It Takes Two to Lie: One to Lie, and One to Listen

Trust is implicit in many online text conversations—striking up new friendships, or asking for tech support. But trust can be betrayed through deception. We study the language and dynamics of deception in the negotiation-based game Diplomacy, where seven players compete for world domination by forging and breaking alliances with each other. Our study with players from the Diplomacy community gathers 17,289 messages annotated by the sender for their intended truthfulness and by the receiver for their perceived truthfulness. Unlike existing datasets, this captures deception in long-lasting relationships, where the interlocutors strategically combine truth with lies to advance objectives. A model that uses power dynamics and conversational contexts can predict when a lie occurs nearly as well as human players.

[1]  Zhi-Hua Zhou,et al.  Ieee Transactions on Knowledge and Data Engineering 1 Training Cost-sensitive Neural Networks with Methods Addressing the Class Imbalance Problem , 2022 .

[2]  Claire Cardie,et al.  Finding Deceptive Opinion Spam by Any Stretch of the Imagination , 2011, ACL.

[3]  Alex Black,et al.  Truths, Lies, and Equivocations: The Effects of Conflicting Goals on Discourse , 1990 .

[4]  Yonatan Belinkov,et al.  Analysis Methods in Neural Language Processing: A Survey , 2018, TACL.

[5]  Claire Cardie,et al.  Estimating the prevalence of deception in online review communities , 2012, WWW.

[6]  Justin Cheng,et al.  Don’t Let Me Be Misunderstood:Comparing Intentions and Perceptions in Online Discussions , 2020, WWW.

[7]  Cristian Danescu-Niculescu-Mizil,et al.  Linguistic Harbingers of Betrayal: A Case Study on an Online Strategy Game , 2015, ACL.

[8]  Massimo Poesio,et al.  Automatic deception detection in Italian court cases , 2013, Artificial Intelligence and Law.

[9]  Verónica Pérez-Rosas,et al.  Automatic Detection of Fake News , 2017, COLING.

[10]  David Bamman,et al.  Contextualized Sarcasm Detection on Twitter , 2015, ICWSM.

[11]  Nina Wacholder,et al.  Identifying Sarcasm in Twitter: A Closer Look , 2011, ACL.

[12]  Jure Leskovec,et al.  A computational approach to politeness with application to social factors , 2013, ACL.

[13]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[14]  Eyal Amir,et al.  Psycholinguistic Features for Deceptive Role Detection in Werewolf , 2016, NAACL.

[15]  Bo Xie,et al.  Public library computer training for older adults to access high-quality Internet health information. , 2009, Library & information science research.

[16]  Ben Shneiderman,et al.  Designing trust into online experiences , 2000, CACM.

[17]  Dorée D. Seligmann,et al.  Power dynamics in spoken interactions: a case study on 2012 republican primary debates , 2013, WWW '13 Companion.

[18]  James F. Roiger,et al.  Testing Interpersonal Deception Theory: The Language of Interpersonal Deception , 1996 .

[19]  Noah J. Goldstein,et al.  Social influence: compliance and conformity. , 2004, Annual review of psychology.

[20]  Kalina Bontcheva,et al.  Corpus Annotation through Crowdsourcing: Towards Best Practice Guidelines , 2014, LREC.

[21]  James Edwin Mahon,et al.  The Definition of Lying and Deception , 2015 .

[22]  Jeffrey T. Hancock,et al.  Ethical dilemma: Deception dynamics in computer‐mediated group communication , 2017, J. Assoc. Inf. Sci. Technol..

[23]  James J. Lindsay,et al.  Cues to deception. , 2003, Psychological bulletin.

[24]  Dante Alighieri,et al.  Dante's Inferno, The Indiana Critical Edition , 1995 .

[25]  Chengkai Li,et al.  Toward Automated Fact-Checking: Detecting Check-worthy Factual Claims by ClaimBuster , 2017, KDD.

[26]  Verónica Pérez-Rosas,et al.  Box of Lies: Multimodal Deception Detection in Dialogues , 2019, NAACL.

[27]  Marti A. Hearst,et al.  Why phishing works , 2006, CHI.

[28]  Gün R. Semin,et al.  Linguistic cues predict fraudulent events in a corporate social network , 2010 .

