Charisma in English and Arabic Political Speech

1
Charisma in English and Arabic Political Speech

• Julia Hirschberg
• Columbia University
• Joint work with Andrew Rosenberg and Fadi Biadsy
• Stony Brook University, 9 Nov 2007

2
(No Transcript)
3
What is Charisma?

• The ability to attract, and retain followers by
  virtue of personal characteristics -- not
  traditional or political office (Weber 47)
• E.g. Gandhi, Hitler, Castro, Martin Luther King
  Jr.,..
• Personalismo
• What makes an individual charismatic? (Bird 93,
  Boss 76, Dowis 00, Marcus 67, Touati 93,
  Tuppen 74, Weber 47)
• Their message?
• Their personality?
• Their speaking style?

4
What is Charismatic Speech?

• Circularly
• Speech that leads listeners to perceive the
  speaker as charismatic
• What aspects of speech might contribute to the
  perception of a speaker as charismatic?
• Content of the message?
• Lexico-syntactic features?
• Acoustic-prosodic features?

5
Why Study Charismatic Speech?

• Its an interesting phenomenon
• To identify potential charismatic leaders
• To provide a feedback system for individuals who
  want to improve their speaking style --
  politicians, professors, students
• To create a charismatic Text-to-Speech system

6
Our Approach

• Collect tokens of charismatic and non-charismatic
  speech from a small set of speakers on a small
  set of topics
• Ask listeners to rate the The speaker is
  charismatic plus statements about a number of
  other attributes (e.g. The speaker is boring,
  charming, persuasive,)
• Correlate listener ratings with lexico-syntactic
  and acoustic-prosodic features of the tokens to
  identify potential cues to perception of charisma

7
American English Perception Study

• Data 45 2-30s speech segments, 5 each from 9
  candidates for Democratic nomination for U.S.
  president in 2004
• 2 charismatic, 2 not charismatic
• Topics greeting, reasons for running, tax cuts,
  postwar Iraq, healthcare
• 4 genres stump speeches, debates, interviews,
  ads
• 8 subjects rated each segment on a Likert scale
  (1-5) for 26 questions in a web survey
• Duration avg. 1.5 hrs, min 45m, max 3hrs

8
Results How Much Do Subjects Agree with Each
Other?

• Over all statements?
• Using weighted kappa statistic with quadratic
  weighting, mean ? 0.207
• On the charismatic statement?
• ? 0.232 (8th most agreed upon statement)
• By token?
• No significant differences across all tokens
• By statement?
• Individual statements demonstrate significantly
  different agreements (most agreement The speaker
  is accusatory, angry, passionate, intense least
  agreement The speaker is trustworthy,
  believable, reasonable, trustworthy)

9
Results What Do Subjects Mean by Charismatic?

• Which other statements are most closely
  correlated with the charismatic statement?
  (determined by kappa) a functional definition

The speaker is enthusiastic 0.620
The speaker is persuasive 0.577
The speaker is charming 0.575
The speaker is passionate 0.543
The speaker is boring -0.513
The speaker is convincing 0.499
10
Results Does Whether a Subject Agrees with the
Speaker or Finds the Speaker Clear Affect
Charisma Judgments

• Whether a subject agrees with a token does not
  correlate highly with charisma judgments (?
  0.30)
• Whether a subject finds the token clear does not
  correlate highly with charisma judgments (?
  0.26)

11
Results Does the Identity of the Speaker Affect
Judgments of Charisma?

• There is a significant difference between
  speakers (p2.20e-2)
• Most charismatic
• Rep. John Edwards (mean 3.86)
• Rev. Al Sharpton (3.56)
• Gov. Howard Dean (3.40)
• Least charismatic
• Sen. Joseph Lieberman (2.42)
• Rep. Dennis Kucinich (2.65)
• Rep. Richard Gephardt (2.93)

12
Results Does Recognizing a Speaker Affect
Judgments of Charisma?

• Subjects asked to identify which, if any,
  speakers they recognized at the end of the study.
• Mean number of speakers believed to have been
  recognized, 5.8
• Subjects rated recognized speakers as
  significantly more charismatic than those they
  did not (mean 3.39 vs. mean 3.30).

13
Results Does Genre or Topic Affect Judgments of
Charisma?

• Recall that tokens were taken from debates,
  interviews, stump speeches, and campaign ads
• Genre does influence charisma ratings (p.0004)
• Stump speeches were the most charismatic (3.38)
• Interviews were the least (2.96)
• Topic does affect ratings of charisma
  significantly (p.0517)
• Healthcare gt post-war Iraq gt reasons for running
  neutral gt taxes

14
What makes Speech Charismatic?Features Examined

• Duration (secs, words, syls)
• Charismatic speech is personal Pronoun density
• Charismatic speech is contentful
  Function/content word ratio
• Charismatic speech is simple Complexity mean
  syllables/word (Dowis)
• Disfluencies
• Repeated words

