Abstract
Trust as a precursor for users' acceptance of artificial intelligence (AI) technologies that operate as a conceptual extension of humans (e.g., autonomous vehicles (AVs)) is highly influenced by users' risk perception amongst other factors. Prior studies that investigated the interplay between risk and trust perception recommended the development of real-time tools for monitoring cognitive states (e.g., trust). The primary objective of this study was to investigate a feature selection method that yields feature sets that can help develop a highly optimized and stable ensemble trust classifier model. The secondary objective of this study was to investigate how varying levels of risk perception influence users' trust and overall reliance on technology. A within-subject four-condition experiment was implemented with an AV driving game. This experiment involved 25 participants, and their electroencephalogram, electrodermal activity, and facial electromyogram psychophysiological signals were acquired. We applied wrapper, filter, and hybrid feature selection methods on the 82 features extracted from the psychophysiological signals. We trained and tested five voting-based ensemble trust classifier models using training and testing datasets containing only the features identified by the feature selection methods. The results indicate the superiority of the hybrid feature selection method over other methods in terms of model performance. In addition, the self-reported trust measurement and overall reliance of participants on the technology (AV) measured with joystick movements throughout the game reveals that a reduction in risk results in an increase in trust and overall reliance on technology.
- [n.d.]. 2019 CIGI-Ipsos Global Survey on Internet Security and Trust. http://www.cigionline.org/internet-survey-2019Google Scholar
- David A Abbink, Tom Carlson, Mark Mulder, Joost CF de Winter, Farzad Aminravan, Tricia L Gibo, and Erwin R Boer. 2018. A topology of shared control systems-finding common ground in diversity. IEEE Transactions on Human-Machine Systems 48, 5 (2018), 509--525.Google Scholar
Cross Ref
- Muhammad Aurangzeb Ahmad, Carly Eckert, and Ankur Teredesai. 2018. Interpretable machine learning in healthcare. In Proceedings of the 2018 ACM international conference on bioinformatics, computational biology, and health informatics. 559--560. Google Scholar
Digital Library
- Ighoyota Ben Ajenaghughrure, Sonia Claudia da Costa Sousa, and David Lamas. 2020. Risk and Trust in artificial intelligence technologies: A case study of Autonomous Vehicles. In 2020 13th International Conference on Human System Interaction (HSI). IEEE, 118--123.Google Scholar
Cross Ref
- Ighoyota Ben Ajenaghughrure, Sonia C Sousa, Ilkka Johannes Kosunen, and David Lamas. 2019. Predictive model to assess user trust: a psycho-physiological approach. In Proceedings of the 10th Indian Conference on Human-Computer Interaction. ACM, 4. Google Scholar
Digital Library
- Ighoyota Ben Ajenaghughrure, Sonia Da Costa Sousa, and David Lamas. 2020. Measuring Trust with Psychophysiological Signals: A Systematic Mapping Study of Approaches Used. Multimodal Technologies and Interaction 4, 3 (2020), 63.Google Scholar
Cross Ref
- Kumar Akash, Wan-Lin Hu, Neera Jain, and Tahira Reid. 2018. A classification model for sensing human trust in machines using EEG and GSR. ACM Transactions on Interactive Intelligent Systems (TiiS)8, 4 (2018), 1--20. Google Scholar
Digital Library
- Kumar Akash, Tahira Reid, and Neera Jain. 2018. Adaptive Probabilistic Classification of Dynamic Processes: A Case Study on Human Trust in Automation. In 2018 Annual American Control Conference (ACC). IEEE, 246--251.Google Scholar
