SUPREME COURT S A R A H I T A L E V I T A N D R . J U L I A H I - - PowerPoint PPT Presentation

▶
supreme court
SMART_READER_LITE
LIVE PREVIEW

SUPREME COURT S A R A H I T A L E V I T A N D R . J U L I A H I - - PowerPoint PPT Presentation

May 16, 2023 154 likes •483 views

ENTRAINMENT IN THE SUPREME COURT S A R A H I T A L E V I T A N D R . J U L I A H I R S C H B E R G C O L U M B I A U N I V E R S I T Y D E P A R T M E N T O F C O M P U T E R S C I E N C E D R E U 2 0 1 2 A U G U S T 9 , 2 0 1 2 1

slide-1
SLIDE 1

1

ENTRAINMENT IN THE SUPREME COURT

S A R A H I T A L E V I T A N D R . J U L I A H I R S C H B E R G C O L U M B I A U N I V E R S I T Y D E P A R T M E N T O F C O M P U T E R S C I E N C E D R E U 2 0 1 2 A U G U S T 9 , 2 0 1 2

slide-2
SLIDE 2

OUTLINE

  • Overview
  • Entrainment
  • Supreme Court Corpus
  • Mechanical Turk
  • Methods
  • Results

2

slide-3
SLIDE 3

OVERVIEW

Results file Text grid

Supreme Court corpus

3

slide-4
SLIDE 4

OUTLINE

  • Overview
  • Entrainment
  • Supreme Court Corpus
  • Mechanical Turk
  • Methods
  • Results

4

slide-5
SLIDE 5

ENTRAINMENT

  • Definition
  • Dialogue success and quality
  • Types of entrainment
  • Examples

5

slide-6
SLIDE 6

ENTRAINMENT

  • Definition
  • Phenomenon of people becoming similar to

each other in conversation

  • Dialogue success and quality
  • Types of entrainment
  • Examples

6

slide-7
SLIDE 7

ENTRAINMENT

  • Definition
  • Dialogue success and quality
  • Reitter & Moore, 2007
  • Nenkova et al., 2008
  • Levitan et al., 2011
  • Types of entrainment
  • Examples

7

slide-8
SLIDE 8

ENTRAINMENT

  • Definition
  • Dialogue success and quality
  • Types of entrainment
  • Lexical
  • Acoustic/prosodic
  • Examples

8

slide-9
SLIDE 9

ENTRAINMENT

  • Definition
  • Dialogue success and quality
  • Types of entrainment
  • Examples

9

slide-10
SLIDE 10

OUTLINE

  • Overview
  • Entrainment
  • Supreme Court Corpus
  • Mechanical Turk
  • Methods
  • Results

10

slide-11
SLIDE 11

SUPREME COURT CORPUS

PROS:

  • Over 50 years of oral arguments
  • 9000 hours of audio
  • 2001 – transcribed, speaker id, word aligned

(OYEZ project)

  • Knowledge of outcome

11

slide-12
SLIDE 12

SUPREME COURT CORPUS

CONS:

  • Noise
  • Alignment issues

12

slide-13
SLIDE 13

SUPREME COURT CORPUS

Questions:

  • Do justices entrain more to lawyers that they

eventually side with?

  • Does entrainment depend on other factors like

justice gender, ideology, or investment in the case?

  • Do more successful lawyers entrain more?

13

slide-14
SLIDE 14

OUTLINE

  • Overview
  • Entrainment
  • Supreme Court Corpus
  • Mechanical Turk
  • Methods
  • Results

14

slide-15
SLIDE 15

AMAZON MECHANICAL TURK (AMT)

  • Marketplace for work that requires human

intelligence

15

slide-16
SLIDE 16

AMAZON MECHANICAL TURK (AMT)

  • Marketplace for work that requires human

intelligence

  • Terminology
  • HIT
  • Requester, Turker
  • Reward

16

slide-17
SLIDE 17

AMAZON MECHANICAL TURK (AMT)

  • Marketplace for work that requires human

intelligence

  • Terminology
  • Creative uses
  • thesheepmarket.com
  • Facebook

17

slide-18
SLIDE 18

AMAZON MECHANICAL TURK (AMT)

  • Marketplace for work that requires human

intelligence

  • Terminology
  • Creative uses
  • Research uses
  • Social variables
  • Clarification questions
  • WordsEye annotations

18

slide-19
SLIDE 19

AMAZON MECHANICAL TURK (AMT)

PROS:

  • On demand workforce
  • Cost effective
  • Speed

CONS:

  • Quality control
  • Virtual sweatshop?

19

slide-20
SLIDE 20

AMAZON MECHANICAL TURK (AMT)

Quality Control

  • US only
  • 90% acceptance rate
  • Qualification exam
  • Gold standard questions

20

slide-21
SLIDE 21

AMAZON MECHANICAL TURK (AMT)

21

slide-22
SLIDE 22

identify noisy IPUs (inter-pausal units)

SAMPLE HIT

22

slide-23
SLIDE 23

OUTLINE

  • Overview
  • Entrainment
  • Supreme Court Corpus
  • Mechanical Turk
  • Methods
  • Results

23

slide-24
SLIDE 24

METHODS

  • HIT preparation
  • Getting results

24

slide-25
SLIDE 25

METHODS

  • HIT preparation
  • Amazon CLT (Command Line Tools)
  • Python scripts
  • CGI (Common Gateway Interface)
  • Getting results

25

slide-26
SLIDE 26

METHODS

  • HIT preparation
  • Getting results
  • Python scripts
  • Text grids
  • Praat scripts

26

slide-27
SLIDE 27

METHODS

  • Getting results (cont)
  • Extracted intensity from all sessions
  • Calculated intensity at beginnings and

ends of turns

  • Preliminary analysis using R

27

slide-28
SLIDE 28

OUTLINE

  • Overview
  • Entrainment
  • Supreme Court Corpus
  • Mechanical Turk
  • Methods
  • Results

28

slide-29
SLIDE 29

RESULTS

  • Smaller intensity differences between lawyers and

justices than between justices and lawyers

(t=-7.92, df=17622, p=2.57e-15, mean_lawyer=3.59, mean_justice=3.94)

  • Dominance
  • No significant difference in entrainment between

male and female lawyers

(t=1.29, df=2205.1, p=0.20, mean_male=3.61, mean_female=3.50)

29

slide-30
SLIDE 30

RESULTS

  • Differences between justices and petitioners are

significantly smaller when the justice sides with the petitioner!

(t=-2.14, df=294.86, p=0.03, mean_petitioner=3.71, mean_respondent=4.18)

  • However, differences between justices and

respondents are also significantly smaller (when the petitioner wins the case)

(t=-2.53, df=217.9, p=0.01, mean_petitioner=3.68, mean_respondent=4.26)

30

slide-31
SLIDE 31

FUTURE WORK

  • AMT – continue with more sessions
  • Build classifier
  • Extract more features
  • Pitch
  • Speaking rate
  • Voice quality
  • Look for evidence of multi-party entrainment
  • Look for association between entrainment and

case outcome

31

slide-32
SLIDE 32

32