Predicting Strategic Behavior from Free Text

The connection between messaging and action is fundamental both to web applications, such as web search and sentiment analysis, and to economics. However, while prominent online applications exploit messaging in natural (human) language in order to predict non-strategic action selection, the economics literature focuses on the connection between structured stylized messaging to strategic decisions in games and multi-agent encounters. This paper aims to connect these two strands of research, which we consider highly timely and important due to the vast online textual communication on the web. Particularly, we introduce the following question: can free text expressed in natural language serve for the prediction of action selection in an economic context, modeled as a game? In order to initiate the research on this question, we introduce the study of an individual's action prediction in a one-shot game based on free text he/she provides, while being unaware of the game to be played. We approach the problem by attributing commonsensical personality attributes via crowd-sourcing to free texts written by individuals, and employing transductive learning to predict actions taken by these individuals in one-shot games based on these attributes. Our approach allows us to train a single classifier that can make predictions with respect to actions taken in multiple games. In experiments with three well-studied games, our algorithm compares favorably with strong alternative approaches. In ablation analysis, we demonstrate the importance of our modeling choices---the representation of the text with the commonsensical personality attributes and our classifier---to the predictive power of our model.

[1]  R. Kirk CONVENTION: A PHILOSOPHICAL STUDY , 1970 .

[2]  Tal Yarkoni Personality in 100,000 Words: A large-scale analysis of personality and word use among bloggers. , 2010, Journal of research in personality.

[3]  Cristian Danescu-Niculescu-Mizil,et al.  Winning Arguments: Interaction Dynamics and Persuasion Strategies in Good-faith Online Discussions , 2016, WWW.

[4]  Thorsten Joachims,et al.  Transductive Learning via Spectral Graph Partitioning , 2003, ICML.

[5]  Moshe Tennenholtz,et al.  Learning in One-Shot Strategic Form Games , 2006, ECML.

[6]  Jonathan Gratch,et al.  The Importance of Cognition and Affect for Artificially Intelligent Decision Makers , 2014, AAAI.

[7]  Jeffrey Pennington,et al.  GloVe: Global Vectors for Word Representation , 2014, EMNLP.

[8]  Noah A. Smith,et al.  Text-Driven Forecasting , 2010 .

[9]  Gaël Varoquaux,et al.  Scikit-learn: Machine Learning in Python , 2011, J. Mach. Learn. Res..

[10]  Sarit Kraus,et al.  Predicting Human Decision-Making: From Prediction to Action , 2018, Predicting Human Decision-Making.

[11]  Jalal Mahmud,et al.  25 Tweets to Know You: A New Model to Predict Personality with Social Media , 2017, ICWSM.

[12]  William Ickes,et al.  Predicting Final Course Performance From Students’ Written Self-Introductions , 2013 .

[13]  Amos Azaria,et al.  Giving Advice to People in Path Selection Problems , 2012, Interactive Decision Theory and Game Theory.

[14]  Jon Oberlander,et al.  What Are They Blogging About? Personality, Topic and Motivation in Blogs , 2009, ICWSM.

[15]  Douglas Walton,et al.  Argumentation Theory: A Very Short Introduction , 2009, Argumentation in Artificial Intelligence.

[16]  Milind Tambe,et al.  Learning about Cyber Deception through Simulations: Predictions of Human Decision Making with Deceptive Signals in Stackelberg Security Games , 2018, CogSci.

[17]  Amos Azaria,et al.  Strategic advice provision in repeated human-agent interactions , 2012, Autonomous Agents and Multi-Agent Systems.

[18]  J. H. Ward Hierarchical Grouping to Optimize an Objective Function , 1963 .

[19]  S. Srivastava,et al.  The Big Five Trait taxonomy: History, measurement, and theoretical perspectives. , 1999 .

[20]  Noah A. Smith,et al.  Predicting Risk from Financial Reports with Regression , 2009, NAACL.

[21]  Jeffrey Nichols,et al.  Who will retweet this?: Automatically Identifying and Engaging Strangers on Twitter to Spread Information , 2014, IUI.

[22]  Brendan T. O'Connor,et al.  Predicting a Scientific Community’s Response to an Article , 2011, EMNLP.

[23]  Jeffrey Nichols,et al.  Recommending targeted strangers from whom to solicit information on social media , 2013, IUI '13.

[24]  Rui Prada,et al.  Teaming up humans with autonomous synthetic characters , 2008, AI Commun..

[25]  James W. Pennebaker,et al.  Linguistic Inquiry and Word Count (LIWC2007) , 2007 .

[26]  Noah A. Smith,et al.  A Utility Model of Authors in the Scientific Community , 2015, EMNLP.

