Machine Behaviour - Papers and Resources

---

Conversations in Machine Behaviour - Season 1

• "Machine’s Moral Codes"
  • with Azim Shariff & Iyad Rahwan [Video]
• "How AI Will Shift Human Communication"
  • with Nick Obradovich & Bill Powers [Video]
• "The Benefits and Limits of Personal Robots"
  • with Cynthia Breazeal & Nick Obradovich [Video]
• "AI in the Real World"
  • with Ece Kamar & Nick Obradovich [Video]
• "Ethics in Artificial Intelligence"
  • with Jean-François Bonnefon & Iyad Rahwan [Video]
• "Social Learning and Artificial Intelligence"
  • with Nicholas Christakis & Iyad Rahwan [Video]
• "Artificially Intelligent Decision Makers in the Real World"
  • with Michael Wellman & Bill Powers [Video]
• "AI and the Human Experience"
  • with Sandy Pentland & Manuel Cebrian [Video]
• "Artificial Intelligence in the Marketplace"
  • with David Parkes & Iyad Rahwan [Video]
• "Social Media and the Bifurcation of the Internet"
  • with Manuel Cebrian & Nick Obradovich [Video]
• "Making Human-AI Cooperation Possible"
  • with Jacob Crandall & Manuel Cebrian [Video]
• "AI and Censorship"
  • with Molly Roberts & Nick Obradovich [Video]
• "How Social Networking Became the Biggest Big Data"
  • with David Lazer & Bill Powers [Video]
• "How Social Networks Reinforce Insulated Communities"
  • with Matt Jackson & Nick Obradovich [Video]
• "Understanding Evolutionary Robotics" with Josh Bongard & Manuel Cebrian
  • with Josh Bongard & Manuel Cebrian [Video]
• "AI and Asimov—The Three Laws in the Real World"
  • with Iyad Rahwan & Nick Obradovich [Video]

---

Papers

2019

• Machine behaviour
  • Rahwan, Iyad, Manuel Cebrian, Nick Obradovich, Josh Bongard, Jean-François Bonnefon, Cynthia Breazeal, Jacob W. Crandall, et al. Nature 568, no. 7753 (April 2019): 477. [Paper]
• The Human Network: How Your Social Position Determines Your Power, Beliefs, and Behaviors
  • Jackson, M. et al (Knopf Doubleday, 2019).

2018

• ‘It’s reducing a human being to a percentage’: perceptions of justice in algorithmic decisions.
  • Binns, R. et al. In Proc. 2018 CHI Conference on Human Factors in Computing Systems 377 (ACM, 2018). [Paper]
• Human decisions and machine predictions.
  • Kleinberg, J., Lakkaraju, H., Leskovec, J., Ludwig, J. & Mullainathan, S., Q. J. Econ. 133, 237–293 (2018). [Paper]
• Measuring young children’s long-term relationships with social robots.
  • Westlund, J. M. K., Park, H. W., Williams, R. & Breazeal, C. In Proc. 17th ACM Conference on Interaction Design and Children 207–218 (ACM, 2018). [Paper]
• Living, Learning and Creating with Social Robots
  • [Slides]
• Cooperating with machines.
  • Crandall, J. W. et al. Nat. Commun. 9, 233 (2018) [Paper]
• Gender shades: intersectional accuracy disparities in commercial gender classification.
  • Buolamwini, J. & Gebru, T. In Proc. 1st Conference on Fairness, Accountability and Transparency (eds Friedler, S. A. & Wilson, C.) 81, 77–91 (PMLR, 2018). [Paper]
• Closing the AI knowledge gap.
  • Epstein, Z. et al. (2018). [Paper]
• Model cards for model reporting.
  • Mitchell, M. et al. (2018). [Paper]
• Datasheets for datasets.
  • Gebru, T. et al. (2018). [Paper]
• The Moral Machine experiment.
  • Awad, E. et al. Nature 563, 59–64 (2018). [Paper]
• Visual interpretability for deep learning: a survey.
  • Zhang, Q.-S. & Zhu, S.-C. Front. Inf. Technol. Electronic Eng. 19, 27–39 (2018). [pdf]
• The spread of true and false news online.
  • Vosoughi, S., Roy, D. & Aral, S. Science 359, 1146–1151 (2018). [Paper]
• Psychlab: a psychology laboratory for deep reinforcement learning agents.
  • Leibo, J. Z. et al. (2018) [Paper]
• AI at Google: Our Principles. (2018).
  • Pichai, S. [Google Blog]
• Huggable: the impact of embodiment on promoting socio-emotional interactions for young pediatric inpatients.
  • Jeong, S., Breazeal, C., Logan, D. & Weinstock, P. In Proc. 2018 CHI Conference on Human Factors in Computing Systems 495 (ACM, 2018).

