.

Friendly is one of the word that stood out in most of the positive reviews indicating the service of restaurants seems to be the priority for most customers

Below word clouds provides insights on the most commonly used terms in the positive and the negative reviews.


An interactive app  of the breakdown by cuisines and restaurants is available in my Shiny App.


Based on the analysis, metrics can be used by restaurants in improving hospitality, competitive pricing. Also restaurants considering opening in a specific neighborhood could use these insights to help them differentiate themselves from competitors.

A deeper study can be done using Aspect based analysis on the reviews to gather more information.



About Author

Related Articles

Leave a Comment

No comments found.

View Posts by Categories

Our Recent Popular Posts

View Posts by Tags

#python #trainwithnycdsa 2019 airbnb Alex Baransky alumni Alumni Interview Alumni Reviews Alumni Spotlight alumni story Alumnus API Application artist aws beautiful soup Best Bootcamp Best Data Science 2019 Best Data Science Bootcamp Best Data Science Bootcamp 2020 Best Ranked Big Data Book Launch Book-Signing bootcamp Bootcamp Alumni Bootcamp Prep Bundles California Cancer Research capstone Career Career Day citibike clustering Coding Course Demo Course Report D3.js data Data Analyst data science Data Science Academy Data Science Bootcamp Data science jobs Data Science Reviews Data Scientist Data Scientist Jobs data visualization Deep Learning Demo Day Discount dplyr employer networking feature engineering Finance Financial Data Science Flask gbm Get Hired ggplot2 googleVis Hadoop higgs boson Hiring hiring partner events Hiring Partners Industry Experts Instructor Blog Instructor Interview Job Job Placement Jobs Jon Krohn JP Morgan Chase Kaggle Kickstarter lasso regression Lead Data Scienctist Lead Data Scientist leaflet linear regression Logistic Regression machine learning Maps matplotlib Medical Research Meet the team meetup Networking neural network Neural networks New Courses nlp NYC NYC Data Science nyc data science academy NYC Open Data NYCDSA NYCDSA Alumni Online Online Bootcamp Online Training Open Data painter pandas Part-time Portfolio Development prediction Prework Programming PwC python Python Data Analysis python machine learning python scrapy python web scraping python webscraping Python Workshop R R language R Programming R Shiny r studio R Visualization R Workshop R-bloggers random forest Ranking recommendation recommendation system regression Remote remote data science bootcamp Scrapy scrapy visualization seaborn Selenium sentiment analysis Shiny Shiny Dashboard Spark Special Special Summer Sports statistics streaming Student Interview Student Showcase SVM Switchup Tableau team TensorFlow Testimonial tf-idf Top Data Science Bootcamp twitter visualization web scraping Weekend Course What to expect word cloud word2vec XGBoost yelp