A Longitude Study of Global Warming Discussion on Social Media

Submission information

Submission Number: 172

Submission ID: 3941

Submission UUID: 68301537-b21f-4e18-a2f2-87f036821ebe

Submission URI: /form/project

Created: Mon, 08/21/2023 - 05:54

Completed: Mon, 08/21/2023 - 06:01

Changed: Fri, 03/29/2024 - 13:43

Remote IP address: 146.75.253.174

Submitted by: Gaurav Khanna

Language: English

Is draft: No

Webform: Project

Project Title A Longitude Study of Global Warming Discussion on Social Media

Program CAREERS

Project Image

Tags big-data (4), data-analysis (422), data-science (688)

Status Complete

Project Leader

Project Leader Suhong Li

Email sli@bryant.edu

Mobile Phone {Empty}

Work Phone {Empty}

Project Personnel

Mentor(s) Suhong Li

Student-facilitator(s) Connor Emery

Mentee(s) {Empty}

Project Information

Project Description I have collected 28 million tweets using keyworks global warming between 2010 and 2022. This project focuses on people’s perception toward global warming and how the perception has changed over the year. Especially, the following topics will be explored: 1). Sentiment analysis: analyzing the sentiment of tweets related to global warming to understand public attitude and emotions toward issues over the past decade; 2) User Demographics and Global Warming Tweets: Analyzing the demographic characteristics of users tweeting about global warming to identify patterns in engagement based on gender, location, etc. 3) Social Network Analysis of Global Warming Discourse: Examining the network structures and interactions among users discussing global warming on Twitter to identify influential users, communities, and patterns of information flow. 4) Political Divide on Global Warming: Explore the influence of political polarization on public opinion and climate policy approaches related to global warming.

The student will learn from start to finish using various data analytic methodologies including sentiment/emotion analysis, topic modelling, network analytics, natural language processing and machine learning/deep learning. Due to the big size of the tweets, I plan to run this analysis on an HPC environment and the student is expected to learn to use UNITY and to execute code in a HPC environment. The student facilitator will learn how to make effective use of the UMass-URI UNITY cluster and will leverage the workflow developed previously by students who were supported by CAREERS.

Project Information Subsection

Project Deliverables {Empty}

Student Research Computing Facilitator Profile {Empty}

Mentee Research Computing Profile {Empty}

Student Facilitator Programming Skill Level {Empty}

Mentee Programming Skill Level {Empty}

Project Institution Bryant University

Project Address {Empty}

Anchor Institution CR-University of Rhode Island

Preferred Start Date {Empty}

Start as soon as possible. No

Project Urgency Already behind3Start date is flexible

Expected Project Duration (in months) 6

Launch Presentation

Careers.project.launch_Emery_Revised.pptx (1.01 MB)

Launch Presentation Date {Empty}

Wrap Presentation

ConnorEmery_CAREERSwrap.pdf (1.33 MB)

Wrap Presentation Date {Empty}

Project Milestones

Milestone Title: Milestone #1
Milestone Description: The student reviews relevant literature and learn about ML, NLP and other needed libraries/packages. Set up HPC Access and project on github. Launch presentation.
Completion Date Goal: 2023-10-31
Milestone Title: Milestone #2
Milestone Description: The student reviews the twitter data set and formats the data for use by the ML, NLP, etc. software.
Completion Date Goal: 2023-11-30
Milestone Title: Milestone #3
Milestone Description: Student performs extensive analysis of the formatted data using ML and NLP techniques. The following trends will be studied:
Sentiment/emotion analysis: analyzing the sentiment/emotion of tweets related to global warming to understand public attitude and emotions toward issues over the past decade;
User Demographics and Global Warming Tweets: Analyzing the demographic characteristics of users tweeting about global warming to identify patterns in engagement based on gender, location, etc.
Social Network Analysis of Global Warming Discourse: Examining the network structures and interactions among users discussing global warming on Twitter to identify influential users, communities, and patterns of information flow.
Political Divide on Global Warming: Explore the influence of political polarization on public opinion and climate policy approaches related to global warming.
Completion Date Goal: 2024-01-31
Milestone Title: Milestone #4
Milestone Description: Student works with faculty to interpret the results and write a report.
Completion Date Goal: 2024-02-28
Milestone Title: Milestone #5
Milestone Description: Wrap up development, update project git and documentation, wrap presentation. The student submits the project to a conference.
Completion Date Goal: 2024-03-31

