Your Mouse Knows When You Are Mad

Websites May Soon Know If You’re Mad—a Little Mouse Will Tell Them

Cursor speed and precision link to anger and other negative emotions.

Beth Mole | December 15, 2015

[...]Perturbed users also tended to navigate their mouse more slowly, not faster as some might expect. The findings, reported in the information systems journal MIS Quarterly, may allow computer scientists or website developers to identify and intervene in real time when users become agitated with the interface or content of a site.
"Using this technology, websites will no longer be dumb," Jeff Jenkins, lead study author and an information systems professor at Brigham Young University, said in a press release. [...]

<more at http://arstechnica.com/science/2015/12/websites-may-soon-know-if-youre-mad-a-little-mouse-will-tell-them/; related links: http://techcrunch.com/2015/12/16/your-mouse-knows-when-youre-mad/ (Your Mouse Knows When You’re Mad. December 16, 2015) and http://www.misq.org/skin/frontend/default/misq/pdf/Abstracts/11979_RN_HibbelnAbstract.pdf (Inferring Negative Emotion from Mouse Cursor Movements.Martin Hibbeln, Jeffrey L. Jenkins, Christoph Schneider, Joseph S. Valacich, and Markus Weinmann. MIS Quarterly. 01/2015. [Abstract: Experiencing negative emotion during system use can adversely influence important user behaviors, including purchasing decisions, technology use, and customer loyalty. The ability to easily assess users’ negative emotions during live system use, therefore, has practical significance for the design and improvement of information systems. We utilize attentional control theory to explain how mouse cursor movements can be a real-time indicator of negative emotion. We report three studies. In Study 1, an experiment with 65 participants from Amazon’s Mechanical Turk, we randomly manipulated negative emotion and then monitored participants’ mouse cursor movements as they completed a number-ordering task. We found that negative emotion increases the distance and reduces the speed of mouse cursor movements during the task. In Study 2, an experiment with 126 participants from a U.S. university, we randomly manipulated negative emotion and then monitored participants’ mouse cursor movements while they interacted with a mock e-commerce site. We found that mouse cursor distance and speed can be used to infer the presence of negative emotion with an overall accuracy rate of 81.7 percent. In Study 3, an observational study with 80 participants from universities in Germany and Hong Kong, we monitored mouse cursor movements while participants interacted with an online product configurator. Participants reported their level of emotion after each step in the configuration process. We found that mouse cursor
distance and speed can be used to infer the level of negative emotion with an out-of-sample R2  of 0.17. The results enable researchers to assess negative emotional reactions during live system use, examine emotional reactions with more temporal precision, conduct multimethod emotion research, and create more unobtrusive affective and adaptive systems.])>