- J Andreassi. 2000. Psychophysiology: Human Behavior and Physiological Response; Lawrence Erlabaum Associates. Inc.: Mahwah, NJ, USA(2000).Google Scholar
- Naomi Aoki. 2020. The importance of the assurance that "humans are still in the decision loop" for public trust in artificial intelligence: Evidence from an online experiment.Computers in Human Behavior(2020), 106572.Google Scholar
- Edmond Awad, Sohan Dsouza, Richard Kim, Jonathan Schulz, Joseph Henrich, Azim Shariff, Jean-François Bonnefon, and Iyad Rahwan. 2018. The moral machine experiment. Nature 563, 7729 (2018), 59.Google Scholar
- Izak Benbasat and Weiquan Wang. 2005. Trust in and adoption of online recommendation agents. Journal of the association for information systems 6, 3 (2005), 4.Google Scholar
Cross Ref
- Mathias Benedek and Christian Kaernbach. 2010. A continuous measure of phasic electrodermal activity.Journal of neuroscience methods 190, 1 (2010), 80--91.Google Scholar
- Cindy L Bethel, Kristen Salomon, Robin R Murphy, and Jennifer L Burke. 2007. Survey of psychophysiology measurements applied to human-robot interaction. In RO-MAN 2007-The 16th IEEE International Symposium on Robot and Human Interactive Communication. IEEE, 732--737.Google Scholar
Cross Ref
- Sviatoslav Braynov. 2013. What human trust is and is not: on the biology of human trust. In 2013 AAAI Spring Symposium Series.Google Scholar
- Lars Buitinck, Gilles Louppe, Mathieu Blondel, Fabian Pedregosa, Andreas Mueller, Olivier Grisel, Vlad Niculae, Peter Prettenhofer, Alexandre Gramfort, Jaques Grobler, Robert Layton, Jake Vander Plas, Arnaud Joly, Brian Holt, and Gaël Varoquaux. 2013. API design for machine learning software: experiences from the scikit-learn project. In ECML PKDD Workshop: Languages for Data Mining and Machine Learning. 108--122.Google Scholar
- Charles S Carver and Teri L White. 1994. Behavioral inhibition, behavioral activation, and affective responses to impending reward and punishment: the BIS/BAS scales. Journal of personality and social psychology 67, 2 (1994), 319.Google Scholar
Cross Ref
- Girish Chandrashekar and Ferat Sahin. 2014. A survey on feature selection methods. Computers & Electrical Engineering 40, 1 (2014), 16--28. Google Scholar
Digital Library
- Haruna Chiroma, Sameem Abdulkareem, Adamu Abubakar, and Tutut Herawan. 2017. Neural networks optimization through genetic algorithm searches: a review. Appl. Math. Inf. Sci11, 6 (2017), 1543--1564.Google Scholar
Cross Ref
- Benjamin R Cowan, Nadia Pantidi, David Coyle, Kellie Morrissey, Peter Clarke, Sara Al-Shehri, David Earley, and Natasha Bandeira. 2017. "What can i help you with?" infrequent users' experiences of intelligent personal assistants. In Proceedings of the 19th International Conference on Human-Computer Interaction with Mobile Devices and Services. 1--12. Google Scholar
Digital Library
- Manoranjan Dash and Huan Liu. 1997. Feature selection for classification. Intelligent data analysis 1, 1--4 (1997),131--156. Google Scholar
Digital Library
- Ewart J de Visser, Paul J Beatty, Justin R Estepp, Spencer Kohn, Abdulaziz Abubshait, John R Fedota, and Craig G McDonald. 2018. Learning from the slips of others: Neural correlates of trust in automated agents. Frontiers in humanneuroscience12 (2018).Google Scholar
- Jerome H Friedman. 1997. On bias, variance, 0/1-loss, and the curse-of-dimensionality. Data mining and knowledgediscovery1, 1 (1997), 55--77. Google Scholar
Digital Library
- Fernando Galdon and Stephen Jia Wang. [n.d.]. Optimising user engagement in highly automated virtual assistants to improve energy management. ([n. d.]).Google Scholar
- Eva Ganglbauer, Johann Schrammel, Stephanie Deutsch, and Manfred Tscheligi. 2009. Applying psychophysiological methods for measuring user experience: possibilities, challenges and feasibility. In Workshop on user experience evaluation methods in product development. Citeseer.Google Scholar
