Deceptive Speech Frank Enos April 19, 2006 Defining Deception Deliberate choice to mislead a target without prior notification (Ekman‘’01) Often to gain.

Slides:



Advertisements
Similar presentations
Detecting Deception with LIWC Aberdeen, MD April 12, 2006.
Advertisements

Based on the Studies of Paul Eckman LIE TO ME
Detecting Deception Chapter 11. Detecting Deception  Lying & deception as a consistent feature of human behavior  “Santa Claus”  People in general.
Lying and deception:. Theoretical perspectives on non-verbal cues to deception.
Impression Management You never get a second chance to make a first impression...
Spoken Cues to Deception CS 4706 What is Deception?
Verbal Gestures © Master In Mind on behalf of ISIO 2013 Slip of the Tongue - Known as the Freudian Slip. The unconscious mind is a memory bank of past.
Social Perception: Overview How do we make attributions about social behavior? –Internal versus External attributions Do people make attributions in a.
Who Can Best Catch a Liar? A Meta-Analysis of Individual Differences in Detecting Deception Michael G. Aamodt & Heather Mitchell Radford University Radford,
Lecture 13: 10/13/04 Negotiating Strategy 1.Lies (and the Lying Liars who tell them) 2.Ethics 3.Wrap up.
Comparing American and Palestinian Perceptions of Charisma Using Acoustic-Prosodic and Lexical Analysis Fadi Biadsy, Julia Hirschberg, Andrew Rosenberg,
Presented by Ravi Kiran. Julia Hirschberg Stefan Benus Jason M. Brenier Frank Enos Sarah Friedman Sarah Gilman Cynthia Girand Martin Graciarena Andreas.
Spoken Language Processing Lab Who we are: Julia Hirschberg, Stefan Benus, Fadi Biadsy, Frank Enos, Agus Gravano, Jackson Liscombe, Sameer Maskey, Andrew.
Extracting Social Meaning Identifying Interactional Style in Spoken Conversation Jurafsky et al ‘09 Presented by Laura Willson.
Deceptive Speech Frank Enos April 25, Defining Deception Deliberate choice to mislead a target without notification (Ekman‘’01) Often to gain some.
1 Evidence of Emotion Julia Hirschberg
Techniques for Emotion Classification Julia Hirschberg COMS 4995/6998 Thanks to Kaushal Lahankar.
Classification of Discourse Functions of Affirmative Words in Spoken Dialogue Julia Agustín Gravano, Stefan Benus, Julia Hirschberg Shira Mitchell, Ilia.
Detecting deception A lie: a deliberate attempt by one person to mislead another No prior warning of this intent To detect a lie, we need to understand.
Psychology of the Fraudster Nikki Grieve-Top Investigative Psychologist Health Risk Management, Bupa International 7th November 2013.
LIAR BEHAVIOR: VERBAL AND NONVERBAL PERSPECTIVES.
Linguistic Credibility Assessment. Emma – general comments on language Matt – tools for linguistic analysis Mary – case study.
® Automatic Scoring of Children's Read-Aloud Text Passages and Word Lists Klaus Zechner, John Sabatini and Lei Chen Educational Testing Service.
Trait and Social-Cognitive Perspectives on Personality
LEARNING PERSONALITY, MORALITY, AND EMOTIONS Sociology – Chapter 3 – Mrs. Madison.
Emotion.
Chapter 3.  Curiosity  Playfulness  Imagination  Creativity  Wonderment  Wisdom  Inventiveness  Vitality  Sensitivity  Flexibility  Humor.
An Ecological Approach to Deception Detection J. Pete Blair, Ph.D., Department of Criminal Justice, Texas State University Tim R. Levine, Ph.D., Department.