2017

• Observing algorithmic marketplaces in-the-wild.
  • Chen, L. & Wilson, C. et al. SIGecom Exch. 15, 34–39 (2017). [Paper]
• Bias in Online freelance marketplaces: evidence from TaskRabbit and Fiverr.
  • Hannák, A. et al. In Proc. ACM Conference on Computer Supported Cooperative Work and Social Computing 1914–1933 (2017). [Paper]
• Ethical issues for autonomous trading agents.
  • Wellman, M. P. & Rajan, U. et al. Minds Mach. 27, 609–624 (2017). [Paper]
• Multipolicy decision-making for autonomous driving via changepoint-based behavior prediction: theory and experiment.
  • Galceran, E., Cunningham, A. G., Eustice, R. M. & Olson, E. et al. Auton. Robots 41, 1367–1382 (2017). [Paper]
• Analyzing Uber’s ride-sharing economy.
  • Kooti, F. et al. In Proc. 26th International Conference on World Wide Web 574–582 (International World Wide Web Conferences Steering Committee, 2017). [Paper]
• Growing growth mindset with a social robot peer.
  • Park, H. W., Rosenberg-Kima, R., Rosenberg, M., Gordon, G. & Breazeal, C. et al. In Proc. 2017 ACM/IEEE International Conference on Human–Robot Interaction 137–145 (ACM, 2017). [Paper]
• Flat vs. expressive storytelling: young children’s learning and retention of a social robot’s narrative.
  • Kory Westlund, J. M. et al. Front. Hum. Neurosci. 11, 295 (2017). [Paper]
• Bots as virtual confederates: design and ethics.
  • Krafft, P. M., Macy, M. & Pentland, A. et al. In Proc. 2017 ACM Conference on Computer Supported Cooperative Work and Social Computing 183–190 (ACM, 2017). [Paper]
• The AI detectives.
  • Voosen, P. et al. Science 357, 22–27 (2017). [Paper]
• Towards a rigorous science of interpretable machine learning.
  • Doshi-Velez, F. & Kim, B. et al. [Paper]
• Identifying unknown unknowns in the open world: representations and policies for guided exploration.
  • Lakkaraju, H., Kamar, E., Caruana, R. & Horvitz, E. In Proc. 31st Association for the Advancement of Artificial Intelligence Conference on Artificial Intelligence 2 (2017). [Paper]
• Algorithmic decision making and the cost of fairness.
  • Corbett-Davies, S., Pierson, E., Feller, A., Goel, S. & Huq, A. et al. In Proc. 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining 797–806 (ACM, 2017). [Paper]
• Semantics derived automatically from language corpora contain human-like biases.
  • Caliskan, A., Bryson, J. J. & Narayanan, A. et al. Science 356, 183–186 (2017). [Paper]
• Runaway feedback loops in predictive policing.
  • Ensign, D., Friedler, S. A., Neville, S., Scheidegger, C. & Venkatasubramanian, S. et al. [Paper]
• Mastering the game of Go without human knowledge.
  • Silver, D. et al. Nature 550, 354–359 (2017). [Paper]
• SmoothGrad: removing noise by adding noise. (2017).
  • Smilkov, D., Thorat, N., Kim, B., Viégas, F. & Wattenberg, M. et al. [Paper]
• Even good bots fight: the case of Wikipedia.
  • Tsvetkova, M., García-Gavilanes, R., Floridi, L. & Yasseri, T. PLoS ONE 12, e0171774 (2017). [Paper]
• Evidence of complex contagion of information in social media: an experiment using Twitter bots.
  • Mønsted, B., Sapieżyński, P., Ferrara, E. & Lehmann, S. PLoS ONE 12, e0184148 (2017). [Paper]
• Toward scalable social alt text: conversational crowdsourcing as a tool for refining vision-to-language technology for the blind. Proc.
  • Salisbury, E., Kamar, E. & Morris, M. R. et al. 5th AAAI Conference on Human Computation and Crowdsourcing (2017). [Paper]
• What can machine learning do? Workforce implications.
  • Brynjolfsson, E. & Mitchell, T. et al. Science 358, 1530–1534 (2017). [Paper]
• Deep reinforcement learning from human preferences.
  • Christiano, P. F. et al. In Proc. Advances in Neural Information Processing Systems 30 (eds Guyon, I. et al.) 4299–4307 (Curran Associates, 2017). [Paper]
• Understanding human–machine networks: a cross-disciplinary survey.
  • Tsvetkova, M. et al. ACM Comput. Surv. 50, 12:1–12:35 (2017). [Paper]
• Locally noisy autonomous agents improve global human coordination in network experiments.
  • Shirado, H. & Christakis, N. A. et al. Nature 545, 370–374 (2017)