- Bezalel Gavish and Christopher L Tucci. 2006. Fraudulent auctions on the Internet. Electronic Commerce Research 6, 2(2006), 127--140. Google Scholar
Digital Library
- Darren Gergle and Desney S Tan. 2014. Experimental research in HCI. In Ways of Knowing in HCI. Springer, 191--227.Google Scholar
- Tricia Gibo. 2016. The "Shared Control" Committee [Society News]. IEEE Systems, Man, and Cybernetics Magazine 2, 2 (2016), 51--55.Google Scholar
Cross Ref
- Alexandre Gramfort, Martin Luessi, Eric Larson, Denis A Engemann, Daniel Strohmeier, Christian Brodbeck, Roman Goj, Mainak Jas, Teon Brooks, Lauri Parkkonen, et al. 2013. MEG and EEG data analysis with MNE-Python. Frontiers in neuroscience 7 (2013), 267.Google Scholar
- Siddharth Gulati, Sonia Sousa, and David Lamas. 2017. Modelling trust: An empirical assessment. In IFIP Conference on Human-Computer Interaction. Springer, 40--61. Google Scholar
Digital Library
- Siddharth Gulati, Sonia Sousa, and David Lamas. 2018. Modelling trust in human-like technologies. In Proceedings of the 9th Indian Conference on Human Computer Interaction. ACM, 1--10. Google Scholar
Digital Library
- Siddharth Gulati, Sonia Sousa, and David Lamas. 2019. Design, development and evaluation of a human-computer trust scale. Behaviour & Information Technology(2019), 1--12.Google Scholar
- Leanne M Hirshfield, Stuart H Hirshfield, Samuel Hincks, Matthew Russell, Rachel Ward, and Tom Williams. 2011. Trust in human-computer interactions as measured by frustration, surprise, and workload. In International Conference on Foundations of Augmented Cognition. Springer, 507--516. Google Scholar
Digital Library
- Matthew B Hoy. 2018. Alexa, siri, cortana, and more: An introduction to voice assistants. Medical reference services quarterly 37, 1 (2018), 81--88.Google Scholar
- Jeremy Hsu. 2017. When It Comes to Safety, Autonomous Cars are Still 'Teen Drivers,'. Scientific American(2017).Google Scholar
- Wan-Lin Hu, Kumar Akash, Neera Jain, and Tahira Reid. 2016. Real-time sensing of trust in human-machine interactions. IFAC-Papers OnLine 49, 32 (2016), 48--53.Google Scholar
Cross Ref
- George Hurlburt. 2017. How Much to Trust Artificial Intelligence? IT Professional 19, 4 (2017), 7--11.Google Scholar
Digital Library
- Matthew L Jensen, Paul Benjamin Lowry, Jude K Burgoon, and Jay F Nunamaker. 2010. Technology dominance in complex decision making: The case of aided credibility assessment. Journal of Management Information Systems 27, 1(2010), 175--202. Google Scholar
Digital Library
- Halimahtun Khalid, Wei Shiung Liew, Bin Sheng Voong, and Martin Helander. 2018. Creativity in Measuring Trust in Human-Robot Interaction Using Interactive Dialogs. In Congress of the International Ergonomics Association. Springer, 1175--1190.Google Scholar
- Halimahtun M Khalid, Liew Wei Shiung, Parham Nooralishahi, Zeeshan Rasool, Martin G Helander, Loo Chu Kiong,and Chin Aivyrn. 2016. Exploring psycho-physiological correlates to trust: Implications for human-robot-human interaction. In Proceedings of the human factors and ergonomics society annual meeting, Vol. 60. SAGE Publications SageCA: Los Angeles, CA, 697--701.Google Scholar
Cross Ref
- Ahmad Khawaji, Jianlong Zhou, Fang Chen, and Nadine Marcus. 2015. Using galvanic skin response (GSR) to measure trust and cognitive load in the text-chat environment. In Proceedings of the 33rd Annual ACM Conference Extended Abstracts on Human Factors in Computing Systems. ACM, 1989--1994. Google Scholar
Digital Library
- G Fine Kinney and AD Wiruth. 1976.Practical risk analysis for safety management. Technical Report. Naval Weapons Center China Lake Ca.Google Scholar