Social Cognitive & Trait Theories
1 Deceptive Speech CS4706 Julia Hirschberg 2 Everyday Lies Ordinary people tell an average of 2 lies per day –Your new hair-cut looks great. –I’m sorry.
CH EMOTIONS. EXPRESSED EMOTION  People more speedily detect an angry face than a happy one (Ohman, 2001a)
Bargaining and Psychology Lecture Two: Preferences, Beliefs, and Lies Keith Chen, Nov 10 th 2004.
Making a Case: Interviewing Suspects. MAKING A CASE Interviewing Witnesses Interviewing Suspects Creating A Profile Recognising Faces.
Graham Davies Week 5 Detecting Deception in Witnesses and Suspects.
Ethics in Negotiation. Why Do Ethics Apply to Negotiation?  “Ethics are broadly applied social standards for what is right or wrong in a particular situation.
1 Computation Approaches to Emotional Speech Julia Hirschberg
Predicting Student Emotions in Computer-Human Tutoring Dialogues Diane J. Litman&Kate Forbes-Riley University of Pittsburgh Department of Computer Science.
The Expression of Emotion: Nonverbal Communication.
Central Core CD Unit B 2-5 Employability in Agriculture/Horticulture Industry.
1 Psychology 320: Gender Psychology Lecture Invitational Office Hour Invitations, by Student Number for October 8 th 11:30-12:30, 3:30-4:30 Kenny.
Decision Making Week 6. Decision-Making Would you rather work alone or in a team? Do groups make better decisions?
Hello, Who is Calling? Can Words Reveal the Social Nature of Conversations?
Copyright © Allyn and Bacon Emotion Interaction of four components 1. physiological arousal 2. subjective feelings 3. cognitive interpretation 4.
Emotional Intelligence
Truth and Deception Detection
Communication Skills Personal Communication Skills.
 Hailey Maurer and Liya Zalaltdinova Lying Words: Predicting Deception From Linguistic Styles by Matthew L. Newman, James W. Pennebaker, Diane S. Berry.
Acoustic Cues to Emotional Speech Julia Hirschberg (joint work with Jennifer Venditti and Jackson Liscombe) Columbia University 26 June 2003.
1 Identifying Deceptive Speech within and across Cultures Sarah Ita Levitan, Guozhen An, Michelle Levine, Andrew Rosenberg, Julia Hirschberg Computer.
Interpreting Ambiguous Emotional Expressions Speech Analysis and Interpretation Laboratory ACII 2009.
On the role of context and prosody in the interpretation of ‘okay’ Julia Agustín Gravano, Stefan Benus, Julia Hirschberg Héctor Chávez, and Lauren Wilcox.
Personal Power 6: Value and belief system.  Reminder: 1. Please choose a “challenging” topic for your final project. Each group leader needs to upload.
Deceptive Communication (Floyd, 2017)
Interpretation and Perception
Theories of Emotion 3 Theories of Emotion.
Towards Emotion Prediction in Spoken Tutoring Dialogues
Lying and Psychology Do you Lie?.
Automatic Fluency Assessment
Comparing American and Palestinian Perceptions of Charisma Using Acoustic-Prosodic and Lexical Analysis Fadi Biadsy, Julia Hirschberg, Andrew Rosenberg,
PERSUASION SOCIAL INFLUENCE & COMPLIANCE GAINING
Advanced NLP: Speech Research and Technologies
Emotional Speech Julia Hirschberg CS /16/2019.
Quick review on Sex & Orientation EMOTION: Theories and Expression
Copyright © Allyn & Bacon 2006
Criteria used for statement analysis in courts and asylum procedures
Acoustic-Prosodic and Lexical Entrainment in Deceptive Dialogue
Presentation transcript:

