scispace - formally typeset
Search or ask a question
Proceedings ArticleDOI

"Oh dear stacy!": social interaction, elaboration, and learning with teachable agents

TL;DR: Treating her as a partner, primarily through aligning oneself with Stacy using pronouns like you or the authors rather than she or it significantly correlates with student learning, as do playful face-threatening comments such as teasing, while elaborate explanations of Stacy's behavior in the third-person and formal tutoring statements reduce learning gains.
Abstract: Understanding how children perceive and interact with teachable agents (systems where children learn through teaching a synthetic character embedded in an intelligent tutoring system) can provide insight into the effects of so-cial interaction on learning with intelligent tutoring systems. We describe results from a think-aloud study where children were instructed to narrate their experience teaching Stacy, an agent who can learn to solve linear equations with the student's help. We found treating her as a partner, primarily through aligning oneself with Stacy using pronouns like you or we rather than she or it significantly correlates with student learning, as do playful face-threatening comments such as teasing, while elaborate explanations of Stacy's behavior in the third-person and formal tutoring statements reduce learning gains. Additionally, we found that the agent's mistakes were a significant predictor for students shifting away from alignment with the agent.

Content maybe subject to copyright    Report

Citations
More filters
Proceedings ArticleDOI
Jessy Ceha1, Ken Jen Lee1, Elizabeth S. Nilsen1, Joslin Goh1, Edith Law1 
06 May 2021
TL;DR: This article examined the effects of a conversational agent's use of affiliative and self-defeating humour on learners' perception of the agent and attitudes towards the task using a between-subjects protocol.
Abstract: Previous studies have highlighted the benefits of pedagogical conversational agents using socially-oriented conversation with students. In this work, we examine the effects of a conversational agent’s use of affiliative and self-defeating humour — considered conducive to social well-being and enhancing interpersonal relationships — on learners’ perception of the agent and attitudes towards the task. Using a between-subjects protocol, 58 participants taught a conversational agent about rock classification using a learning-by-teaching platform, the Curiosity Notebook. While all agents were curious and enthusiastic, the style of humour was manipulated such that the agent either expressed an affiliative style, a self-defeating style, or no humour. Results demonstrate that affiliative humour can significantly increase motivation and effort, while self-defeating humour, although enhancing effort, negatively impacts enjoyment. Findings further highlight the importance of understanding learner characteristics when using humour.

14 citations

Journal Article
TL;DR: This paper aims to propose a Motivated Teachable Agent (MTA) which incorporates intrinsic motivation to agent modeling and synthesizes various behaviors of TAs into a full play.
Abstract: Introduction Thousands of years ago philosopher Lucius Seneca stated, "We learn by teaching". This idea, nowadays, evolved to a modern educational theory called "Learning-by-Teaching". It has been widely observed that when students teach their peers they learn much better than they learn for themselves (Allen & Feldman, 1976; Gartner, 1971), since they no longer passively receive knowledge from teachers but perform as a young tutor to actively master the learning content. In light of this theory, a new type of pedagogical agent, Teachable Agent (TA), emerged in 1990s. Teachable agents are computer agents that allow students to teach them and in this way to improve the learning of students per se (Biswas, et al., 2005). Many researchers worked on designing TAs in their virtual learning environments (Ailiya, et al., 2011; Chou, et al., 2003; Kauchak & Eggen, 1997; Leelawong & Biswas, 2008; Matsuda, et al., 2010; Obayashi, et al., 2000). Three advantages of TAs include that TAs can increase student's knowledge reflection and self-explanation (Roscoe & Chi, 2007), help them structure and reorganize their knowledge (Fantuzzo, et al., 1992), and promote students to take the responsibility of learning. However, the limitation of existing TAs lies in the fact that they do not take the initiative in the interactions with students. The interaction between TAs and students is important for facilitating a better learning, so a TA should be more active and should avoid responding to students passively (Biswas, et al., 2005; Ogan et al., 2012). To overcome the limitation, we look into the field of computer agents. One of the focuses is to embody autonomous behaviors in the agent systems. In particular, the agent autonomy refers to allowing agents to decide whether or not to perform a certain action by themselves. Motivated by the concept of "intrinsic motivation" from psychology, agent researchers from Intrinsically Motivated Agent (IMA) consider an agent as intrinsically motivated when its behavior is engaged in "for its own sake", other than driven by a specific "externally-directed" problem (Singh, et al., 2005). If a TA could have intrinsic motivation, the autonomous behaviors of the agent can be derived based on its own interest, and a diversity of agent abilities can be naturally presented under a unified sense of "self- willing". Motivated by this, this paper aims to propose a Motivated Teachable Agent (MTA) which incorporates intrinsic motivation to agent modeling and synthesizes various behaviors of TAs into a full play. However, readers may have a question: what does it mean by an agent's initiative? Several researchers discussed their opinions: (1) (Singh, et al., 2010), from an evolutionary perspective, considered "reproductive success" as the drive for agents to behave proactively; (2) (Baranes & Oudeyer, 2009) designed robots to pursue activities for which "learning progress is maximal"; (3) (Merrick, 2010) considered agent's self-motivated exploration as seeking for "novelty, interest, and competence". However, none of them is designed for educational purpose, and the agent initiative lacks an educational value. Thus, we need to define an agent model by which agent's initiatives can be directly related to the educational requirements of a TA. The ultimate goal of designing TAs is to facilitate student's learning and stimulate their learning interest. In this paper, we argue that TAs should satisfy the three fundamental educational requirements of Learning-by-Teaching. First, a TA should have the ability to learn new knowledge from students in order to encourage them to reflect the learning materials. Second, a TA should have the ability to apply the learnt knowledge, and provide feedbacks to students in order to give them an opportunity to validate and rethink their teaching. Third, a TA should have the ability to establish good relationship with students and encourage them to teach well in order to promote students to take the responsibility of learning. …