- Asle H Kiran and Peter-Paul Verbeek. 2010. Trusting our selves to technology. Knowledge, Technology & Policy 23, 3--4(2010), 409--427.Google Scholar
Cross Ref
- Kara Kockelman, Paul Avery, Prateek Bansal, Stephen D Boyles, Pavle Bujanovic, Tejas Choudhary, Lewis Clements, Gleb Domnenko, Dan Fagnant, John Helsel, et al. 2016. Implications of connected and automated vehicles on the safety and operations of roadway networks: a final report. Technical Report.Google Scholar
- Ron Kohavi and George H John. 1997. Wrappers for feature subset selection. Artificial intelligence 97, 1--2 (1997),273--324. Google Scholar
Digital Library
- Philip Koopman and Michael Wagner. 2017. Autonomous vehicle safety: An interdisciplinary challenge. IEEE Intelligent Transportation Systems Magazine 9, 1 (2017), 90--96.Google Scholar
- Miltos Kyriakidis, Riender Happee, and Joost CF de Winter. 2015. Public opinion on automated driving: Results of an international questionnaire among 5000 respondents.Transportation research part F: traffic psychology and behaviour 32 (2015), 127--140.Google Scholar
- John D Lee and Katrina A See. 2004. Trust in automation: Designing for appropriate reliance. Human factors 46, 1(2004), 50--80.Google Scholar
- Imke LJ Lemmers-Jansen, Lydia Krabbendam, Dick J Veltman, and Anne-Kathrin J Fett. 2017. Boys vs. girls: Gender differences in the neural development of trust and reciprocity depend on social context. Developmental cognitive neuroscience 25 (2017), 235--245.Google Scholar
- Tsz Him Leung. [n.d.]. Sensitivity to Risk Profiles of Users When Developing AI Systems. In Advances in Artificial Intelligence: 33rd Canadian Conference on Artificial Intelligence, Canadian AI 2020, Ottawa, ON, Canada, May 13--15, 2020, Proceedings. Springer Nature, 138.Google Scholar
- Sam Levin and Nicky Woolf. 2016. Tesla driver killed while using autopilot was watching Harry Potter, witness says. https://www.theguardian.com/technology/2016/jul/01/tesla-driver-killed-autopilot-self-driving-car-harry-potter Last accessed 16 September 2019.Google Scholar
- Mengyao Li, Brittany E Holthausen, Rachel E Stuck, and Bruce N Walker. 2019. No risk no trust: Investigating perceived risk in highly automated driving. In Proceedings of the 11th International Conference on Automotive User Interfaces and Interactive Vehicular Applications. 177--185. Google Scholar
Digital Library
- Q Vera Liao, Moninder Singh, Yunfeng Zhang, and Rachel KE Bellamy. 2020. Introduction to Explainable AI. In Extended Abstracts of the 2020 CHI Conference on Human Factors in Computing Systems. 1--4. Google Scholar
Digital Library
- Gian Luca Liehner, Philipp Brauner, Anne Kathrin Schaar, and Martina Ziefle. 2020. Development and Evaluation of a Research Framework for Measuring the Reliance on Automation in Situations of Risk and Moral Dilemma. In Digital Human Modeling and Applications in Health, Safety, Ergonomics and Risk Management. Human Communication, Organization and Work, Vincent G. Duffy (Ed.). Springer International Publishing, Cham, 280--295.Google Scholar
- Huan Liu and Hiroshi Motoda. 2012. Feature selection for knowledge discovery and data mining. Vol. 454. Springer Science & Business Media.Google Scholar
- Martin Lochner, Andreas Duenser, and Shouvojit Sarker. 2019. Trust and Cognitive Load in Semi-Automated UAV Operation. In Proceedings of the 31st Australian Conference on Human-Computer-Interaction(Fremantle, WA, Australia)(OZCHI'19). Association for Computing Machinery, New York, NY, USA, 437--441. https://doi.org/10.1145/3369457.3369509 Google Scholar
Digital Library
- Fabien Lotte, Laurent Bougrain, Andrzej Cichocki, Maureen Clerc, Marco Congedo, Alain Rakotomamonjy, and Florian Yger. 2018. A review of classification algorithms for EEG-based brain--computer interfaces: a 10 year update. Journal of neural engineering 15, 3 (2018), 031005.Google Scholar