Deceptive Speech Frank Enos April 19, 2006

Defining Deception Deliberate choice to mislead a target without prior notification (Ekman‘’01) Often to gain some advantage Excludes:  Self-deception  Theater, etc.  Falsehoods due to ignorance/error  Pathological behaviors

Why study deception? Law enforcement / Jurisprudence Intelligence / Military / Security Business Politics Mental health practitioners Social situations  Is it ever good to lie?

Why study deception? What makes speech “believable”? Recognizing deception means recognizing intention. How do people spot a liar? How does this relate to other subjective phenomena in speech? E.g. emotion, charisma

Problems in studying deception? Most people are terrible at detecting deception — ~50% accuracy (Ekman & O’sullivan 1991, Aamodt 2006, etc.) People use subjective judgments — emotion, etc. Recognizing emotion is hard

People Are Terrible At This Group#Studies#SubjectsAccuracy % Criminals Secret service Psychologists Judges Cops Federal officers Students1228, Detectives Parole officers

Problems in studying deception? Hard to get good data  Real world (example)  Laboratory Ethical issues  Privacy  Subject rights  Claims of success But also ethical imperatives:  Need for reliable methods  Debunking faulty methods  False confessions

20th Century Lie Detection Polygraph   The Polygraph and Lie Detection (N.A.P. 2003) Voice Stress Analysis  Microtremors 8-12Hz  Universal Lie response   Reid  Behavioral Analysis Interview  Interrogation

Frank Tells Some Lies An Example…

Frank Tells Some Lies Maria: I’m buying tickets to Händel’s Messiah for me and my friends — would you like to join us? Frank: When is it? Maria: December 19th. Frank: Uh… the 19th… Maria: My two friends from school are coming, and Robin… Frank: I’d love to!

How to Lie (Ekman‘’01) Concealment Falsification Misdirecting Telling the truth falsely Half-concealment Incorrect inference dodge.

Frank Tells Some Lies Maria: I’m buying tickets to Handel’s Messiah for me and my friends — would you like to join us? Frank: When is it? Maria: December 19th. Frank: Uh… the 19th… Maria: My two friends from school are coming, and Robin… Frank: I’d love to! Concealment Falsification Misdirecting Telling the truth falsely Half-concealment Incorrect inference dodge.

Reasons To Lie (Frank‘’92 ) Self-preservation Self-presentation *Gain Altruistic (social) lies

How Not To Lie (Ekman‘’01) Leakage  Part of the truth comes out  Liar shows inconsistent emotion  Liar says something inconsistent with the lie Deception clues  Indications that the speaker is deceiving  Again, can be emotion  Inconsistent story

How Not To Lie (Ekman‘’01) Bad lines  Lying well is hard  Fabrication means keeping story straight  Concealment means remembering what is omitted  All this creates cognitive load  harder to hide emotion Detection apprehension (fear)  Target is hard to fool  Target is suspicious  Stakes are high  Serious rewards and/or punishments are at stake  Punishment for being caught is great

How Not To Lie (Ekman‘’01) Deception guilt  Stakes for the target are high  Deceit is unauthorized  Liar is not practiced at lying  Liar and target are acquainted  Target can’t be faulted as mean or gullible  Deception is unexpected by target Duping delight  Target poses particular challenge  Lie is a particular challenge  Others can appreciate liar’s performance

Features of Deception Cognitive  Coherence, fluency Interpersonal  Discourse features: DA, turn-taking, etc. Emotion

Describing Emotion Primary emotions  Acceptance, anger, anticipation, disgust, joy, fear, sadness, surprise One approach: continuous dim. model (Cowie/Lang) Activation – evaluation space Add control/agency Primary E’s differ on at least 2 dimensions of this scale (Pereira)

Problems With Emotion and Deception Relevant emotions may not differ much on these scales Othello error  People are afraid of the police  People are angry when wrongly accused  People think pizza is funny Brokow hazard  Failure to account for individual differences

Bulk of extant deception research… Not focused on verifying 20th century techniques Done by psychologists Considers primarily facial and physical cues “Speech is hard” Little focus on automatic detection of deception

Modeling Deception in Speech Lexical Prosodic/Acoustic Discourse

Deception in Speech (Depaulo ’03) Positive Correlates  Interrupted/repeated words  References to “external” events  Verbal/vocal uncertainty  Vocal tension  F0

Deception in Speech (Depaulo ’03) Negative Correlates  Subject stays on topic  Admitted uncertainties  Verbal/vocal immediacy  Admitted lack of memory  Spontaneous corrections

Problems, revisited Differences due to:  Gender  Social Status  Language  Culture  Personality

Columbia/SRI/Colorado Corpus With Julia Hirschberg, Stefan Benus, and colleagues from SRI/ICSI and U. C. Boulder Goals  Examine feasibility of automatic deception detection using speech  Discover or verify acoustic/prosodic, lexical, and discourse correlates of deception  Model a “non-guilt” scenario  Create a “clean” corpus

