Limits...
Why Robots Should Be Social: Enhancing Machine Learning through Social Human-Robot Interaction.

de Greeff J, Belpaeme T - PLoS ONE (2015)

Bottom Line: We observe that conveying a learning preference through the use of social cues results in better and faster learning by the robot.In addition, the social learning shows a clear gender effect with female participants being responsive to the robot's bids, while male teachers appear to be less receptive.This work shows how additional social cues in social machine learning can result in people offering better quality learning input to artificial systems, resulting in improved learning performance.

View Article: PubMed Central - PubMed

Affiliation: Centre for Robotics and Neural Systems, Plymouth University, Plymouth, United Kingdom; Interactive Intelligence Group, Delft University of Technology, Delft, the Netherlands.

ABSTRACT
Social learning is a powerful method for cultural propagation of knowledge and skills relying on a complex interplay of learning strategies, social ecology and the human propensity for both learning and tutoring. Social learning has the potential to be an equally potent learning strategy for artificial systems and robots in specific. However, given the complexity and unstructured nature of social learning, implementing social machine learning proves to be a challenging problem. We study one particular aspect of social machine learning: that of offering social cues during the learning interaction. Specifically, we study whether people are sensitive to social cues offered by a learning robot, in a similar way to children's social bids for tutoring. We use a child-like social robot and a task in which the robot has to learn the meaning of words. For this a simple turn-based interaction is used, based on language games. Two conditions are tested: one in which the robot uses social means to invite a human teacher to provide information based on what the robot requires to fill gaps in its knowledge (i.e. expression of a learning preference); the other in which the robot does not provide social cues to communicate a learning preference. We observe that conveying a learning preference through the use of social cues results in better and faster learning by the robot. People also seem to form a "mental model" of the robot, tailoring the tutoring to the robot's performance as opposed to using simply random teaching. In addition, the social learning shows a clear gender effect with female participants being responsive to the robot's bids, while male teachers appear to be less receptive. This work shows how additional social cues in social machine learning can result in people offering better quality learning input to artificial systems, resulting in improved learning performance.

No MeSH data available.


Q2: Participants’ rating of robot behaviour in terms of naturalness.Error bars indicate 95% confidence interval.
© Copyright Policy
Related In: Results  -  Collection

License
getmorefigures.php?uid=PMC4589374&req=5

pone.0138061.g009: Q2: Participants’ rating of robot behaviour in terms of naturalness.Error bars indicate 95% confidence interval.

Mentions: The questionnaire revealed some interactions between participants gender and the social-non social condition. For the question “How do you rate the robot’s behaviour?” (Q2), with a 7-point Likert scale ranging from ‘not natural at all’ to ‘very natural’, average ratings between the social and non-social condition hardly differ. However, when split into gender, a significant interaction between participants gender and the social condition can be observed (Fig 9). This is confirmed by an ANOVA with F(1, 34) = 8.4974, p = 0.006. The use of ANOVA to analyse Likert scale responses is appropriate here, as we use a 7-point Likert scale and sum at least 8 responses, thereby approaching normality and not requiring a non-parametric test [63]. No main effects were found, but an interaction exist: female participants find the robot’s behaviour in the social condition more natural than male participants, while it is the reverse in the non-social condition. A two sample t-test showed a significant difference in mean robot rating for female participants depending on the social condition, with t(17.664) = -2.5734, p = 0.0193, while this was not found for male participants (t(14.972) = 1.6912, p = 0.1115).


Why Robots Should Be Social: Enhancing Machine Learning through Social Human-Robot Interaction.

de Greeff J, Belpaeme T - PLoS ONE (2015)

Q2: Participants’ rating of robot behaviour in terms of naturalness.Error bars indicate 95% confidence interval.
© Copyright Policy
Related In: Results  -  Collection

License
Show All Figures
getmorefigures.php?uid=PMC4589374&req=5

pone.0138061.g009: Q2: Participants’ rating of robot behaviour in terms of naturalness.Error bars indicate 95% confidence interval.
Mentions: The questionnaire revealed some interactions between participants gender and the social-non social condition. For the question “How do you rate the robot’s behaviour?” (Q2), with a 7-point Likert scale ranging from ‘not natural at all’ to ‘very natural’, average ratings between the social and non-social condition hardly differ. However, when split into gender, a significant interaction between participants gender and the social condition can be observed (Fig 9). This is confirmed by an ANOVA with F(1, 34) = 8.4974, p = 0.006. The use of ANOVA to analyse Likert scale responses is appropriate here, as we use a 7-point Likert scale and sum at least 8 responses, thereby approaching normality and not requiring a non-parametric test [63]. No main effects were found, but an interaction exist: female participants find the robot’s behaviour in the social condition more natural than male participants, while it is the reverse in the non-social condition. A two sample t-test showed a significant difference in mean robot rating for female participants depending on the social condition, with t(17.664) = -2.5734, p = 0.0193, while this was not found for male participants (t(14.972) = 1.6912, p = 0.1115).

Bottom Line: We observe that conveying a learning preference through the use of social cues results in better and faster learning by the robot.In addition, the social learning shows a clear gender effect with female participants being responsive to the robot's bids, while male teachers appear to be less receptive.This work shows how additional social cues in social machine learning can result in people offering better quality learning input to artificial systems, resulting in improved learning performance.

View Article: PubMed Central - PubMed

Affiliation: Centre for Robotics and Neural Systems, Plymouth University, Plymouth, United Kingdom; Interactive Intelligence Group, Delft University of Technology, Delft, the Netherlands.

ABSTRACT
Social learning is a powerful method for cultural propagation of knowledge and skills relying on a complex interplay of learning strategies, social ecology and the human propensity for both learning and tutoring. Social learning has the potential to be an equally potent learning strategy for artificial systems and robots in specific. However, given the complexity and unstructured nature of social learning, implementing social machine learning proves to be a challenging problem. We study one particular aspect of social machine learning: that of offering social cues during the learning interaction. Specifically, we study whether people are sensitive to social cues offered by a learning robot, in a similar way to children's social bids for tutoring. We use a child-like social robot and a task in which the robot has to learn the meaning of words. For this a simple turn-based interaction is used, based on language games. Two conditions are tested: one in which the robot uses social means to invite a human teacher to provide information based on what the robot requires to fill gaps in its knowledge (i.e. expression of a learning preference); the other in which the robot does not provide social cues to communicate a learning preference. We observe that conveying a learning preference through the use of social cues results in better and faster learning by the robot. People also seem to form a "mental model" of the robot, tailoring the tutoring to the robot's performance as opposed to using simply random teaching. In addition, the social learning shows a clear gender effect with female participants being responsive to the robot's bids, while male teachers appear to be less receptive. This work shows how additional social cues in social machine learning can result in people offering better quality learning input to artificial systems, resulting in improved learning performance.

No MeSH data available.