Reinforcement Sensitivity and Engagement in Proactive Recommendations: Experimental Evidence

We drew on revised Reinforcement Sensitivity Theory to claim that users with an anxiety-related behavioral inhibition would experience proactively delivered recommendations as potential threats. Such users would display higher user engagement especially when they were interrupted by inaccurate (vs. accurate) recommendations, because they ruminate about them. This prediction was tested and confirmed in a controlled experiment that exposed participants to proactive recommendations on their smartphone. Results highlight the need to gain more knowledge on the neural correlates of anxiety, and to apply such insights to human–computer interaction design for recommender systems.

[1]  Fred D. Davis,et al.  NeuroIS: The Potential of Cognitive Neuroscience for Information Systems Research , 2008, ICIS.

[2]  P. Resnick,et al.  Recommender systems — beyond matrix completion , 2016, Commun. ACM.

[3]  Heidi N. Keiser,et al.  Carver and Whites' BIS/FFFS/BAS scales and domains and facets of the Five Factor Model of personality , 2011 .

[4]  J. Gray,et al.  Précis of The neuropsychology of anxiety: An enquiry into the functions of the septo-hippocampal system , 1982, Behavioral and Brain Sciences.

[5]  Angelika Dimoka,et al.  THE POTENTIAL OF COGNITIVE NEUROSCIENCE FOR INFORMATION SYSTEMS RESEARCH , 2008 .

[6]  P. Corr,et al.  Neuroscience of Motivation and Organizational Behavior: Putting the Reinforcement Sensitivity Theory (RST) to Work , 2016 .

[7]  Eean R. Crawford,et al.  JOB ENGAGEMENT: ANTECEDENTS AND EFFECTS ON JOB PERFORMANCE , 2010 .

[8]  Soumya Ray,et al.  The Central Role of Engagement in Online Communities , 2014, Inf. Syst. Res..

[9]  Hans Ulrich Buhl.  Is the Diversification Benefit for Teams More Sustainable Than at the Financial Market? , 2010, Bus. Inf. Syst. Eng..

[10]  P. Muris,et al.  Psychometric Properties of the Dutch BIS/BAS Scales , 2005 .

[11]  Eamonn Ferguson,et al.  An evaluation of the relationship between Gray’s revised RST and Eysenck’s PEN: Distinguishing BIS and FFFS in Carver and White’s BIS/BAS scales , 2008 .

[12]  Chris J. Jackson,et al.  How the Five Factor Model and revised Reinforcement Sensitivity Theory predict divergent thinking , 2014 .

[13]  A. G. Gutiérrez-García,et al.  Anxiety: An Adaptive Emotion , 2013 .

[14]  Maarten A. S. Boksem,et al.  Cortisol involvement in mechanisms of behavioral inhibition. , 2011, Psychophysiology.

[15]  Angelika Dimoka,et al.  On the Use of Neuropyhsiological Tools in IS Research: Developing a Research Agenda for NeuroIS , 2012, MIS Q..

[16]  C. Carver,et al.  Behavioral inhibition, behavioral activation, and affective responses to impending reward and punishment: The BIS/BAS Scales , 1994 .

[17]  René Riedl,et al.  Technostress from a Neurobiological Perspective , 2012, Business & Information Systems Engineering.

[18]  Bracha Shapira,et al.  Recommender Systems Handbook , 2015, Springer US.

[19]  Angelika Dimoka,et al.  What Does the Brain Tell Us About Trust and Distrust? Evidence from a Functional Neuroimaging Study , 2010, MIS Q..

[20]  Angelika Dimoka,et al.  Research Commentary - NeuroIS: The Potential of Cognitive Neuroscience for Information Systems Research , 2011, Inf. Syst. Res..

[21]  C. Rusbult,et al.  IMPACT OF EXCHANGE VARIABLES ON EXIT, VOICE, LOYALTY, AND NEGLECT: AN INTEGRATIVE MODEL OF RESPONSES TO DECLINING JOB STATUS SATISFACTION. , 1988 .

[22]  P. Corr.  Anxiety: Splitting the phenomenological atom , 2011 .

[23]  A. Auinger,et al.  Technostress from a Neurobiological Perspective : System Breakdown Increases the Stress Hormone Cortisol in Computer Users , 2012 .

[24]  Sean M. McNee,et al.  Being accurate is not enough: how accuracy metrics have hurt recommender systems , 2006, CHI Extended Abstracts.