13 citations

Journal ArticleDOI
TL;DR: The analyses suggest that two of the gaze behaviors were positively correlated with the game performance measure, as hypothesized, and can be interpreted as an indication that the children had an understanding of their teachable agent as an entity that made decisions based on own ‘knowledge’.
Abstract: This study investigated how preschool children processed and understood critical information in Magical Garden, a teachable agent-based play-&-learn game targeting early math. We analyzed 36 children’s (ages 4–6 years) real-time behavior during game-use to explore whether children: (i) processed the information meant to support number sense development; (ii) showed an understanding of the teachable agent as an entity with agency. An important methodological goal was to go beyond observable behavior and shed some light on how cognitive processing and understanding in children of such young age can be studied. First, the children played Magical Garden for three weeks to get acquainted with the game. Second, in an experimental part of the study, the children’s gaze behaviors were measured during 5 rounds of interaction with an experimental version of one of the sub-games. The analyses suggest that two of the gaze behaviors were positively correlated with the game performance measure, as hypothesized. Another result was that children looked at the teachable agent significantly more often when the teachable agent had been in charge of gameplay than when it had not. This can be interpreted as an indication that the children had an understanding of their teachable agent as an entity that, like themselves and unlike other dynamic visual elements in the game, made decisions based on own ‘knowledge’. In a broader context, the findings are important in showing the potential gains of combining log data with eye-tracking data for developing and refining AI algorithms for adaptive individual feedback and scaffolding.

10 citations

01 Jan 2017
TL;DR: This paper aims to provide a chronology of the events leading up to and including the publication of this book and some of the key events that led to its publication.
Abstract: ................................................................................................................................................... iii Acknowledgements .............................................................................................................................. iv

10 citations


Cites background or methods from ""Oh dear stacy!": social interactio..."

  • ...Ogan et al. (2012a) analyzed data on a similar time scale as my study where they looked at the change in behaviors between two sessions....

    [...]

  • ...Additionally, most ITS systems do not support the combination of individual and collaborative learning, despite this being common in the classroom (Ogan et al., 2012)....

    [...]

  • ...However, students within a class do not always use them individually and communicate with peers when they need help (Ogan et al., 2012)....

    [...]

Proceedings Article
01 Jan 2014
TL;DR: This work conducted a study involving students interacting with a social robot that made attributions to ability and effort, and to the student, itself, or both, to understand how different attributions influence student perceptions.
Abstract: Teachable agents foster student learning by employing the learning by teaching paradigm. Since social factors influence learning from this paradigm, understanding which social behaviors a teachable agent should embody is an important first step for designing such an agent. Here, we focus on the impact of causal attributions made by a teachable agent. To obtain data on student perceptions of agent attributions, we conducted a study involving students interacting with a social robot that made attributions to ability and effort, and to the student, itself, or both. We analyzed data from semi-structured interviews to understand how different attributions influence student perceptions, and discuss design opportunities for manipulating these attributions to improve student motivation.

8 citations


Cites background from ""Oh dear stacy!": social interactio..."

  • ...Others have begun to explore how conversational strategies such as teasing between human peers (Ogan et al., 2012b) and human-agent peers (Ogan et al., 2012a) impacts rapport with the human learner....

    [...]

  • ...Prior work with students in peer-to-peer interactions showed face threatening moves of this type were in some cases associated with learning (Ogan et al., 2012b), and in fact we did find that some students had a positive reaction, even saying that the message made them want to teach more....

    [...]

  • ...Since prior work indicated that when peers are friends certain social behaviors are associated with learning (Ogan et al., 2012b), students were asked to pretend that Quinn was a long-time friend; following the teachable agent paradigm, they were also told that it is Quinn who gets the answer…...

    [...]

