A '''pedagogical agent''' is a concept borrowed from [[computer science]] and [[artificial intelligence]] and applied to education, usually as part of an [[Intelligent tutoring system|intelligent tutoring system (ITS)]]. It is a simulated human-like interface between the learner and the content, in an educational environment. A pedagogical agent is designed to model the type of interactions between a student and another person. Mabanza and de Wet define it as "a character enacted by a computer that interacts with the user in a socially engaging manner".<ref name="one">{{cite book|last1=Mabanza|first1=N|last2=de Wet|first2=L|title=E-Learning Paradigms and Applications|chapter=Determining the Usability Effect of Pedagogical Interface Agents on Adult Computer Literacy Training|journal=E-Learning|volume=528|pages=145–183|date=2014|doi=10.1007/978-3-642-41965-2_6|series=Studies in Computational Intelligence|isbn=978-3-642-41964-5}}</ref> A pedagogical agent can be assigned different roles in the [[learning environment]], such as tutor or co-learner,<ref>{{cite journal|last1=Chin|first1=Doris B.|last2=Dohmen|first2=Ilsa M.|last3=Cheng|first3=Britte H.|last4=Oppezzo|first4=Marily A.|last5=Chase|first5=Catherine C.|last6=Schwartz|first6=Daniel L.|title=Preparing students for future learning with Teachable Agents|journal=Education Tech Research Dev|date=2010|volume=58|issue=6|pages=649–669|doi=10.1007/s11423-010-9154-5|s2cid=54686518 }}</ref> depending on the desired purpose of the agent. "A tutor agent plays the role of a teacher, while a co-learner agent plays the role of a learning companion".<ref name="one" /> [[File:Automated online assistant.png|thumb|right|Computerized agent designed to facilitate interaction between the computer program and the person]]
== History == The history of Pedagogical Agents is closely aligned with the history of [[computer animation]]. As computer animation progressed, it was adopted by educators to enhance computerized learning by including a lifelike interface between the program and the learner. The first versions of a pedagogical agent were more cartoon than person, like Microsoft's [[Office Assistant|Clippy]] which helped users of Microsoft Office load and use the program's features in 1997. However, with developments in computer animation, pedagogical agents can now look lifelike. By 2006 there was a call to develop modular, reusable agents to decrease the time and expertise required to create a pedagogical agent.<ref>{{cite book|last1=Silveira|first1=R.A.|last2=Gomes|first2=E.R.|last3=Vicari|first3=R|editor1-last=Kumar|editor1-first=D|editor2-last=Turner|editor2-first=J|title=Education for the 21st Century-Impact of CIT and Digital Resources|date=2006|publisher=Springer|location=Boston|pages=411–415|chapter=Intelligent Learning Objects: An Agent Approach to Create Interoperable Learning Objects}}</ref> There was also a call in 2009 to enact agent standards.<ref>{{cite journal|last1=Veletsianos|first1=George|last2=Miller|first2=Charles|last3=Doering|first3=Aaron|title=ENALI: A research and design framework for virtual characters and pedagogical agents|journal=Educational Computing Research|date=2009|volume=41|issue=2|pages=171–194|doi=10.2190/EC.41.2.c|url=https://viurrspace.ca/bitstream/10613/5076/1/veletsianos_agents_ENALI.pdf|hdl=10613/5076|s2cid=145034418 |hdl-access=free}}</ref> The standardization and re-usability of pedagogical agents is less of an issue since the decrease in cost and widespread availability of animation tools.<ref>{{cite journal|last1=Govindasamy|first1=Malliga K.|title=Animated pedagogical agents: A review of agent technology software in electronic learning environments|journal=Journal of Educational Multimedia and Hypermedia|date=2014|volume=23|issue=2|pages=163–188}}</ref><ref>{{cite journal|last1=Schroeder|first1=Noah L.|last2=Adesope|first2=Olusola O.|title=A case for the use of pedagogical agents in online learning environments|journal=Journal of Teaching and Learning with Technology|date=2012|volume=1|issue=2|pages=43–47}}</ref> Individualized pedagogical agents can be found across disciplines including medicine, math, law, language learning, automotive, and armed forces.<ref name="one" /> They are used in applications directed to every age, from preschool to adult.<ref name="one" />
