NYC Data Science Academy| Blog
Bootcamps
Lifetime Job Support Available Financing Available
Bootcamps
Data Science with Machine Learning Flagship ๐Ÿ† Data Analytics Bootcamp Artificial Intelligence Bootcamp New Release ๐ŸŽ‰
Free Lesson
Intro to Data Science New Release ๐ŸŽ‰
Find Inspiration
Find Alumni with Similar Background
Job Outlook
Occupational Outlook Graduate Outcomes Must See ๐Ÿ”ฅ
Alumni
Success Stories Testimonials Alumni Directory Alumni Exclusive Study Program
Courses
View Bundled Courses
Financing Available
Bootcamp Prep Popular ๐Ÿ”ฅ Data Science Mastery Data Science Launchpad with Python View AI Courses Generative AI for Everyone New ๐ŸŽ‰ Generative AI for Finance New ๐ŸŽ‰ Generative AI for Marketing New ๐ŸŽ‰
Bundle Up
Learn More and Save More
Combination of data science courses.
View Data Science Courses
Beginner
Introductory Python
Intermediate
Data Science Python: Data Analysis and Visualization Popular ๐Ÿ”ฅ Data Science R: Data Analysis and Visualization
Advanced
Data Science Python: Machine Learning Popular ๐Ÿ”ฅ Data Science R: Machine Learning Designing and Implementing Production MLOps New ๐ŸŽ‰ Natural Language Processing for Production (NLP) New ๐ŸŽ‰
Find Inspiration
Get Course Recommendation Must Try ๐Ÿ’Ž An Ultimate Guide to Become a Data Scientist
For Companies
For Companies
Corporate Offerings Hiring Partners Candidate Portfolio Hire Our Graduates
Students Work
Students Work
All Posts Capstone Data Visualization Machine Learning Python Projects R Projects
Tutorials
About
About
About Us Accreditation Contact Us Join Us FAQ Webinars Subscription An Ultimate Guide to
Become a Data Scientist
    Login
NYC Data Science Acedemy
Bootcamps
Courses
Students Work
About
Bootcamps
Bootcamps
Data Science with Machine Learning Flagship
Data Analytics Bootcamp
Artificial Intelligence Bootcamp New Release ๐ŸŽ‰
Free Lessons
Intro to Data Science New Release ๐ŸŽ‰
Find Inspiration
Find Alumni with Similar Background
Job Outlook
Occupational Outlook
Graduate Outcomes Must See ๐Ÿ”ฅ
Alumni
Success Stories
Testimonials
Alumni Directory
Alumni Exclusive Study Program
Courses
Bundles
financing available
View All Bundles
Bootcamp Prep
Data Science Mastery
Data Science Launchpad with Python NEW!
View AI Courses
Generative AI for Everyone
Generative AI for Finance
Generative AI for Marketing
View Data Science Courses
View All Professional Development Courses
Beginner
Introductory Python
Intermediate
Python: Data Analysis and Visualization
R: Data Analysis and Visualization
Advanced
Python: Machine Learning
R: Machine Learning
Designing and Implementing Production MLOps
Natural Language Processing for Production (NLP)
For Companies
Corporate Offerings
Hiring Partners
Candidate Portfolio
Hire Our Graduates
Students Work
All Posts
Capstone
Data Visualization
Machine Learning
Python Projects
R Projects
About
Accreditation
About Us
Contact Us
Join Us
FAQ
Webinars
Subscription
An Ultimate Guide to Become a Data Scientist
Tutorials
Data Analytics
  • Learn Pandas
  • Learn NumPy
  • Learn SciPy
  • Learn Matplotlib
Machine Learning
  • Boosting
  • Random Forest
  • Linear Regression
  • Decision Tree
  • PCA
Interview by Companies
  • JPMC
  • Google
  • Facebook
Artificial Intelligence
  • Learn Generative AI
  • Learn ChatGPT-3.5
  • Learn ChatGPT-4
  • Learn Google Bard
Coding
  • Learn Python
  • Learn SQL
  • Learn MySQL
  • Learn NoSQL
  • Learn PySpark
  • Learn PyTorch
Interview Questions
  • Python Hard
  • R Easy
  • R Hard
  • SQL Easy
  • SQL Hard
  • Python Easy
Data Science Blog > Data Visualization > Senti-Meter applied to US Governors

Senti-Meter applied to US Governors

Shivakumar Ranganathan
Posted on Aug 2, 2017

The skills the authors demonstrated here can be learned through taking Data Science with Machine Learning bootcamp with NYC Data Science Academy.

