Exploring Polarization in Climate Change Debate on Twitter Aman - - PDF document

<Your Name> 1

Center for Computational Analysis of Social and Organizational Systems http://www.casos.cs.cmu.edu/

Engineering & Public Policy

Exploring Polarization in Climate Change Debate on Twitter

Aman Tyagi

11 June 2020 2 Aman Tyagi Engineering & Public Policy

Motivation

• Social Media is used to debate around complex

social issues

• Climate change is one such complex issue
• Study polarizing communities debating climate

change issue

• Find disinformation stories in communities
• Recognize topics within these communities
• Bot Activity within these communities

<Your Name> 2

11 June 2020 3 Aman Tyagi Engineering & Public Policy

Case Study : UN’s COP24

• United Nation’s Conference of Parties (COP)

– Annual conference to discuss progress and establish

• bligations

– COP24 – Held in Poland between 2nd December - 15th December 2018

• Collected ~1.3M tweets using keywords and

hashtags related to Climate Change

Image Source: https://www.enel.com/ 11 June 2020 4 Aman Tyagi Engineering & Public Policy

Community Detection Using Hashtags

• Classify users into Believers, Deniers and Neutral
• Found “#ClimateHoax” used by Deniers and

“#ClimateChangeIsReal” used by Believers

(Hashtags used >15 times only)

<Your Name> 3

11 June 2020 5 Aman Tyagi Engineering & Public Policy

Community Detection Using Hashtags

• Classify users into Believers, Deniers and Neutral
• Found “#ClimateHoax” used by Deniers and

“#ClimateChangeIsReal” used by Believers

• Used weighted hashtag x hashtag co-occurrence

network to find other hashtags

• Aggregate hashtags used by each user to classify

user

Deniers Believers climatehoax climatechangeisreal yellowvests ClimateActionNow qanon factsmatter

• 8,413 tweets from 2,170 Deniers
• 120,497 tweets from 15,640 Believers

11 June 2020 6 Aman Tyagi Engineering & Public Policy

Isolating Disinformation and BOT Detection

• Disinformation:

– Break tweets into unigrams and bigrams – Match the unigrams and bigrams with disinformation related words/phrases

• Bot Detection- CMU’s Bot Hunter

<Your Name> 4

11 June 2020 7 Aman Tyagi Engineering & Public Policy

Believer and Denier Networks

Denier and Believer Retweet Network

11 June 2020 8 Aman Tyagi Engineering & Public Policy

Believer and Denier Networks

Denier and Believer Mentions Network

<Your Name> 5

11 June 2020 9 Aman Tyagi Engineering & Public Policy

Believer and Denier Networks

Denier and Believer Reply Network

11 June 2020 10 Aman Tyagi Engineering & Public Policy

Echo-chamberness of Both Groups Decreases

• n Adding Neutrals

Echo-chamberness (Nodes) Echo-chamberness with Neutrals (Nodes) Deniers 0.007 (2,170) 0.003 (435,181) Believers 0.006 (15,640) 0.003 (432,944)

• Each group is talking more to themselves

<Your Name> 6

11 June 2020 11 Aman Tyagi Engineering & Public Policy

Keywords in Discussion

Deniers Believer

11 June 2020 12 Aman Tyagi Engineering & Public Policy

Unigram Topic Analysis – Using LDA

Deniers Believers climate climate climate cop yellowves ts cop science climate climatechang eisreal cop scam change bernie parisagre ement maga climat climate change climatechang e climateaction change globalwar ming sanders climate trump stopblahblah year like auspol climate nuclear world travel climateact ion carbontax die keepitinthegr

• und

ipcc climatestrike katowice industry carbon potus katowice france talanoa climateemerg ency fridaysforfutu re climateaction now world fakenews climateho ax month energy macron tico record ambition greennewdea l takeyourseat crisis people change auspol policy est renewableen ergy renewables climate leader record new planet ipcc french klimaschutz bcpoli support cdnpoli solar global know great climatech angehoax people sur end scottmorriso nmp stopadani change agw like face unfccc hoax cambioclim fact australia globalwarmin g poland

