A Machine Learning Analysis of Twitter Sentiment to the Sandy Hook - - PowerPoint PPT Presentation

▶

Oct 06, 2023 346 likes •614 views

A Machine Learning Analysis of Twitter Sentiment to the Sandy Hook Shootings Nan Wang, Blesson Varghese Queens University Belfast Peter Donnelly University of Toronto 12-CRS-0106 REVISED 8 FEB 2013 1 10/26/16 Outline Motivation

SLIDE 1

12-CRS-0106 REVISED 8 FEB 2013

10/26/16 1

A Machine Learning Analysis of Twitter Sentiment to the Sandy Hook Shootings

Nan Wang, Blesson Varghese

Queen’s University Belfast

Peter Donnelly University of Toronto

SLIDE 2

12-CRS-0106 REVISED 8 FEB 2013

10/26/16 2

Outline

Motivation
Methodology
Machine Learning Approaches
Case Study: Sandy Hook Elementary School Shooting
Limitations
Conclusion
Q & A

SLIDE 3

12-CRS-0106 REVISED 8 FEB 2013

10/26/16 3

Outline

Motivation
Methodology
Machine Learning Approaches
Case Study: Sandy Hook Elementary School Shooting
Limitations
Conclusion
Q & A

SLIDE 4

12-CRS-0106 REVISED 8 FEB 2013

A Machine Learning Analysis of Twitter Sentiment to the Sandy Hook Shootings

Motivation

– Apply and evaluate machine learning approaches for sentiment analysis on social network – Provide insights gathered from social networks to decision makers – Engage non-CS audiences with research outputs through interactive visualisation

4 10/26/16

SLIDE 5

12-CRS-0106 REVISED 8 FEB 2013

10/26/16 5

Outline

Motivation & Contribution
Methodology
Machine Learning Approaches
Case Study: Sandy Hook Elementary School Shooting
Limitations
Conclusion
Q & A

SLIDE 6

12-CRS-0106 REVISED 8 FEB 2013

10/26/16 6

Methodology

SLIDE 7

12-CRS-0106 REVISED 8 FEB 2013

10/26/16 7

Methodology

Pro-Gun Public Sentiment Score

– Baseline – Correction for Volume of Tweets – Correction for Volume of Tweets & Population

g: geographic region t: time frame

SLIDE 8

12-CRS-0106 REVISED 8 FEB 2013

10/26/16 8

Outline

Motivation & Contribution
Methodology
Machine Learning Approaches
Case Study: Sandy Hook Elementary School Shooting
Limitations
Conclusion
Q & A

SLIDE 9

12-CRS-0106 REVISED 8 FEB 2013

10/26/16 9

Machine Learning Approaches

Feature Extraction

– N-gram

Uni-gram Bi-gram Tri-gram Not Not sure Not sure if sure sure if sure if gun if if gun if gun shot gun gun shot gun shot or shot shot or shot or fire

r
r firework
r firework

firework

SLIDE 10

12-CRS-0106 REVISED 8 FEB 2013

10/26/16 10

Machine Learning Approaches

Feature Extraction

– Hashtags #PrayForNewtown, #NRA, #guncontrol – Reply/Mention Tags @BarackObama, @Death, @cnnbrk

SLIDE 11

12-CRS-0106 REVISED 8 FEB 2013

10/26/16 11

Machine Learning Approaches

Modelling

– Support Vector Machine (SVM) – Naïve Bayes (NB) – Maximum Entropy (ME) – Decision Tree (Single, Bagged, Boosted) – Random Forest (RF) – Neural Network (NN)

SLIDE 12

12-CRS-0106 REVISED 8 FEB 2013

10/26/16 12

Machine Learning Approaches

Evaluation

SLIDE 13

12-CRS-0106 REVISED 8 FEB 2013

10/26/16 13

Machine Learning Approaches

Evaluation

SLIDE 14

12-CRS-0106 REVISED 8 FEB 2013

10/26/16 14

Outline

Motivation & Contribution
Methodology
Machine Learning Approaches
Case Study: Sandy Hook Elementary School Shooting
Limitations
Conclusion
Q & A

SLIDE 15

12-CRS-0106 REVISED 8 FEB 2013

10/26/16 15

Case Study: Sandy Hook Elementary School Shooting

Data Description

– Timeframe

Friday, 12/07/2012 00:00:01 GMT ~ Tuesday, 01/15/2013 23:59:59 GMT

– Data Size

7 million tweets

Triple-class Sentiment

– Positive

“The only thing that stops a bad guy with a gun, is a good guy with a gun”

– Negative

“We NEED strict gun control. #Newtwon”

– Neutral

“Not sure if gun shot of firework.”

SLIDE 16

12-CRS-0106 REVISED 8 FEB 2013

10/26/16 16

Case Study: Sandy Hook Elementary School Shooting

Tweets Statistics

SLIDE 17

12-CRS-0106 REVISED 8 FEB 2013

10/26/16 17

Case Study: Sandy Hook Elementary School Shooting

Tweets Statistics

SLIDE 18

12-CRS-0106 REVISED 8 FEB 2013

10/26/16 18

Case Study: Sandy Hook Elementary School Shooting

Visualisation http://www.gunsontwitter.com/

– Motion Chart

SLIDE 19

12-CRS-0106 REVISED 8 FEB 2013

10/26/16 19

Case Study: Sandy Hook Elementary School Shooting

Visualisation

– Line Graph

SLIDE 20

12-CRS-0106 REVISED 8 FEB 2013

10/26/16 20

Case Study: Sandy Hook Elementary School Shooting

Visualisation

– Geo Map

Baseline PGPSS

12/07/2012 ~ 01/15/2013 12/13/2012 ~ 12/15/2012

SLIDE 21

12-CRS-0106 REVISED 8 FEB 2013

10/26/16 21

Outline

Motivation & Contribution
Methodology
Machine Learning Approaches
Case Study: Sandy Hook Elementary School Shooting
Limitations
Conclusion
Q & A

SLIDE 22

12-CRS-0106 REVISED 8 FEB 2013

10/26/16 22

Limitations

Size of Twitter Corpus
Complexity of Feature Selection

– emoticon – Part-Of-Speech tagging

Trade-off between Performance & Computing

Power

SLIDE 23

12-CRS-0106 REVISED 8 FEB 2013

10/26/16 23

Outline

Motivation & Contribution
Methodology
Machine Learning Approaches
Case Study: Sandy Hook Elementary School Shooting
Limitations
Conclusion
Q & A

SLIDE 24

12-CRS-0106 REVISED 8 FEB 2013

10/26/16 24

Conclusion

This paper

– Evaluates of machine learning approaches for twitter sentiment analysis – Investigates tweets’ relevance to gun violence – Visualises public sentiment related data on multiple geographic/temporal level interactively

SLIDE 25

12-CRS-0106 REVISED 8 FEB 2013

Q & A

25 10/26/16