Columbia/SRI/Colorado Corpus Inflated-performance scenario Motivation: financial gain and self-presentation 32 Subjects: 16 women, 16 men Native speakers of Standard American English Subjects told study seeks to identify people who match profile based on “25 Top Entrepreneurs”

Columbia/SRI/Colorado Corpus Subjects take test in six categories:  Interactive, music, survival, food, NYC geography, civics Questions manipulated   2 too high; 2 too low; 2 match Subjects told study also seeks people who can convince interviewer they match profile  Self-presentation + reward Subjects undergo recorded interview in booth  Indicate veracity of factual content of each utterance using pedals

CSC Corpus: Data 15.2 hrs. of interviews; 7 hrs subject speech Lexically transcribed & automatically aligned  lexical/discourse features Lie conditions: Global Lie / Local Lie Segmentations (LT/LL): slash units (5709/3782), phrases (11,612/7108), turns (2230/1573) Acoustic features (± recognizer output)

um i was visiting a friend in venezuela and we went camping Columbia University– SRI/ICSI – University of Colorado Deception Corpus: An Example Segment Breath Group SEGMENT TYPE LABEL ACOUSTIC FEATURES LEXICAL FEATURES LIE max_corrected_pitch 5.7 mean_corrected_pitch 5.3 pitch_change_1st_word -6.7 pitch_change_last_word normalized_mean_energy 0.2 unintelligible_words 0.0 Obtained from subject pedal presses. has_filled_pause YES positive_emotion_word YES uses_past_tense NO negative_emotion_word NO contains_pronoun_i YES verbs_in_gerund YES Produced using ASR output and other acoustic analyses Produced automatically using lexical transcription. LIE PREDICTION

CSC Corpus: Results Classification (Ripper rule induction, randomized 5-fold cv)  Slash Units / Local Lies — Baseline 60.2% Lexical & acoustic: 62.8 %; + subject dependent: 66.4%  Phrases / Local Lies — Baseline 59.9% Lexical & acoustic 61.1%; + subject dependent: 67.1% Other findings  Positive emotion words  deception (LIWC)  Pleasantness  deception (DAL)  Filled pauses  truth  Some pitch correlation — varies with subject

Example JRIP rules: (cueLieToCueTruths >= 2) and (TOPIC = topic_newyork) and (numSUwithFPtoNumSU PEDAL=L (231.0/61.0) (cueLieToCueTruths >= 2) and (numSUwithFPtoNumSU = ) and (wu_F0_SLOPES_NOHD__LAST >= ) => PEDAL=L (284.0/117.0) (cueLieToCueTruths >= 2) and (wu_F0_RAW_MAX >= ) and (wu_DUR_PHONE_SPNN_AV PEDAL=L (262.0/115.0)

CSC Corpus: A Perception Study With Julia Hirschberg, Stefan Benus, Robin Cautin and colleagues from SRI/ICSI 32 Judges Each judge rated 2 interviews Judge Labels:  Local Lie using Praat  Global Lie on paper Takes pre- and post-test questionnaires Personality Inventory Judge receives ‘training’ on one subject.

By Judge 58.2% Acc. By Interviewee

Personality Measure: NEO-FFI Costa & McCrae (1992) Five-factor model  Openness to Experience  Conscientiousness  Extraversion  Agreeability  Neuroticism Widely used in psychology literature

Neuroticism, Openness & Agreeableness correlate with judge performance WRT Global lies.

These factors also provide strongly predictive models for accuracy at global lies.

Other Perception Findings No effect for training Judges’ post-test confidence did not correlate with pre-test confidence Judges who claimed experience had significantly higher pre-test confidence  But not higher accuracy! Many subjects used disfluencies as cues to D.  In this corpus, disfluencies correlate with TRUTH! (Benus et al. ‘06)

Our Future Work Individual differences  Wizards of deception Predicting Global Lies  Local lies as ‘hotspots’ New paradigm  Shorter  Addition of personality test for speakers  Addition of cognitive load