Table 1 Common measures for determining cognitive and affective outcomes in robots for learning.
CognitiveLearning gain, measured as difference between pre- and posttest score
Administer posttest either immediately after exposure to robot or with delay
Correct for varying initial knowledge, e.g., using normalized learning gain (77)
Difference in completion time of test
Number of attempts needed for correct response
AffectivePersistence, measured as number of attempts made or time spent with robot
Number of interactions with the system, such as utterances or responses
Coding emotional expressions of the learner, can be automated using face analysis software (47)
Godspeed questionnaire, measuring the user’s perception of robots (78)
Tripod survey, measuring the learner’s perspective on teaching, environment, and engagement (79)
Immediacy, measuring psychological availability of the robot teacher (3, 10)
Evolution of time between answers, e.g., to indicate fatigue (31)
Coding of video recordings of participants responses
Coding or automated recording of eye gaze behavior (to code attention, for example)
Subjective rating of the robot’s teaching and the learning experience (15)
Foreign language anxiety questionnaire (80)
KindSAR interactivity index, quantitative measure of children’s interactions with a robot (81)
Basic empathy scale, self-report of empathy (82)
Free-form feedback or interviews