Electronic Mentors
Atkinson, R. K. (2002). Optimizing learning from examples using animated pedagogical agents. Journal of Educational Psychology, 94(2), 416-427.
This study compared the effectiveness of an animated pedagogical agent delivering instructional explanations in different media. College students solved word problems with the assistance of an animated agent providing instructional explanations as onscreen text or speech. Student performance was significantly better with oral explanations.
Atkinson, R. K., Mayer, R. E., & Merrill, M. M. (2005). Fostering social agency in multimedia learning: Examining the impact of an animated agent’s voice. Contemporary Educational Psychology, 30(1), 117-139.
Consistent with social agency theory, we hypothesized that learners who studied a set of worked-out examples involving proportional reasoning narrated by an animated agent with a human voice would perform better on near and far transfer tests and rate the speaker more positively compared to learners who studied the same set of examples narrated by an agent with a machine synthesized voice. This hypothesis was supported across two experiments, including one conducted in a high school computer classroom. Overall, the results are consistent with social agency theory that posits that social cues in multimedia messages, including the type of voice, can affect how much students like the speaker and how hard students try to understand the presented material. [Copyright 2005 Elsevier]; Copyright of Contemporary Educational Psychology is the property of Academic Press Inc. and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract.
Biswas, G., Leelawong, K., Schwartz, D., Vye, N., & The Teachable Agents Group at Vanderbilt. (2005). Learning by teaching: A new agent paradigm for educational software. Applied Artificial Intelligence, 19, 363-392.
This paper discusses Betty's Brain, a teachable agent in the domain of river ecosystems that combines learning by teaching with self-regulation mentoring to promote deep learning and understanding. Two studies demonstrate the effectiveness of this system. The first study focused on components that define student-teacher interactions in the learning by teaching task. The second study examined the value of adding meta-cognitive strategies that governed Betty's behavior and self-regulation hints provided by a mentor agent. The study compared three versions: a system where the student was tutored by a pedagogical agent, a learning by teaching system, where students taught a baseline version of Betty, and received tutoring help from the mentor, and a learning by teaching system, where Betty was enhanced to include self-regulation strategies, and the mentor provided help on domain material on how to become better learners and better teachers. Results indicate that the addition of the self-regulated Betty and the self-regulation mentor better prepared students to learn new concepts later, even when they no longer had access to the SRL environment.
Craig, S. D., Gholson, B., & Driscoll, D. M. (2002). Animated pedagogical agents in multimedia educational environments: Effects of agent properties, picture features, and redundancy. Journal of Educational Psychology, 94(2), 428-434.
Presents a study on the integration of animated agents into multimedia educational environments. Discussions concerning the modality and contiguity principles of multimedia theory; Effects of agent properties on multimedia environment; Efficacy of animation conditions in facilitating performance relative to the static-picture condition.
Craig, S. D., Graesser, A. C., Sullins, J., & Gholson, B. (2004). Affect and learning: An exploratory look into the role of affect in learning with AutoTutor. Journal of Educational Media, 29(3), 241-250.
The role that affective states play in learning was investigated from the perspective of a constructivist learning framework. We observed six different affect states (frustration, boredom, flow, confusion, eureka and neutral) that potentially occur during the process of learning introductory computer literacy with AutoTutor, an intelligent tutoring system with tutorial dialogue in natural language. Observational analyses revealed significant relationships between learning and the affective states of boredom, flow and confusion. The positive correlation between confusion and learning is consistent with a model that assumes that cognitive disequilibrium is one precursor to deep learning. The findings that learning correlates negatively with boredom and positively with flow are consistent with predictions from Csikszentmihalyi's analysis of flow experiences.
Creed, C., & Beale, R. (2007). Psychological responses to simulated displays of mismatched emotional expressions. Interacting with Computers, 20(2), 225-239.
Embodied agents are often designed with the ability to simulate human emotion. This paper investigates the psychological impact of simulated emotional expressions on computer users with a particular emphasis on how mismatched facial and audio expressions are perceived (e.g. a happy face with a concerned voice). In a within-subjects repeated measures experiment (N=68), mismatched animations were perceived as more engaging, warm, concerned and happy when a happy or warm face was in the animation (as opposed to a neutral or concerned face) and when a happy or warm voice was in the animation (as opposed to a neutral or concerned voice). The results appear to follow cognitive dissonance theory as subjects attempted to make mismatched expressions consistent on both the visual and audio dimensions of animations, resulting in confused perceptions of the emotional expressions. Design implications for affective embodied agents are discussed and future research areas identified.
Dunsworth, Q., & Atkinson, R. K. (2007). Fostering multimedia learning of science: Exploring the role of an animated agent’s image. Computers & Education, 49(3), 677-690.
