Addressing student behavior and affect with empathy and growth mindset

Shamya Karumbaiah, Rafael Lizarralde, Danielle Allessio, Beverly Woolf, Ivon Arroyo, Naomi Wixon, Winslow Burleson

Research output: Contribution to conferencePaperpeer-review


We present results of a randomized controlled study that compared different types of affective messages delivered by pedagogical agents. We used animated characters that were empathic and emphasized the malleability of intelligence and the importance of effort. Results showed significant correlations between students who received more empathic messages and those who were more confident, more patient, exhibited higher levels of interest, and valued math knowledge more. Students who received more growth mindset messages, tended to get more problems correct on their first attempt but valued math knowledge less and had lower posttest scores. Students who received more success/failure messages tended to make more mistakes, to be less learning-oriented, and stated that they were more confused. We conclude that these affective messages are powerful media to influence students’ perceptions of themselves as learners, as well as their perceptions of the domain being taught. We have reported significant results that support the use of empathy to improve student affect and attitudes in a math tutor.

Original languageEnglish (US)
Number of pages8
StatePublished - Jan 1 2017
Event10th International Conference on Educational Data Mining, EDM 2017 - Wuhan, China
Duration: Jun 25 2017Jun 28 2017


Conference10th International Conference on Educational Data Mining, EDM 2017


  • Confidence
  • Empathy messages
  • Growth mindset
  • Intelligent tutor
  • Pedagogical agents
  • Student affect

ASJC Scopus subject areas

  • Computer Science Applications
  • Information Systems


Dive into the research topics of 'Addressing student behavior and affect with empathy and growth mindset'. Together they form a unique fingerprint.

Cite this