• Min, max, mean, stdev F0 (Boss, Tuppen)
• Raw and normalized by speaker
• Min, max, mean, stdev intensity
• Speaking rate (syls/sec)
• Intonational features
• Pitch accents
• Phrasal tones
• Contours

15
Results Lexico-Syntactic Correlates of Charisma

• Length Greater number of words positively
  correlates with charisma (r.13 p.002)
• Personal pronouns
• Density of first person plural and third person
  singular pronouns positively correlates with
  charisma (r.16, p0 r.16, p0)
• Third person plural pronoun density correlates
  negatively with charisma (r-.19,p0)
• Content Ratio of adjectives/all words negatively
  correlates with charisma (r-.12,p.008)
• Complexity Higher mean syllables/word positively
  correlates with charisma (p.034)

16

• Disfluency greater negatively correlates with
  charisma (r-.18, p0)
• Repetition Proportion of repeated words
  positively correlates with charisma (r.12,
  p.004)

17
Results Acoustic-Prosodic Correlates of Charisma

• Pitch
• Higher F0 (mean, min, mean HiF0, over male
  speakers) positively correlates with charisma
  (r.24,p0r.14 p0r.20,p0)
• Loudness Mean rms and sdev of mean rms
  positively correlates with charisma
  (r.21,p0r.21,p0)
• Speaking Rate
• Faster overall rate (voice/unvoiced frames)
  positively correlates with charisma (r.16,p0)

18

• Duration Longer duration correlates positively
  with charisma (r.09,p.037)
• Length of pause sdev negatively correlates with
  charisma (r-.09,p.004)

19
Results Intonational Correlates of Charisma
(Hand-Annotated Features)

• Pitch Accent Type
• Positive correlation with !H and LH accents
  (r.09,p0r.09,p.034)
• Negative correlation with L, H and LH
  accents (r-.13,p.002r-.11,p.014r-.08,p.052
  )
• Phrasal Types
• Negative correlation with !H-L and !H- endings
  (r-.11,p.015r-.10,p.026)

20
Summary for American English

• In Standard American English, charismatic
  speakers tend to be those also highly rated for
  enthusiasm, charm, persuasiveness, passionateness
  and convincingness they are not thought to be
  boring
• Charismatic utterances tend to be longer than
  others, to contain a lower ratio of adjectives to
  all words, a higher density of first person
  plural and third person singular pronouns and
  fewer third person plurals, fewer disfluencies, a
  larger percentage of repeated words, and more
  complex words than non-charismatic utterances

21

• Charismatic utterances are higher in pitch (mean,
  min) with more regularity in pause length, louder
  with more variation in intensity, faster, and
  with more !H and LH accents and fewer L, H,
  and LH accents and fewer !H- and !H-L phrasal
  endings

22
Replication of Perception Study from Text Alone

• Lower statement agreement, much less on
  charismatic statement, different speakers
  most/least charismatic
• Agreement with speaker, genre and topic had
  stronger correlations
• Lexico-syntactic features show weaker
  correlations
• 1st person pronoun density negatively correlated
  and complexity not at all
• Similar to speech experiment for duration,
  function/content, disfluencies, repeated words

23
Hypothesis Charisma is a Culture-Dependent
Phenomenon

• People of different languages and cultures
  perceive charisma differently
• In particular, they perceive charisma in speech
  differently
• Do Arabic listeners respond to American
  politicians the same way Americans do?
• Do Americans hear Swedish professors the same way
  Swedish students do?

24
Charismatic Speech in Palestinian Arabic

• Are these tokens charismatic?
• Are these?

25
Palestinian Arabic Perception Study

• Same paradigm as for SAE
• Materials
• 44 speech tokens from 22 male native-Palestinian
  Arabic speakers taken from Al-Jazeera TV talk
  shows
• Two speech segments extracted for each speaker
  from the same topic (one we thought charismatic
  and one not)
• Web form with statements to be rated translated
  into Arabic
• Subjects 12 native speakers of Palestinian
  Arabic

26
Data
Total corpus duration 10.3 minutes
Token with min duration 3 seconds
Token with max duration 28 seconds
Average token duration 14 seconds
Total number of words 1322 words
Token with min words 9 words
Token with max words 65 words
Average number of words in token 30 words
27
How Does Charisma Differ in Arabic?

• Subjects agree on judgments a bit more (?.225)
  than for English (?.207) but still low
• Agree most on clarity of msg, enthusiasm,
  charisma, intensity all differing from
  Americans
• Agree least on desperation (as Amer),
  friendliness, ordinariness, spontaneity of
  speaker
• Charisma statement correlates (positively) most
  strongly with speaker toughness, powerfulness,
  persuasiveness, charm, and enthusiasm and
  negatively with boringness