Research suggests that students learn better when studying a picture coupled with narration rather than on-screen text in a computer-based multimedia learning environment. Moreover, combining narration with the visual presence of an animated pedagogical agent may also encourage students to process information deeper than narration or on-screen text alone. The current study was designed to evaluate three effects among students learning about the human cardiovascular system: the modality effect (narration vs. on-screen text), the embodied agent effect (narration+agent vs. on-screen text), and the image effect (narration+agent vs. narration). The results of this study document large and significant embodied agent and image effects on the posttest (particularly retention items) but surprisingly no modality effect was found. Overall, the results suggest that incorporating an animated pedagogical agent—programmed to coordinate narration with gaze and pointing—into a science-focused multimedia learning environment can foster learning.
Graesser, A. C., McNamara, D. S., & VanLehn, K. (2005). Scaffolding deep comprehension strategies through Point&Query, AutoTutor, and iSTART. Educational Psychologist, 40(4), 225-234.
It is well-documented that most students do not have adequate proficiencies in inquiry and metacognition, particularly at deeper levels of comprehension that require explanatory reasoning. The proficiencies are not routinely provided by teachers and normal tutors so it is worthwhile to turn to computer-based learning environments. This article describes some of our recent computer systems that were designed to facilitate explanation-centered learning through strategies of inquiry and metacognition while students learn science and technology content. Point&Query augments hypertext, hypermedia, and other learning environments with question-answer facilities that are under the learner control. AutoTutor and iSTART use animated conversational agents to scaffold strategies of inquiry, metacognition, and explanation construction. AutoTutor coaches students in generating answers to questions that require explanations (e.g., why, what-if, how) by holding a mixed-initiative dialogue in natural language. iSTART models and coaches students in constructing self-explanations and in applying other metacomprehension strategies while reading text. These systems have shown promising results in tests of learning gains and learning strategies.
Kim, Y., & Baylor, A. L. (2006). A social-cognitive framework for pedagogical agents as learning companions. Educational Technology Research and Development, 54(6), 569-596.
Teaching and learning are highly social activities. Seminal psychologists such as Vygotsky, Piaget, and Bandura have theorized that social interaction is a key mechanism in the process of learning and development. In particular, the benefits of peer interaction for learning and motivation in classrooms have been broadly demonstrated through empirical studies. Hence, it would be valuable if computer-based environments could support a mechanism for a peer interaction. Though no claim of peer equivalence is made, pedagogical agents as learning companions (PALs)—animated digital characters functioning to simulate human-peer-like interaction—might provide an opportunity to simulate such social interaction in computer-based learning. In this article we ground the instructional potential of PALs in several social-cognitive theories, including distributed cognition, social interaction, and Bandura’s social-cognitive theory. We discuss how specific concepts of the theories might support various instructional functions of PALs, acknowledging concepts that PALs cannot address. Based on the theoretical perspectives, we suggest key constituents for designing PALs that in human-peer interactions have proven significant. Finally, we review the current status of PAL research with respect to these constituents and suggest where further empirical research is necessary.
Lusk, M. M., & Atkinson, R. K. (2007). Animated pedagogical agents: Does their degree of embodiment impact learning from static or animated worked examples? Applied Cognitive Psychology, 21(6), 747-764.
This study examined the impact of varying an animated pedagogical agent's level of embodiment in a learning environment consisting of static or animated multimodal worked examples illustrating how to solve multi-step proportional word problems. In the fully embodied condition, the agent was programmed to coordinate spoken instructional explanations with non-verbal forms of communication (locomotion, gesture, and gaze) to support learning. In the minimally embodied condition, the same agent provided the spoken instructions but remained static on the screen. In the voice-only condition, the spoken instructions were provided without an agent. Of the 174 college-age participants, those provided with the fully embodied agent produced more conceptually accurate answers to near and far transfer items than their counterparts in the voice-only condition. Moreover, participants that studied animated worked examples, where the problem's sub-goals were presented sequentially over time, outperformed their peers provided with static examples with simultaneously-presented sub-goals on measures of transfer.
Moreno, R., & Flowerday, T. (2006). Students’ choice of animated pedagogical agents in science learning: A test of the similarity-attraction hypothesis on gender and ethnicity. Contemporary Educational Psychology, 31(2), 186-207.
College students learned about science with a multimedia program. One group (choice or C) chose to learn with or without an animated pedagogical agent (APA) representing a male or female of five different ethnicities. Another group (no-choice or NC) was assigned an APA by the system. All participants in C group chose to learn with APAs and students of color chose significantly more same-ethnicity APAs than White American students. A significant interaction between choice and ethnic similarity factors revealed that group C produced lower retention, transfer, and program ratings when learning with same-ethnicity rather than different-ethnicity APAs. Results support an interference hypothesis for students who choose to learn with same-ethnicity APAs.