2016

• Building Machines That Learn and Think Like People
  • Brenden M. Lake, Tomer D. Ullman, Joshua B. Tenenbaum, Samuel J. Gershman, Behavioral and Brain Sciences, (2016). [Paper]
• Why should I trust you? Explaining the predictions of any classifier.
  • Ribeiro, M. T., Singh, S. & Guestrin, C. et al. In Proc. 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining 1135–1144 (ACM, 2016). [Paper]
• The rise of social bots.
  • Ferrara, E., Varol, O., Davis, C., Menczer, F. & Flammini, A. et al. Commun. ACM 59, 96–104 (2016). [Paper]
• Concrete problems in AI safety.
  • Amodei, D. et al. (2016). [Paper]
• The social dilemma of autonomous vehicles.
  • Bonnefon, J.-F., Shariff, A. & Rahwan, I. Science 352, 1573–1576 (2016). [Paper]
• Machine bias.
  • Angwin, J., Larson, J., Mattu, S. & Kirchner, L. et al. ProPublica (2016). [Article]
• Multi-agent cooperation and the emergence of (natural) language.
  • Lazaridou, A., Peysakhovich, A. & Baroni, M. et al. [Paper]
• Artificial Intelligence and Life in 2030. One Hundred Year Study on Artificial Intelligence: Report of the 2015–2016
  • Stone, P. et al. Study Panel (Stanford University, 2016). [Report]
• Noise: how to overcome the high, hidden cost of inconsistent decision making. Harvard Business Review (2016).
  • Kahneman, D., Rosenfield, A. M., Gandhi, L. & Blaser, T. et al. [Article]
• The AI Now report: The Social and Economic Implications of Artificial Intelligence Technologies in the Near-term.
  • Crawford, K. et al. (2016). [Report]
• Synchrony and reciprocity: key mechanisms for social companion robots in therapy and care.
  • Lorenz, T., Weiss, A. & Hirche, S. et al. Int. J. Soc. Robot. 8, 125–143 (2016). [pdf]
• Killer Robots: Legality and Ethicality of Autonomous Weapons
  • Krishnan, A. et al. (Routledge, 2016).
• O’Neil, C. Weapons of Math Destruction: How Big Data Increases Inequality and Threatens Democracy (Broadway Books, 2016).

2015

• Algorithm aversion: people erroneously avoid algorithms after seeing them err.
  • Dietvorst, B. J., Simmons, J. P. & Massey, C. et al. J. Exp. Psychol. Gen. 144, 114–126 (2015). [Article]
• The rise of the social algorithm.
  • Lazer, D. et al. Science 348, 1090–1091 (2015). [Article]
• Economic reasoning and artificial intelligence.
  • Parkes, D. C. & Wellman, M. P. et al. Science 349, 267–272 (2015). [Article]
• Robots that can adapt like animals.
  • Cully, A., Clune, J., Tarapore, D. & Mouret, J.-B. et al. Nature 521, 503–507 (2015). [Paper]
• Automated Experiments on Ad Privacy Settings.
  • Datta, A., Tschantz, M. C. & Datta, A. et al. Proc. Privacy Enhancing Technologies 2015, 92–112 (2015). [Paper]
• How to solve the world’s biggest problems.
  • Ledford, H. et al. Nature 525, 308–311 (2015). [Article]
• Exposure to ideologically diverse news and opinion on Facebook.
  • Bakshy, E., Messing, S. & Adamic, L. A. et al. Science 348, 1130–1132 (2015). [pdf]
• Autonomous weapons: an open letter from AI & robotics researchers.
  • Future of Life Institute. (2015) [Letter]
• Pentland, A. Social Physics: How Social Networks Can Make Us Smarter (Penguin, 2015).