28

• Role of speaker identity important in judgments
  of charisma in Arabic as in English
• Most charismatic speakers Ibrahim Hamami (4.75),
  Azmi Bishara (4.42), Mustafa Barghouti (4.33)
• Least Shafiq Al-Hoot (3.10), Mohammed Al-Tamini
  (3.42), Azzam Al-Ahmad (3.33)
• Raters claimed to recognize only .55 (of 22)
  speakers on average, perhaps because the speakers
  were less well known than the Americans
• Topic important in charisma ratings (r0,p.043)
• Israeli separation wall gt assassination of Hamas
  leader gt debates among Palestinian groups gt the
  Palestinian Authority and calls for reform gt the
  Intifada and resistance

29
Lexical Cues to Charisma

• Length in words positively correlates with
  charisma, as for Americans
• Disfluency rate negatively correlates, as for
  Americans
• Repeated words positively correlates with
  charisma, as for Americans
• Presence of Arabic dialect markers (words,
  pronunciations) negatively correlates with
  charisma
• Density of third person plural pronouns
  positively correlates w/ charisma differing
  from Americans

30
Acoustic/Prosodic Cues to Charisma

• Duration positively correlated with charisma, as
  for Americans
• Speaking rate approaches negative correlation
  opposite from American
• But rate of the fastest intonational phrase in
  the token positively correlated for both
  languages
• Sdev of rate across intonational phrases
  positively correlated for charisma in Arabic
• Pauses
• pauses/words ratio positively correlated with
  charisma but not for Americans

31

• Sdev of length of pause positively correlated in
  Arabic but negatively for Americans
• Pitch
• Mean pitch positively correlates (as for
  Americans) but also F0 max and sdev
• Min pitch negatively correlates (opposite from
  Americans)
• Intensity Sdev positively correlates w/ charisma

32
How Are Perceptions of Charisma Similar Across
Cultures?

• Level of subject agreement on statements
• Role of speaker ID, topic in charisma judgments
• Positive correlations with charisma
• Mean pitch and range
• Duration, repeated words
• Speaking rate of fastest IP
• Negative correlations with charisma
• Disfluencies

33
How Do Charisma Judgments Differ Across Cultures?

• Statements most and least agreed upon
• For Arabic vs. English
• Positive correlations with charisma
• Sdev of speaking rate, pause/word ratio, sdev of
  pause length, F0 max and sdev, sdev intensity
• Negative correlations with charisma
• Dialect, density of third person plural pronouns
• Speaking rate, min F0

34
Future Work

• Machine learning experiments -- automatic
  detection of charisma
• Cross-cultural perception experiments American
  raters/Arabic speech, Palestinian raters/English
  speech, Swedish raters/English speech
• Do native and non-native raters differ on mean
  scores per token? (Yes, for Eng/Swe rating Eng
  and Eng/Pal rating Arabic)
• Do mean scores correlate per token? (Yes, for all)

35

• Amer and Swe rating English
• paired t-test betw means per token p-value
  0.03064
• cor between means of rater-normalized ratings r
  0.60, p-value 1.170e-05
• Amer and Pal rating English
• paired t-test betw means p-value 0.1048
• cor between means of rater-normalized ratings r
  0.47, p-value 0.0009849
• Amer and Pal rating Arabic
• paired t-test betw means p-value 0.00164
• cor between means of rater-normalized ratings r
  0.72, p-value 3.049e-08
• Swe and Pal rating English
• paired t-test betw means p-value 0.8479 (not
  normalized)
• cor between means of rater-normalized ratings
  (rater normalization) r 0.55, p-value
  9.467e-05

36
Thank you!
37
Arabic Prosodic Phenomena MSA vs. Dialect

• A word is considered dialectal if
• It does not exist in the standard Arabic lexicon
• It does not satisfy the MSA morphotactic
  constraints
• Phonetically different (e.g., ya?kul vs. ywkil)
• In corpus of tokens
• 8 of the words are dialect.
• 80 of the dialect words are accented.

38
Arabic Prosody Accentuation

• 70 of words are accented
• 60 of the de-accented words are function words
  or disfluent items
• Based on automatic POS analysis (MADA)
• 12 of content words are deaccented
• Distribution of accent types
• H or !H pitch accent, 73
• LH or L!H, 20
• L, 5
• H!H, 2

39
Arabic Prosody Phrasing

• Mean of 1.6 intermediate phrases per intonational
  phrase
• Intermediate phrases contain 2.4 words on average
• Distribution of phrase accent/boundary tone
  combinations
• L-L 59
• H-L 26
• L-H 8
• H-L 6
• H-H 1

40
Arabic Prosody most common contours
H L- 21.9
H H- 13.4
LH L- 9.7
H H L- 7.6
H !H L- 4.1
L L- 4.1
LH !H L- 3
H H H- 3
H !H !H L- 2.3
LH H- 2.1
41
Arabic Prosody Disfluency

• In addition to standard disfluency
• Hesitations
• filled pauses
• self-repairs
• In Arabic, speakers could produce a sequence of
  all of the above. (see praat file 1036 and
  2016)
• Disfluency may disconnect prepositions and
  conjunctions from the content word
• ?????? gt ? ... ?? ... ???? ... ????
• w- l- uh- yEny uh- t?ty instead of wlt?ty