Moreno, R., Mayer, R. E., Spires, H. A., & Lester, J. C. (2001). The case for social agency in computer-based teaching: Do students learn more deeply when they interact with animated pedagogical agents? Cognition and Instruction, 19(2), 177.
In two sets of experiments, college students and grade 7 students engaged in a computer-based multimedia lesson in plant biology with or without the assistance of an animated pedagogical agent who provided verbal advice and encouraging comments. Students working with an agent significantly outperformed peers working without one on problem-solving, and rated the program as significantly more interesting.
Prendinger, H., Ma, C., & Ishizuka, M. (2007). Eye movements as indices for the utility of life-like interface agents: A pilot study. Interacting with Computers, 19(2), 281-292.
We motivate an approach to evaluating the utility of life-like interface agents that is based on human eye movements rather than questionnaires. An eye tracker is employed to obtain quantitative evidence of a user’s focus of attention without distracting from the primary task. The salient feature of our evaluation strategy is that it allows us to measure important properties of a user’s interaction experience on a moment-by-moment basis in addition to a cumulative (spatial) analysis of the user’s areas of interest. We describe a pilot study in which we compare attending behavior of subjects watching the presentation of a computer-generated apartment layout and visualization augmented by three types of media: an animated agent, a text box, and speech only. The investigation of eye movements revealed that deictic gestures performed by the agent are more effective in directing the attentional focus of subjects to relevant interface objects than the media used in the two control conditions, at a slight cost of distracting the user from visual inspection of the object of reference. The results also demonstrate that the presence of an interface agent seemingly triggers natural and social interaction protocols of human users.
Ryokai, K., Vaucelle, C., & Cassell, J. (2003). Virtual peers as partners in storytelling and literacy learning. Journal of Computer Assisted Learning, 19(2), 195-208.
Literacy learning—learning how to read and write—begins long before children enter school. One of the key skills to reading and writing is the ability to represent thoughts symbolically and share them in language with an audience who may not necessarily share the same temporal and spatial context. Children learn and practice these important language skills everyday, telling stories with the peers and adults around them. In particular, storytelling in the context of peer collaboration provides a key environment for children to learn language skills important for literacy. In light of this, an embodied conversational agent, Sam, who tells stories collaboratively with children was designed. Sam looks like a peer for pre-school children, but tells stories in a developmentally advanced way, modeling narrative skills important for literacy. Results demonstrated that children who played with the virtual peer told stories that more closely resembled the virtual peer's linguistically advanced stories: using more quoted speech and temporal and spatial expressions. In addition, children listened to Sam's stories carefully, assisting her and suggesting improvements. The potential benefits of having technology play a social role in young children's literacy learning is discussed.
Van Eck, R. (2006). The effect of contextual pedagogical advisement and competition on middle-school students' attitude toward mathematics and mathematics instruction using a computer-based simulation game. Journal of Computers in Mathematics and Science Teaching, 25(2), 165-195.
Many students enter mathematics courses with a poor attitude toward mathematics (Gal & Ginsburg, 1994), making attitude as important a consideration as achievement in mathematics (Cognition and Technology Group at Vanderbilt (CTGV), 1992; Marsh, Cairns, Relich, Barnes, & Debus, 1984; Sedighian & Sedighian, 1996). Pedagogical agents are often touted for their ability to address affective variables in learning (Moreno, Mayer, Spires, & Lester, 2001; Baylor, 2000), as are games for both attitude and achievement (Baltra, 1990; Fery & Ponserre, 2001; Kent, 1999). However, few studies have examined the effect of combining agents and games, and none has examined their effect on attitude toward mathematics. This study was designed to determine the effect of contextual pedagogical advisement (CPA) and competition on attitude toward mathematics in a computer-based simulation game. A total of 123 seventh- and eighth-grade students were randomly assigned to one of five conditions formed by crossing the two independent variables and adding a control group. Results indicate that contextual pedagogical advisement can result in lower anxiety toward mathematics scores, especially under competitive conditions.
Veletsianos, G. (2007). Cognitive and affective benefits of an animated pedagogical agent: Considering contextual relevance and aesthetics. Journal of Educational Computing Research, 36(4), 373-377.
Choi and Clark (2006) argue that learning is attributed to the instructional method rather than the specific medium used to deliver instruction (i.e., the pedagogical agent). Additionally, they consider pedagogical agents as unnecessarily expensive tools, whose instructional affordances can be replicated by less expensive options. In this response to Choi and Clark (2006), I argue that pedagogical agents are not a new iteration of the media debate because the anthropomorphous features and social affordances of pedagogical agents elicit psychological responses from learners that other media cannot educe. As such, when considering the implementation of pedagogical agents, researchers need to consider the agent's (a) contextual relevance, and (b) aesthetic properties. It is important to note that none of these factors influence the instructional method used to deliver instruction via a pedagogical agent.