Cross Ref
- Fabien Lotte, Marco Congedo, Anatole Lécuyer, Fabrice Lamarche, and Bruno Arnaldi. 2007. A review of classification algorithms for EEG-based brain--computer interfaces. Journal of neural engineering 4, 2 (2007), R1.Google Scholar
Cross Ref
- P Maes. 1994. Agents that Reduce Work and Information Overload, Comm.Google Scholar
- Phil McCausland. 2019. Uber self-driving car in fatal crash did not recognize that pedestrians jaywalk.https://www.euronews.com/2019/11/09/self-driving-uber-car-hit-killed-woman-did-not-recognize-n1079281 Last accessed16 September 2019.Google Scholar
- Drew M Morris, Jason M Erno, and June J Pilcher. 2017. Electrodermal response and automation trust during simulated self-driving car use. In Proceedings of the Human Factors and Ergonomics Society Annual Meeting, Vol. 61. SAGE Publications Sage CA: Los Angeles, CA, 1759--1762.Google Scholar
Cross Ref
- Yuko Nagata and Khim Hoong Chu. 2003. Optimization of a fermentation medium using neural networks and genetic algorithms. Biotechnology letters 25, 21 (2003), 1837--1842.Google Scholar
- Alan Ohnsman. 2014. Automated cars may boost fuel use, Toyota scientist says. Bloomberg. July 16 (2014).Google Scholar
- Darian M Onchis. [n.d.]. Should I trust a deep learning condition monitoring prediction? ([n. d.]).Google Scholar
- Cynthia Owsley, Beth Stalvey, Jennifer Wells, and Michael E Sloane. 1999. Older drivers and cataract: driving habits and crash risk. Journals of Gerontology Series A: Biomedical Sciences and Medical Sciences 54, 4 (1999), M203--M211.Google Scholar
Cross Ref
- Byungho Park. 2009. Psychophysiology as a tool for HCI research: promises and pitfalls. In International Conference on Human-Computer Interaction. Springer, 141--148. Google Scholar
Digital Library
- Aum Patil, Amey Wadekar, Tanishq Gupta, Rohit Vijan, and Faruk Kazi. 2019. Explainable LSTM Model for Anomaly Detection in HDFS Log File using Layerwise Relevance Propagation. In 2019 IEEE Bombay Section Signature Conference(IBSSC). IEEE, 1--6.Google Scholar
Cross Ref
- F. Pedregosa, G. Varoquaux, A. Gramfort, V. Michel, B. Thirion, O. Grisel, M. Blondel, P. Prettenhofer, R. Weiss, V.Dubourg, J. Vanderplas, A. Passos, D. Cournapeau, M. Brucher, M. Perrot, and E. Duchesnay. 2011. Scikit-learn: Machine Learning in Python. Journal of Machine Learning Research 12 (2011), 2825--2830. Google Scholar
Digital Library
- LeeAnn Perkins, Janet E Miller, Ali Hashemi, and Gary Burns. 2010. Designing for human-centered systems: Situational risk as a factor of trust in automation. In Proceedings of the human factors and ergonomics society annual meeting, Vol. 54. SAGE Publications Sage CA: Los Angeles, CA, 2130--2134.Google Scholar
Cross Ref
- Xavier Perrin, Francis Colas, Cédric Pradalier, Roland Siegwart, Ricardo Chavarriaga, and José del R Millán. 2011. Learning user habits for semi-autonomous navigation using low throughput interfaces. In 2011 IEEE International Conference on Systems, Man, and Cybernetics. IEEE, 1--6.Google Scholar
Cross Ref
- Colin Powell. 2019. 4.2 Automotive Bugs. Bits and Bugs: A Scientific and Historical Review of Software Failures in Computational Science 29 (2019), 114.Google Scholar
- Sebastian Raschka. 2018. MLxtend: Providing machine learning and data science utilities and extensions to Python's scientific computing stack. The Journal of Open Source Software 3, 24 (April 2018). https://doi.org/10.21105/joss.00638Google Scholar
Cross Ref
- René Riedl and Andrija Javor. 2012. The biology of trust: Integrating evidence from genetics, endocrinology, and functional brain imaging. Journal of Neuroscience, Psychology, and Economics 5, 2 (2012), 63.Google Scholar