Background

What do you measure with a senti-meter? Sentiments, of course. In recent years, social media outlets have become a platform on which anyone can express emotions publicly. As per the information posted on Pew Research Center, 68 % of US Adults use Facebook, and about 21 % use Twitter. Social Media platforms can be viewed as vast reservoirs filled with information on human emotions. The purpose of this web scraping project is to assess if tweets could be used to measure the approval ratings of US Governors. The main objectives are as follows:

  1. Scrape tweets using Selenium.
  2. Quantify the sentiment in the extracted tweets.
  3. Provide insight on performance as a function of age, party affiliation and gender of governors.
  4. Identify key topics that are of interest to various states.
  5. Rank the governors (states) based on the sentiment analysis and compare the rankings with the recently published Morning Consult Governor Approval rankings.

The subsequent sections present the methodology including which data in the tweets are extracted, visualized and subsequently analyzed to come up with a sentiment score used to rank every governor.

Methodology

The methodology employed in this study is summarized in Figure-1. The first part of the study was focused on scraping tweets. Although, Twitter provides tweets extraction using API, it poses rate limits on a per user basis. Hence, a decision was made to use Selenium for web scraping due to its reliability even though it can be slow at times. To filter out irrelevant tweets from individuals with similar names as the governors, the tweets were sampled only if they had a reference to twitter verified @Governor handle.

For example, the official Twitter handle for the governor of New Jersey is @GovChristie. Once the Twitter handle was identified, it was used as the Twitter search term, and the resulting Uniform Resource Locator (URL) was used to scrape the tweets pertaining to the Governor of New Jersey. Tweets were not directly read from @Governor handle since this may be overwhelmingly positive or neutral.

A similar process was adapted for the governors of the remaining 49 states. The objective was to extract roughly about 50,000 tweets (1000 tweets per governor and 50 states), but the program ended up scraping a total of 43,737 tweets (see Figure-2). This is partly because some of the @Governor handles were not very active on Twitter and generated fewer than 1000 tweets. The extracted tweets were saved in a csv file with a tag name identifying each governor.

Figure-1: Methodology


Figure-2: Visualization of total tweets scrapedโ€”a) by State (top); b) by Governor Name (bottom)

Once the data scraping was complete, postprocessing (Sentiment Analysis and Data Visualization) of the data was done on R-Studio. For the Sentiment Analysis, each tweet was cleaned up (using the functions โ€˜gsubโ€™, โ€˜tolowerโ€™, โ€˜str_splitโ€™) and the individual words were matched with a word repository [1,2] with approximately 2006 positive and 4784 negative words (see Figure-3) to obtain a sentiment score [+1 if positive, 0 if neutral and -1 if negative]. For example, the sentiment analysis function would return the following scores (see TABLE-1)โ€”

TABLE-1: Sentiment Score

Example Tweet Score
โ€œWeb scraping is exciting and funโ€ 2
โ€œWeb scraping is okayโ€ 0
โ€œWeb scraping can be challenging at timesโ€ -1

Figure-3: Some of the positive and negative words included in the word repository

Every tweet had an associated sentiment score that generated a statistical distribution for all the tweets for a governor. This approach was repeated for all the governors, which resulted in fifty sentiment distributions. The mean of every distribution was called the mean sentiment score, which was used to rank the governors. More details can be found in the Source codes posted on GitHub.

Data Visualization & Analysis

Several visualization tools are employed to better understand the effect of each variable on the sentiment score and are discussed as follows:

a) Political landscape: We begin the discussion by first identifying the states with Republican, Democratic or Independent governors. This is best visualized on a US map using the function โ€˜gvisGeoChartโ€™ (see Figure-4). Clearly, there are 16 states with Democratic governors, 33 states with Republican governors and just one state with an independent governor.

Figure-4: Party affiliation of current governors [Republican, Democrat, Independent]

b) Mean Sentiment Score: Keeping Figure-4 as a reference, the mean sentiment score for every governor is plotted on the US map as seen in Figure-5. Green regions in this plot highlight an overall positive sentiment score highlight that the governor is doing well as per the analysis on the tweets. Red regions represent an overall negative sentiment score. Clearly, states like Iowa, Delaware, North Dakota and Utah are doing very well, while states like Minnesota, New York, Connecticut and New Jersey are not doing so well in terms of the sentiment score. This is better visualized using bar plots (Figure-6).

Figure-5: Mean Sentiment Score for current governors

Figure-6: Mean Sentiment Score for current governors (bar chart)

c) Effect of age, gender and party affiliation: With the complete data at our disposal, it is now possible to seek further insight on performance of the governors as a function of various groups [age, party affiliation (Democratic, Independent, Republican) and gender (Male, Female)] as seen in the box plots (Figures-7a,b,c). Under the assumptions of homoscedasticity, sampling independence and normality an ANOVA test was conducted with a null hypothesis claiming similarity between the means of mean sentiment scores between various groups. In each case, the resulting p-value was significantly greater than 0.05, thereby failing to reject the null hypothesis.