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

[28]  Noah A. Smith,et al.  Movie Reviews and Revenues: An Experiment in Text Regression , 2010, NAACL.

[29]  Thorsten Joachims,et al.  Transductive Inference for Text Classification using Support Vector Machines , 1999, ICML.

[30]  Sarit Kraus,et al.  Strategic Negotiation in Multiagent Environments , 2001, Intelligent robots and autonomous agents.

[31]  D. Funder,et al.  Personality as manifest in word use: correlations with self-report, acquaintance report, and behavior. , 2008, Journal of personality and social psychology.

[32]  J. Pennebaker,et al.  The Psychological Meaning of Words: LIWC and Computerized Text Analysis Methods , 2010 .

[33]  Jennifer Golbeck,et al.  Predicting Personality from Twitter , 2011, 2011 IEEE Third Int'l Conference on Privacy, Security, Risk and Trust and 2011 IEEE Third Int'l Conference on Social Computing.

[34]  Felix Hill,et al.  SimLex-999: Evaluating Semantic Models With (Genuine) Similarity Estimation , 2014, CL.

[35]  Matthew Rabin,et al.  A Model of Pre-game Communication , 1991 .

[36]  Jordan B. Peterson,et al.  Personality and language use in self-narratives. , 2009 .

[37]  Vadlamani Ravi,et al.  A survey on opinion mining and sentiment analysis: Tasks, approaches and applications , 2015, Knowl. Based Syst..

[38]  Nir Friedman,et al.  Probabilistic Graphical Models - Principles and Techniques , 2009 .

[39]  D. Asch,et al.  Facebook language predicts depression in medical records , 2018, Proceedings of the National Academy of Sciences.

[40]  Panagiotis G. Ipeirotis,et al.  Estimating the Helpfulness and Economic Impact of Product Reviews: Mining Text and Reviewer Characteristics , 2010, IEEE Transactions on Knowledge and Data Engineering.

[41]  Bo Pang,et al.  Thumbs up? Sentiment Classification using Machine Learning Techniques , 2002, EMNLP.

[42]  P. Costa,et al.  The revised NEO personality inventory (NEO-PI-R) , 2008 .

[43]  Ehud Rivlin,et al.  Placing search in context: the concept revisited , 2002, TOIS.

[44]  David M. Blei,et al.  Probabilistic topic models , 2012, Commun. ACM.

[45]  Miguel A. Costa-Gomes,et al.  Cognition and Behavior in Normal-Form Games: An Experimental Study , 1998 .

[46]  Kevin Leyton-Brown,et al.  Deep Learning for Predicting Human Strategic Behavior , 2016, NIPS.

[47]  Mark Dredze,et al.  Non-Expert Correction of Automatically Generated Relation Annotations , 2010, Mturk@HLT-NAACL.

[48]  J. Sobel,et al.  STRATEGIC INFORMATION TRANSMISSION , 1982 .

[49]  S. Schwartz Universals in the Content and Structure of Values: Theoretical Advances and Empirical Tests in 20 Countries , 1992 .

[50]  Colin Camerer,et al.  A cognitive hierarchy theory of one-shot games: Some preliminary results , 2003 .

[51]  Sarit Kraus,et al.  Providing Arguments in Discussions on the Basis of the Prediction of Human Argumentative Behavior , 2016, ACM Trans. Interact. Intell. Syst..

[52]  M. Spence Job Market Signaling , 1973 .

[53]  Mausam,et al.  Optimal Testing for Crowd Workers , 2016, AAMAS.

[54]  Moshe Tennenholtz,et al.  Psychological Forest: Predicting Human Behavior , 2016, AAAI.

[55]  Dirk Hovy,et al.  Personality Traits on Twitter—or—How to Get 1,500 Personality Tests in a Week , 2015, WASSA@EMNLP.

[56]  Alexander Gammerman,et al.  Learning by Transduction , 1998, UAI.

[57]  Lillian Lee,et al.  Opinion Mining and Sentiment Analysis , 2008, Found. Trends Inf. Retr..

[58]  Ya'akov Gal,et al.  An Agent Design for Repeated Negotiation and Information Revelation with People , 2013, AAAI.

[59]  Gemma Boleda,et al.  Distributional Semantics in Technicolor , 2012, ACL.

[60]  Brendan T. O'Connor,et al.  Learning Latent Personas of Film Characters , 2013, ACL.

[61]  Brendan T. O'Connor,et al.  From Tweets to Polls: Linking Text Sentiment to Public Opinion Time Series , 2010, ICWSM.

[62]  Ya'akov Gal,et al.  A cultural sensitive agent for human-computer negotiation , 2012, AAMAS.

[63]  R. Rosenthal A class of games possessing pure-strategy Nash equilibria , 1973 .