Cross Ref
- Robert Rosenthal and Ralph L Rosnow. 2008. Essentials of behavioral research: Methods and data analysis.Google Scholar
- Kelly Satterfield, Carryl Baldwin, Ewart de Visser, and Tyler Shaw. 2017. The Influence of Risky Conditions in Trust in Autonomous Systems. In Proceedings of the Human Factors and Ergonomics Society Annual Meeting, Vol. 61. SAGE Publications Sage CA: Los Angeles, CA, 324--328.Google Scholar
Cross Ref
- J-B Schiratti, Jean-Eudes Le Douget, Michel Le van Quyen, Slim Essid, and Alexandre Gramfort. 2018. An ensemble learning approach to detect epileptic seizures from long intracranial EEG recordings. In2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 856--860.Google Scholar
Cross Ref
- M. Seet, J. Harvy, R. Bose, A. Dragomir, A. Bezerianos, and N. Thakor. 2020. Differential Impact of Autonomous Vehicle Malfunctions on Human Trust. IEEE Transactions on Intelligent Transportation Systems(2020), 1--10.Google Scholar
- Shervin Shahrdar, Luiza Menezes, and Mehrdad Nojoumian. 2018. A survey on trust in autonomous systems. In Science and Information Conference. Springer, 368--386.Google Scholar
- Wojciech Siedlecki and Jack Sklansky. 1993. On automatic feature selection. In Handbook of Pattern Recognition and Computer Vision. World Scientific, 63--87. Google Scholar
Digital Library
- Robert Morris Stern, William J Ray, and Karen S Quigley. 2001. Psychophysiological recording. Oxford University Press, USA.Google Scholar
Cross Ref
- Muhammad Atif Tahir, Ahmed Bouridane, and Fatih Kurugollu. 2007. Simultaneous feature selection and feature weighting using Hybrid Tabu Search/K-nearest neighbor classifier. Pattern Recognition Letters 28, 4 (2007), 438--446. Google Scholar
Digital Library
- Guido Tascini. [n.d.]. Chatbot: a Key for Understanding AI Revolution. ([n. d.]).Google Scholar
- K Thangavel and A Pethalakshmi. 2009. Dimensionality reduction based on rough set theory: A review. Applied soft computing 9, 1 (2009), 1--12. Google Scholar
Digital Library
- Xindong Wu, Vipin Kumar, J Ross Quinlan, Joydeep Ghosh, Qiang Yang, Hiroshi Motoda, Geoffrey J McLachlan, Angus Ng, Bing Liu, S Yu Philip, et al. 2008. Top 10 algorithms in data mining. Knowledge and information systems14, 1(2008), 1--37. Google Scholar
Digital Library
- Beste F Yuksel, Penny Collisson, and Mary Czerwinski. 2017. Brains or beauty: How to engender trust in user-agent interactions. ACM Transactions on Internet Technology (TOIT)17, 1 (2017), 2. Google Scholar
Digital Library
- Yunfeng Zhang, Rachel KE Bellamy, Moninder Singh, and Q Vera Liao. 2020. Introduction to AI Fairness. In Extended Abstracts of the 2020 CHI Conference on Human Factors in Computing Systems. 1--4. Google Scholar
Digital Library
Index Terms
Psychophysiological Modeling of Trust In Technology: Influence of Feature Selection Methods
Recommendations
Re-examining post-acceptance model of information systems continuance: A revised theoretical model using MASEM approach
AbstractThis study extends the post-acceptance model of information systems (IS) continuance, which is widely used to explain users’ satisfaction and IS continuance intentions. The extended model includes additional variables such as perceived ...
Highlights- This paper extends the post-acceptance model of information systems continuance.
An empirical assessment of a modified technology acceptance model
Special section: Strategic and competitive information systemsThe technology acceptance model (TAM) is one of the most influential research models in studies of the determinants of information systems/information technology (IS/IT) acceptance. In TAM, perceived usefulness and perceived ease of use are hypothesized ...






Comments