Figure-7: Mean Sentiment Score as a function ofโ€”a) Party affiliation (top); b) Gender (middle) and c) Age (bottom)

d) Analysis on the best and worst scores: The stage is now set to examine the tweets of governors with the highest and lowest sentiment scores. For the sake of this blog post, the focus will be only on the tweets of top three and bottom three governors (Even though Minnesota was at the bottom of the list in terms of the sentiment score, it is excluded from discussion in this section since the total number of tweets scraped was only 138, indicating that the sample size may not be representative when compared to other governors).

The resulting word cloud (minimum frequency=25 words) and the distribution of sentiment scores for these governors is plotted in Figure-8. It is interesting focus on the second tallest skyscraper (tower-2) in the distribution. Clearly, for the top governors, tower-2 is on the right side (positive) of zero and for the governors at the bottom, tower-2 is on the left of zero (negative).

Figure-8: Sentiment scores of โ€”a) top three governors (top); b) top three governors (bottom)

e) Keyword search: Using the tweets scraped, it is possible to analyze the specific issues pertinent to individual states. The tweets were mined for four key words: health, tax, education and jobs. The results for the top three states are summarized in TABLE-2. From the analysis, it appears that while Ohio and Kentucky care most about health, Kansas and Idaho are focused on tax. Similarly, education is a high priority to Oklahoma, whereas Alabama and Michigan residents are focused on jobs.

TABLE-2: Keywords that are important to individual states

f) Rankings based on sentiment score and comparison to Morning Consult: TABLE-3 and TABLE-4 highlight the top-10 and bottom-10 list, respectively based on the Mean Sentiment Score. Also included is the governor approval rankings based on an independent study by Morning Consult, who surveyed 195,704 registered U.S. voters from April 1 through July 10 to determine these ranks. It is interesting to note that there is an overlap of 60 % on the top-10 list between Morning Consult and the current study based on tweets. Along similar lines, there is a 30 % overlap in the bottom-10 list with two other rankings being very close.

TABLE-3: Rankings (from top)

TABLE-4: Rankings (from bottom)

Conclusions

We can draw  the following conclusions:

  1. Tweets can be used as a quick way to gauge the approval of governors (screening). It only takes few hours of coding and data processing when compared to conventional polling techniques that require significant funding and resources.
  2. The analysis presented can be further improved by taking inputs from multiple social media platforms, especially Facebook (with 68 % of US adults registered).
  3. Sentiment analysis can also be improved by constantly updating the list of positive and negative words as the society evolves with time.
  4. There is always a segment of population who do not use social media platforms to express emotions. This will have an impact on the data analysis.
  5. It would be interesting to study how predictions change as a function of the sample size of tweets.
  6. This study can be readily extended to gauge the sentiment towards presidents and presidential candidates as well.

About Author

Shivakumar Ranganathan

Shivakumar Ranganathan (Kumar) earned a PhD in mechanical engineering from the University of Illinois at Urbana-Champaign. He has a wide range of interests in Engineering, Medical Implants, Education and Data Science.
View all posts by Shivakumar Ranganathan >

Related Articles

Capstone
Catching Fraud in the Healthcare System
Data Analysis
Car Sales Report R Shiny App
Data Analysis
Injury Analysis of Soccer Players with Python
Capstone
The Convenience Factor: How Grocery Stores Impact Property Values
Capstone
Acquisition Due Dilligence Automation for Smaller Firms

Leave a Comment

Cancel reply

You must be logged in to post a comment.

No comments found.

View Posts by Categories

All Posts 2399 posts
AI 7 posts
AI Agent 2 posts
AI-based hotel recommendation 1 posts
AIForGood 1 posts
Alumni 60 posts
Animated Maps 1 posts
APIs 41 posts
Artificial Intelligence 2 posts
Artificial Intelligence 2 posts
AWS 13 posts
Banking 1 posts
Big Data 50 posts
Branch Analysis 1 posts
Capstone 206 posts
Career Education 7 posts
CLIP 1 posts
Community 72 posts
Congestion Zone 1 posts
Content Recommendation 1 posts
Cosine SImilarity 1 posts
Data Analysis 5 posts
Data Engineering 1 posts
Data Engineering 3 posts
Data Science 7 posts
Data Science News and Sharing 73 posts
Data Visualization 324 posts
Events 5 posts
Featured 37 posts
Function calling 1 posts
FutureTech 1 posts
Generative AI 5 posts
Hadoop 13 posts
Image Classification 1 posts
Innovation 2 posts
Kmeans Cluster 1 posts
LLM 6 posts
Machine Learning 364 posts
Marketing 1 posts
Meetup 144 posts
MLOPs 1 posts
Model Deployment 1 posts
Nagamas69 1 posts
NLP 1 posts
OpenAI 5 posts
OpenNYC Data 1 posts
pySpark 1 posts
Python 16 posts
Python 458 posts
Python data analysis 4 posts
Python Shiny 2 posts
R 404 posts
R Data Analysis 1 posts
R Shiny 560 posts
R Visualization 445 posts
RAG 1 posts
RoBERTa 1 posts
semantic rearch 2 posts
Spark 17 posts
SQL 1 posts
Streamlit 2 posts
Student Works 1687 posts
Tableau 12 posts
TensorFlow 3 posts
Traffic 1 posts
User Preference Modeling 1 posts
Vector database 2 posts
Web Scraping 483 posts
wukong138 1 posts