== Learning theories related to pedagogical agent design ==
=== Distributed cognition theory === [[Distributed cognition|Distributed cognition theory]] is the method in which cognition progresses in the context of collaboration with others. Pedagogical agents can be designed to assist the cognitive transfer to the learner, operating as artifacts or partners with collaborative role in learning. To support the performance of an action by the user, the pedagogical agent can act as a cognitive tool as long as the agent is equipped with the knowledge that the user lacks. The interactions between the user and the pedagogical agent can facilitate a social relationship. The pedagogical agent may fulfill the role of a working partner.<ref name="five">{{cite journal|last1=Apostol|first1=Ailviu|last2=Şoica|first2=Oana|last3=Manasia|first3=Lorendana|last4=Ştefan|first4=Cătălin|title=Virtual Pedagogical Agents in the Context of Virtual Learning Environments: Framework and Theoretical Models|journal=ELearning & Software for Education|date=2013|issue=2|pages=531–536|doi=10.12753/2066-026X-13-194 |s2cid=257202012 }}</ref>
=== Socio-cultural learning theory === [[Sociocultural perspective|Socio-cultural learning theory]] is how the user develops when they are involved in learning activities in which there is interaction with other agents. A pedagogical agent can: intervene when the user requests, provide support for tasks that the user cannot address, and potentially extend the learners cognitive reach. Interaction with the pedagogical agent may elicit a variety of emotions from the learner. The learner may become excited, confused, frustrated, and/or discouraged. These emotions affect the learners' motivation.<ref name="five" />
=== Extraneous Cognitive Load === [[Cognitive load#Extraneous|Extraneous cognitive load]] is the extra effort being exerted by an individual's [[working memory]] due to the way information is being presented. A pedagogical agent can increase the user's cognitive load by distracting them and becoming the focus of their attention, causing [[Split attention effect|split attention]] between the instructional material and the agent. Agents can reduce the perceived cognitive load by providing narration and personalization that can also promote a user's interest and motivation.<ref>{{Cite journal|last=Yung|first=Hsin I|date=2011|title=Decreasing Extraneous Cognitive Load in Multimedia Environment: Effects of the Pedagogical Agent|journal=Computers and Advanced Technology in Education|location=Calgary, AB, Canada|publisher=ACTAPRESS|doi=10.2316/p.2011.734-055|isbn=9780889868885}}</ref> While research on the reduction of cognitive load from pedagogical agents is minimal, more studies have shown that agents do not increase it.<ref>{{Cite journal|last=Schroeder|first=N. L|date=2017|title=The influence of a pedagogical agent on learners' cognitive load|url=https://www.j-ets.net/ETS/journals/20_4/13.pdf|journal=Journal of Educational Technology & Society|volume=20|issue=4|pages=138–147|archive-date=2019-02-27|access-date=2019-02-27|archive-url=https://web.archive.org/web/20190227120828/https://www.j-ets.net/ETS/journals/20_4/13.pdf|url-status=dead}}</ref><ref>{{Cite journal|last=Davis|first=Robert O.|date=2018|title=The impact of pedagogical agent gesturing in multimedia learning environments: A meta-analysis|journal=Educational Research Review|language=en|volume=24|pages=193–209|doi=10.1016/j.edurev.2018.05.002|s2cid=149837782 }}</ref>