References
More filters
Journal ArticleDOI
Jacob Cohen1
TL;DR: In this article, the authors present a procedure for having two or more judges independently categorize a sample of units and determine the degree, significance, and significance of the units. But they do not discuss the extent to which these judgments are reproducible, i.e., reliable.
Abstract: CONSIDER Table 1. It represents in its formal characteristics a situation which arises in the clinical-social-personality areas of psychology, where it frequently occurs that the only useful level of measurement obtainable is nominal scaling (Stevens, 1951, pp. 2526), i.e. placement in a set of k unordered categories. Because the categorizing of the units is a consequence of some complex judgment process performed by a &dquo;two-legged meter&dquo; (Stevens, 1958), it becomes important to determine the extent to which these judgments are reproducible, i.e., reliable. The procedure which suggests itself is that of having two (or more) judges independently categorize a sample of units and determine the degree, significance, and

34,965 citations


""Oh dear stacy!": social interactio..." refers methods in this paper

  • ...Reliability is given for each coding category below in a Cohen’s K [8]....

    [...]

01 Jan 1987
TL;DR: Gumperz as discussed by the authors discusses politeness strategies in language and their implications for language studies, including sociological implications and implications for social sciences. But he does not discuss the relationship between politeness and language.
Abstract: Symbols and abbreviations Foreword John J. Gumperz Introduction to the reissue Notes 1. Introduction 2. Summarized argument 3. The argument: intuitive bases and derivative definitions 4. On the nature of the model 5. Realizations of politeness strategies in language 6. Derivative hypotheses 7. Sociological implications 8. Implications for language studies 9. Conclusions Notes References Author index Subject index.

9,542 citations

Book
01 Jan 1987
TL;DR: This paper presents an argument about the nature of the model and its implications for language studies and Sociological implications and discusses the role of politeness strategies in language.
Abstract: This study is about the principles for constructing polite speeches. The core of it first appeared in Questions and Politeness, edited by Esther N. Goody (now out of print). It is here reissued with a fresh introduction that surveys the considerable literature in linguistics, psychology and the social sciences that the original extended essay stimulated, and suggests distinct directions for research. The authors describe and account for some remarkable parallelisms in the linguistic construction of utterances with which people express themselves in different languages and cultures. A motive for these parallels is isolated and a universal model is constructed outlining the abstract principles underlying polite usages. This is based on the detailed study of three unrelated languages and cultures: the Tamil of South India, the Tzeltal spoken by Mayan Indians in Chiapas, Mexico, and the English of the USA and England. This volume will be of special interest to students in linguistic pragmatics, sociolinguistics, applied linguistics, anthropology, and the sociology and social psychology of interaction.

9,053 citations


""Oh dear stacy!": social interactio..." refers background in this paper

  • ...face-threatening, by which is meant dialogue moves that threaten the other person’s identity management, or positive sense of him or herself [4]....

    [...]

Book
01 Jan 1996
TL;DR: This chapter discusses the media equation, which describes the role media and personality play in the development of a person's identity and aims at clarifying these roles.
Abstract: Part I. Introduction: 1. The media equation Part II. Media and Manners: 2. Politeness 3. Interpersonal distance 4. Flattery 5. Judging others and ourselves Part III. Media and Personality: 6. Personality of characters 7. Personality of interfaces 8. Imitating a personality Part IV. Media and emotion: 9. Good versus bad 10. Negativity 11. Arousal Part V. Media and Social Roles: 12. Specialists 13. Teammates 14. Gender 15. Voices 16. Source orientation Part VI. Media and Form: 17. Image size 18. Fidelity 19. Synchrony 20. Motion 21. Scene changes 22. Subliminal images Part VII. Final Words: 23. Conclusions about the media equation References.

4,690 citations


""Oh dear stacy!": social interactio..." refers background in this paper

  • ...Students who made many formal tutoring moves and few social moves often used outside-aligned speech to discuss what Stacy did and did not know, which we hypothesize is because it would be face-threatening to discuss her incompetencies with her in detail, along the lines described by Reeves and Nass [16]....

    [...]

  • ...HYPOTHESES Cognitive hypotheses of learning by teaching suggest that tutors will engage in more mental organization of the material and perform more self-explanation as they tutor, leading to learning gains [10,11,16,20,25]....

    [...]

  • ...Given conflicting prior work on whether social relationships can be formed with virtual agents [5,16,17,18] we chose to look at the type of language students used when referring to the agent as a clue to their social stance....

    [...]

Journal ArticleDOI
TL;DR: Cooperative learning is one of the greatest success stories in the history of educational research as discussed by the authors, and the most frequent objective of this research is to determine the effects of cooperative learning on student achievement.

1,563 citations


""Oh dear stacy!": social interactio..." refers background in this paper

  • ...For example, researchers have proposed that there are substantial social aspects of peer tutoring that are responsible for evoking tutor learning effects, such as a strong feeling of accountability for ensuring the tutee is learning the proper information [24], as well as a desire to avoid the face-threat of not being able to fully respond to tutee questions [28]....

    [...]