[29]  Claire Cardie,et al.  In Search of a Gold Standard in Studies of Deception , 2012 .

[30]  Carlos Guestrin,et al.  "Why Should I Trust You?": Explaining the Predictions of Any Classifier , 2016, ArXiv.

[31]  B. Cornwell,et al.  Love on the Internet: involvement and misrepresentation in romantic relationships in cyberspace vs. realspace , 2001, Comput. Hum. Behav..

[32]  B. Depaulo,et al.  Liking and Lying , 1996 .

[33]  J. Pennebaker,et al.  Lying Words: Predicting Deception from Linguistic Styles , 2003, Personality & social psychology bulletin.

[34]  Jeffrey T. Hancock,et al.  What Lies Beneath: The Linguistic Traces of Deception in Online Dating Profiles , 2012 .

[35]  Navneet Kaur,et al.  Opinion mining and sentiment analysis , 2016, 2016 3rd International Conference on Computing for Sustainable Global Development (INDIACom).

[36]  Lyn M. Van Swol,et al.  Justifications Offered, Questions Asked, and Linguistic Patterns in Deceptive and Truthful Monetary Interactions , 2016 .

[37]  Yada Zhu,et al.  Social Phishing , 2018, Encyclopedia of Social Network Analysis and Mining. 2nd Ed..

[38]  Neil Shah,et al.  False Information on Web and Social Media: A Survey , 2018, ArXiv.

[39]  Roberto Navigli,et al.  It’s All Fun and Games until Someone Annotates: Video Games with a Purpose for Linguistic Annotation , 2014, TACL.

[40]  Ming-Wei Chang,et al.  BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding , 2019, NAACL.

[41]  Pietro Perona,et al.  Visual Recognition with Humans in the Loop , 2010, ECCV.

[42]  Nathalie Japkowicz,et al.  The class imbalance problem: A systematic study , 2002, Intell. Data Anal..

[43]  Joelle Pineau,et al.  No Press Diplomacy: Modeling Multi-Agent Gameplay , 2019, NeurIPS.

[44]  A. Hadley.  Lying , 1908, Encyclopedia of Evolutionary Psychological Science.

[45]  Han Liu,et al.  "Why is 'Chicago' deceptive?" Towards Building Model-Driven Tutorials for Humans , 2020, CHI.

[46]  Isabelle Torrance,et al.  Distorted Oaths in Aeschylus , 2015 .

[47]  Lorrie Faith Cranor,et al.  A Framework for Reasoning About the Human in the Loop , 2008, UPSEC.

[48]  V. S. Subrahmanian,et al.  An Army of Me: Sockpuppets in Online Discussion Communities , 2017, WWW.

[49]  Eric Wallace,et al.  Trick Me If You Can: Human-in-the-Loop Generation of Adversarial Examples for Question Answering , 2018, TACL.

[50]  Douglas W. Oard,et al.  Believe Me - We Can Do This! Annotating Persuasive Acts in Blog Text , 2011, Computational Models of Natural Argument.

[51]  Brendan T. O'Connor,et al.  Cheap and Fast – But is it Good? Evaluating Non-Expert Annotations for Natural Language Tasks , 2008, EMNLP.

[52]  Timothy R. Levine,et al.  Accuracy in detecting truths and lies: Documenting the “veracity effect” , 1999 .

[53]  Philip Resnik,et al.  More than Words: Syntactic Packaging and Implicit Sentiment , 2009, NAACL.

[54]  Julia Hirschberg,et al.  Linguistic Cues to Deception and Perceived Deception in Interview Dialogues , 2018, NAACL.

[55]  Tian Lin,et al.  Dissecting Spear Phishing Emails for Older vs Young Adults: On the Interplay of Weapons of Influence and Life Domains in Predicting Susceptibility to Phishing , 2017, CHI.

[56]  Jon M. Kleinberg,et al.  Echoes of power: language effects and power differences in social interaction , 2011, WWW.

[57]  Anne K. Gordon,et al.  The enigma of altruistic lying: Perspective differences in what motivates and justifies lie telling within romantic relationships , 2004 .

[58]  Mohamed Abouelenien,et al.  Verbal and Nonverbal Clues for Real-life Deception Detection , 2015, EMNLP.