Github Contributions {Empty}

Planned Portal Contributions (if any) {Empty}

Planned Publications (if any) {Empty}

What will the student learn? {Empty}

What will the mentee learn? {Empty}

What will the Cyberteam program learn from this project? {Empty}

HPC resources needed to complete this project? {Empty}

Notes {Empty}

Final Report

What is the impact on the development of the principal discipline(s) of the project? This project aimed to contribute to the data science field through an analysis of big data and using text data in order to come to valuable insights regarding climate change and global warming discussion. Through the project we were able to demonstrate how twitter data can be used in order to analyze the change of a conversation over time. We did this through the use of word clouds, topic modeling and emotion analysis in order to identify changes over the 3 main stages of the pandemic, pre, during and post. This project serves as a model for how emotion analysis can be used for topics such as climate change in an efficient and resource friendly way. Using the hugging face model, we were able to label data as having one of the four main emotions, happiness, sadness, anger and optimism. Analyzing these emotions and how they changed over time provided a different kind of analysis compared to other similar studies. It was through this kind of analysis that we were able to come to definite findings. Using the analysis that we conducted, researchers can use similar methods on a range of topics in order to come to additional conclusions and further understand public sentiment the several intricacies of it.

What is the impact on other disciplines? This research also has an impact on the environmental science discipline as well as the political science discipline. With a complex issue such as climate change, the conversation is constantly changing. Identifying how the conversation has shifted over time, it can help researchers of the environmental science discipline in order to be able to advocate better for climate change awareness and understand how the public perception of climate change is changing. Another discipline that could be affected through this research would be the political science discipline. When it comes to making changes regarding the policies and governance of issues such as climate change, it would help to understand where the public talks about issues such as climate change and in what capacity. This could help in order to make more effective policies regarding climate change and gauge public perception. This study aimed to have impacts that extend beyond the realm of data science, through a thorough analysis and extensive research into climate change we have found valuable results that will impact disciplines such as environmental science and public policy.

Is there an impact physical resources that form infrastructure? {Empty}

Is there an impact on the development of human resources for research computing? {Empty}

Is there an impact on institutional resources that form infrastructure? {Empty}

Is there an impact on information resources that form infrastructure? {Empty}

Is there an impact on technology transfer? {Empty}

Is there an impact on society beyond science and technology? For this study, there are implications that go beyond just science and technology. As mentioned previously, public awareness and perception is a major point of conversation for climate change issues and this study has a deep effect on how researchers view the discourse as well as what could be done about it. Another impact of this research would be regarding political policy and decision making. Understanding where the climate change conversation is as well as how it has changed over time is valuable information that can be used in order to construct better and more effective public policies regarding high importance matters. The bounds of this research extend far beyond science and technology and rather have a focus on future learning and the ability for the results of this research to be used in other disciplines moving forward.

Lessons Learned Throughout this project I learned multiple lessons regarding performing academic research as well as the use of high-performance computing resources such as UNITY throughout the course of the project. Through this research, I learned lessons regarding completing a thorough literature review and its purpose for a research project. Through this process a researcher is able to collect valuable information regarding projects that were completed prior to starting their own. I learned that it is through this process that you are able to learn about mistakes made in order to avoid them as well as learn what gaps in research there are and how you can provide valuable insights to the discipline of choice. Throughout the project I also learned valuable lessons regarding the use of high-performance computing systems for research and how valuable they are. The learning curve regarding submitting batch jobs and ensuring that your code is effective and efficient with computing resources was a problem that I had yet to experience coming into the project. Through the use of these resources, I was better able to meet the objectives of my project and put together an analysis that would have an impact on the data science discipline. This project provided a chance for me to have an introduction into academic research as well as learn valuable lessons as mentioned above that I am going to carry with me for the rest of my life.

Overall results Through this project we were able to put together a comprehensive analysis regarding climate change discourse and how it has changed over the three stages of the COVID-19 pandemic. Using word clouds in order to review common words, topic modeling to identify major topics over the three phases as well as emotion analysis to analyze change in emotion, we were able to come to conclusive findings that can be used for further research. First it was found that people are more worried regarding climate change than they have been in the past. topics that were prevalent in the analysis contained key words indicating observation pre covid, impact and awareness during covid and worry post covid. It was also found that there has been a slight increase in anger over time which could be contributed to the pandemic and anger levels rising over the past couple of years. Lastly it was found that the patterns in which climate change discussion occurs is much aligned with the happenings of extreme weather events in which global warming conversation is front in the faces of the public. The findings we found were promising for future study as they showed that there is a difference in the discourse and the conversation is continuing to shift. The results of this study are promising for the data science field as well as other fields that are impacted by climate change research and we look forward to diving further into the topic moving forward.