== Effectiveness == It has been suggested by researchers that pedagogical agents may take on different roles in the learning environment.<ref name="two">{{cite journal|last1=Schroeder|first1=Noah L.|last2=Adesope|first2=Olusola O.|title=A Systematic Review of Pedagogical Agents' Persona, Motivation, and Cognitive Load Implications for Learners|journal=Journal of Research on Technology in Education |date=Spring 2014|volume=46|issue=3|page=229|doi=10.1080/15391523.2014.888265|s2cid=144689960 }}</ref> Examples of these roles are: supplanting, scaffolding, coaching, testing, or demonstrating or modelling a procedure. A pedagogical agent as a tutor has not been demonstrated to add any benefit to an educational strategy in equivalent lessons with and without a pedagogical agent.<ref>{{cite book|last1=Clark|first1=Richard E.|last2=Fledon|first2=David F.|editor1-last=Mayer|editor1-first=Richard|title=The Cambridge Handbook of Multimedia Learning|date=2014|publisher=Cambridge University Press|location=New York, NY|isbn=978-1-107-61031-6|chapter=Ten Common but Questionable Principles of Multimedia Learning}}</ref> According to Richard Mayer, there is some support in research for pedagogical agent increasing learning, but only as a presenter of social cues.<ref>{{cite book|last1=Mayer|first1=Richard|editor1-last=Mayer|editor1-first=Richard|title=The Cambridge Handbook of Multimedia Learning|date=2014|publisher=Cambridge University Press|location=New York, NY|isbn=978-1-107-61031-6|chapter=Principles Based on Social Cues}}</ref> A co-learner pedagogical agent is believed to increase the student's [[self-efficacy]]. By pointing out important features of instructional content, a pedagogical agent can fulfill the signaling function, which research on multimedia learning has shown to enhance learning. Research has demonstrated that human-human interaction may not be completely replaced by pedagogical agents, but learners may prefer the agents to non-agent multimedia systems.<ref name="two" /> This finding is supported by [[Agency (sociology)|social agency theory]].
Much like the varying effectiveness of the pedagogical agent roles in the learning environment, agents that take into account the user's affect have had mixed results. Research has shown pedagogical agents that make use of the users’ affect have been found to increase user knowledge retention, motivation, and perceived self-efficacy.<ref>{{Cite book|last1=Conati|first1=Cristina|author-link= Cristina Conati |last2=Zhao|first2=Xiaohong|chapter=Building and evaluating an intelligent pedagogical agent to improve the effectiveness of an educational game |date=2004|title=Proceedings of the 9th international conference on Intelligent user interface - IUI '04|pages=6–13|location=New York, New York, USA|publisher=ACM Press|doi=10.1145/964445.964446|isbn=978-1581138153|citeseerx=10.1.1.67.6798}}</ref><ref>{{Cite journal|last1=Mumm|first1=Jonathan|last2=Mutlu|first2=Bilge|date=2011|title=Designing motivational agents: The role of praise, social comparison, and embodiment in computer feedback|journal=Computers in Human Behavior|volume=27|issue=5|pages=1643–1650|doi=10.1016/j.chb.2011.02.002|issn=0747-5632}}</ref> However, with such a broad range of modalities in affective expressions, it is often difficult to utilize them.<ref>{{Cite journal|last=Patterson|first=Kathleen|date=2011|title=Demystifying Emotion Handbook of Emotions, Third Edition. Michael Lewis, Jeannette M. Haviland-Jones and Lisa Feldman Barrett (Eds.). (2008). New York: The Guilford Press, 848 pp., $95.00 (HB).|journal=Journal of the International Neuropsychological Society|volume=17|issue=3|pages=566–569|doi=10.1017/s1355617711000506|s2cid=143971132 |issn=1355-6177}}</ref> Additionally, having agents detect a user's affective state with precision remains challenging, as displays of affect are different across individuals.<ref>{{Cite journal|last=Picard|first=R. W.|date=2000|title=Affective computing|journal= Pattern Analysis and Applications|volume=1|pages=71–73|doi=10.1007/bf01238028|s2cid=26564332 }}</ref>
== Design ==