<Your Name> 7

11 June 2020 13 Aman Tyagi Engineering & Public Policy

BOT Activity

0% 10% 20% 30% 40% 50% 60% 70% 80% 90% 100%

0.3 0.4 0.5 0.6 0.7 0.8 0.9

Percentage

Threshold Denier Users Believer Users Denier Tweets Believers Tweets

11 June 2020 14 Aman Tyagi Engineering & Public Policy

It’s a Conspiracy

1000 2000 3000 4000 5000 6000 7000 8000 Sunspot(s) Qanon/Q Illuminati Flat Earth Directed Energy Weapons Chemtrails Geo‐Engineering /Weather Modification Number of Tweets/Retweets

Non Bot Retweeet Non Bot Tweet Bot Retweet Bot Tweet

<Your Name> 8

11 June 2020 15 Aman Tyagi Engineering & Public Policy

Denier’s love Conspiracies

0% 5% 10% 15% 20% 25% Believer Tweet Believer ReTweet Denier Tweet Denier ReTweet Neutral Tweet Neutral ReTweet Percentage 11 June 2020 16 Aman Tyagi Engineering & Public Policy

Example: Deniers Target Exaggerations

• “entire nations could be wiped off the face of the

Earth by rising sea levels if the global warming trend is not reversed by the year 2000” (Spielmann, 1989).

• This story was shared 14 times, all by accounts

we classified as Deniers.

<Your Name> 9

11 June 2020 17 Aman Tyagi Engineering & Public Policy

Lets Call Out Each Other

1 2 3 4 5 6 Denier Tweet Denier Retweet Believer Tweet Believer ReTweet Neutral Tweet Neutral ReTweet

Percentage

Alarmist(s)/Alarmism Denier/Hoaxer/denialist

11 June 2020 18 Aman Tyagi Engineering & Public Policy

Key Takeaways

• For all the types of networks, we found that both

deniers and believers talk within their group more than with the other group

– this is truer for deniers than for believers

• We found that in both deniers and believers bot-

like accounts were equally active

<Your Name> 10

11 June 2020 19 Aman Tyagi Engineering & Public Policy

Key Takeaways

• Tweets and Retweets containing words or

phrases related to conspiracies are more frequent in denier’s conversations

– Conspiracies are Tweeted more than Retweeted

• Exaggerations made by believers were targeted

by deniers to strengthen their argument

– deniers call out believers as Alarmists – believers call out deniers as Hoaxers

Center for Computational Analysis of Social and Organizational Systems http://www.casos.cs.cmu.edu/

Engineering & Public Policy

Exploring Polarization in Climate Change Debate on Twitter ORA-Demo

Aman Tyagi

<Your Name> 11

11 June 2020 21 Aman Tyagi Engineering & Public Policy

Import Twitter Dataset

11 June 2020 22 Aman Tyagi Engineering & Public Policy

Import Dataset

<Your Name> 12

11 June 2020 23 Aman Tyagi Engineering & Public Policy

Import Stance Label

• Select

Agent -> Editor -> Attributes

• > Import

Attributes

11 June 2020 24 Aman Tyagi Engineering & Public Policy

Import Attributes

• Use

selections as in the screenshot and click Import

• In case of

warning, press “Keep Results”

<Your Name> 13

11 June 2020 25 Aman Tyagi Engineering & Public Policy

Delete Any Stance Category

• Select

Stance -> Select -> Select the category to be deleted

11 June 2020 26 Aman Tyagi Engineering & Public Policy

Delete Any Stance Category

• Check

“Select/Cle ar Visible” - > Select -> Nodes -> “Delete Selected Nodes”

<Your Name> 14

11 June 2020 27 Aman Tyagi Engineering & Public Policy

Delete Any Stance Category

• Drag and drop original meta network to make

two copies

• Delete Believers from one network (method

similar to last slide)

• Delete Deniers from the other network

11 June 2020 28 Aman Tyagi Engineering & Public Policy

Calculate Echo Chamberness

• Select any one meta network and click on

”Generate Reports”

• Use the setting from the following Screen Shots

<Your Name> 15

11 June 2020 29 Aman Tyagi Engineering & Public Policy

• Click Finish

and Check the HTML file.

11 June 2020 30 Aman Tyagi Engineering & Public Policy

Thank You!