2014

• Exploring the filter bubble: the effect of using recommender systems on content diversity.
  • Nguyen, T. T., Hui, P.-M., Harper, F. M., Terveen, L. & Konstan, J. A. et al. In Proc. 23rd International Conference on World Wide Web 677–686 (ACM, 2014). [Paper]
• Engineering the public: big data, surveillance and computational politics.
  • Tufekci, Z. et al. [Link]
• Experimental evidence of massive-scale emotional contagion through social networks.
  • Kramer, A. D. I., Guillory, J. E. & Hancock, J. T. et al. Proc. Natl Acad. Sci. USA 111, 8788–8790 (2014). [pdf]
• The strategic robot problem: lethal autonomous weapons in war.
  • Roff, H. M. et al. J. Mil. Ethics 13, 211–227 (2014).

2013

• Intriguing properties of neural networks.
  • Szegedy, C. et al. (2013). [Paper]
• Abrupt rise of new machine ecology beyond human response time.
  • Johnson, N. et al. Sci. Rep. 3, 2627 (2013). [Paper]
• Discrimination in online ad delivery.
  • Sweeney, L. et al. Queueing Syst. 11, 10 (2013). [pdf]
• Moore’s law versus Murphy’s law: algorithmic trading and its discontents.
  • Kirilenko, A. A. & Lo, A. W. et al. J. Econ. Perspect. 27, 51–72 (2013). [Article]
• The arcade learning environment: an evaluation platform for general agents.
  • Bellemare, M. G., Naddaf, Y., Veness, J. & Bowling, M. et al. J. Artif. Intell. Res. 47, 253–279 (2013). [Paper]
• Learning fair representations.
  • Zemel, R., Wu, Y., Swersky, K., Pitassi, T. & Dwork, C. et al. In Proc. International Conference on Machine Learning 325–333 (2013). [Paper]
• Emergent sensing of complex environments by mobile animal groups.
  • Berdahl, A., Torney, C. J., Ioannou, C. C., Faria, J. J. & Couzin, I. D. et al. Science 339, 574–576 (2013). [Link]
• Robustness and Evolvability in Living Systems
  • Wagner, A. et al. (Princeton Univ. Press, 2013).

2012

• What Question Would Turing Pose Today?
  • Barbara Grosz, AI Magazine, (2012). [Paper]
• Online dating: a critical analysis from the perspective of psychological science.
  • Finkel, E. J., Eastwick, P. W., Karney, B. R., Reis, H. T. & Sprecher, S. et al. Psychol. Sci. Public Interest 13, 3–66 (2012).[pdf]
• Feeling robots and human zombies: mind perception and the uncanny valley.
  • Gray, K. & Wegner, D. M. et al. Cognition 125, 125–130 (2012). [Paper]
• Socially assistive robots in elderly care: a systematic review into effects and effectiveness.
  • Bemelmans, R., Gelderblom, G. J., Jonker, P. & de Witte, L. et al. J. Am. Med. Dir. Assoc. 13, 114–120 (2012).
• Combining human and machine intelligence in large-scale crowdsourcing.
  • Kamar, E., Hacker, S. & Horvitz, E. et al. 11th International Conference on Autonomous Agents and Multiagent Systems 467–474. [Paper]

2011

• Robot vacuum cleaner personality and behavior.
  • Hendriks, B., Meerbeek, B., Boess, S., Pauws, S. & Sonneveld, M. et al. Int. J. Soc. Robot. 3, 187–195 (2011). [Paper]
• Drone warfare: blowback from the new American way of war.
  • Hudson, L., Owens, C. S. & Flannes, M. et al. Middle East Policy 18, 122–132 (2011). [Article]
• Uninformed individuals promote democratic consensus in animal groups.
  • Couzin, I. D. et al. Science 334, 1578–1580 (2011). [Paper]

2010

• Empirical limitations on high-frequency trading profitability.
  • Kearns, M., Kulesza, A. & Nevmyvaka, Y. et al. J. Trading 5, 50–62 (2010). [Paper]
• Matching and sorting in online dating.
  • Hitsch, G. J., Hortaçsu, A. & Ariely, D. et al. Am. Econ. Rev. 100, 130–163 (2010). [Paper]