Our Recent Popular Posts

AI 4 AI: ChatGPT Unifies My Blog Posts
by Vinod Chugani
Dec 18, 2022
Meet Your Machine Learning Mentors: Kyle Gallatin
by Vivian Zhang
Nov 4, 2020
NICU Admissions and CCHD: Predicting Based on Data Analysis
by Paul Lee, Aron Berke, Bee Kim, Bettina Meier and Ira Villar
Jan 7, 2020

View Posts by Tags

#python #trainwithnycdsa 2019 2020 Revenue 3-points agriculture air quality airbnb airline alcohol Alex Baransky algorithm alumni Alumni Interview Alumni Reviews Alumni Spotlight alumni story Alumnus ames dataset ames housing dataset apartment rent API Application artist aws bank loans 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 boston safety Bundles cake recipe California Cancer Research capstone car price Career Career Day ChatGPT citibike classic cars classpass clustering Coding Course Demo Course Report covid 19 credit credit card crime frequency crops D3.js data data analysis Data Analyst data analytics data for tripadvisor reviews data science Data Science Academy Data Science Bootcamp Data science jobs Data Science Reviews Data Scientist Data Scientist Jobs data visualization database Deep Learning Demo Day Discount disney dplyr drug data e-commerce economy employee employee burnout employer networking environment feature engineering Finance Financial Data Science fitness studio Flask flight delay football gbm Get Hired ggplot2 googleVis H20 Hadoop hallmark holiday movie happiness healthcare frauds higgs boson Hiring hiring partner events Hiring Partners hotels housing housing data housing predictions housing price hy-vee Income industry Industry Experts Injuries Instructor Blog Instructor Interview insurance italki Job Job Placement Jobs Jon Krohn JP Morgan Chase Kaggle Kickstarter las vegas airport lasso regression Lead Data Scienctist Lead Data Scientist leaflet league linear regression Logistic Regression machine learning Maps market matplotlib Medical Research Meet the team meetup methal health miami beach movie music Napoli NBA netflix Networking neural network Neural networks New Courses NHL nlp NYC NYC Data Science nyc data science academy NYC Open Data nyc property NYCDSA NYCDSA Alumni Online Online Bootcamp Online Training Open Data painter pandas Part-time performance phoenix pollutants Portfolio Development precision measurement prediction Prework Programming public safety PwC python Python Data Analysis python machine learning python scrapy python web scraping python webscraping Python Workshop R R Data Analysis 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 seafood type Selenium sentiment analysis sentiment classification Shiny Shiny Dashboard Spark Special Special Summer Sports statistics streaming Student Interview Student Showcase SVM Switchup Tableau teachers team team performance TensorFlow Testimonial tf-idf Top Data Science Bootcamp Top manufacturing companies Transfers tweets twitter videos visualization wallstreet wallstreetbets web scraping Weekend Course What to expect whiskey whiskeyadvocate wildfire word cloud word2vec XGBoost yelp youtube trending ZORI

NYC Data Science Academy

NYC Data Science Academy teaches data science, trains companies and their employees to better profit from data, excels at big data project consulting, and connects trained Data Scientists to our industry.

NYC Data Science Academy is licensed by New York State Education Department.

Get detailed curriculum information about our
amazing bootcamp!

Please enter a valid email address
Sign up completed. Thank you!

Offerings

  • HOME
  • DATA SCIENCE BOOTCAMP
  • ONLINE DATA SCIENCE BOOTCAMP
  • Professional Development Courses
  • CORPORATE OFFERINGS
  • HIRING PARTNERS
  • About

  • About Us
  • Alumni
  • Blog
  • FAQ
  • Contact Us
  • Refund Policy
  • Join Us
  • SOCIAL MEDIA

    ยฉ 2025 NYC Data Science Academy
    All rights reserved. | Site Map
    Privacy Policy | Terms of Service
    Bootcamp Application