=== Attractiveness === The appearance of a pedagogical agent can be manipulated to meet the learning requirements. The attractiveness of a pedagogical agent can enhance student's learning when the users were the opposite gender of the pedagogical agent. Male students prefer a sexy appearance of a female pedagogical agents and dislike the sexy appearance of male agents. Female students were not attracted by the sexy appearance of either male or female pedagogical agents.<ref>{{cite journal|last1=Wang|first1=Chih-Chien|last2=Yeh|first2=Wei-Jyh|title=Avatars with Sex Appeal as Pedagogical Agents: Attractiveness, Trustworthiness, Expertise, and Gender Differences|journal=Journal of Educational Computing Research|date=2013|volume=48|issue=4|pages=403–429|doi=10.2190/EC.48.4.a|s2cid=147595253 }}</ref>
=== Affective Response === Pedagogical agents have reached a point where they can convey and elicit emotion, but also reason about and respond to it. These agents are often designed to elicit and respond to affective actions from users through various modalities such as speech, facial expressions, and body gestures.<ref>{{Cite journal|last1=Johnson|first1=W. Lewis|last2=Lester|first2=James C.|date=2016|title=Face-to-Face Interaction with Pedagogical Agents, Twenty Years Later|journal=International Journal of Artificial Intelligence in Education|language=en|volume=26|issue=1|pages=25–36|doi=10.1007/s40593-015-0065-9|issn=1560-4292|doi-access=free}}</ref> They respond to the affective state of the given user, and make use of these modalities using a wide array of sensors incorporated into the design of the agent.<ref>{{Cite journal|last1=Grafsgaard|first1=Joseph|last2=Wiggins|first2=Joseph|last3=Boyer|first3=Kristy Elizabeth|last4=Wiebe|first4=Eric|last5=Lester|first5=James|date=2014|title=Predicting learning and affect from multimodal data streams in task-oriented tutorial dialogue|journal=Educational Data Mining 2014}}</ref> Specifically in education and training applications, pedagogical agents are often designed to increasingly recognize when users or learners exhibit frustration, boredom, confusion, and states of flow.<ref>{{Cite journal|last1=Swartout|first1=William|last2=Artstein|first2=Ron|last3=Forbell|first3=Eric|last4=Foutz|first4=Susan|last5=Lane|first5=H. Chad|last6=Lange|first6=Belinda|last7=Morie|first7=Jacquelyn Ford|last8=Rizzo|first8=Albert Skip|last9=Traum|first9=David|date=2013-12-15|title=Virtual Humans for Learning|journal=AI Magazine|volume=34|issue=4|pages=13|doi=10.1609/aimag.v34i4.2487|issn=0738-4602|doi-access=free}}</ref> The added recognition in these agents is a step toward making them more emotionally intelligent, comforting and motivating the users as they interact.
=== Digital Representation === The design of a pedagogical agent often begins with its digital representation, whether it will be [[2D computer graphics|2D]] or [[3D computer graphics|3D]] and static or animated. Several studies have developed pedagogical agents that were both static and animated, then evaluated the relative benefits. Similar to other design considerations, the improved learning from static or animated agents remains questionable. One study showed that the appearance of an agent portrayed using a static image can impact a user's recall, based on the visual appearance. Other research found results that suggest static agent images improve learning outcomes. However, several other studies found user's learned more when the pedagogical agent was animated rather than static.<ref>{{Cite book|title=The Effects of Pedagogical Agent Voice and Animation on Learning, Motivation and Perceived Persona|date=2003|publisher=AACE|isbn=9781880094488|location=Proceedings of ED-MEDIA 2003 -- World Conference on Educational Multimedia, Hypermedia & Telecommunications|oclc=1008947184}}</ref><ref>{{Cite journal|last1=Mayer|first1=Richard E.|last2=DaPra|first2=C. Scott|date=2012|title=An embodiment effect in computer-based learning with animated pedagogical agents.|journal=Journal of Experimental Psychology: Applied|language=en|volume=18|issue=3|pages=239–252|doi=10.1037/a0028616|pmid=22642688|issn=1939-2192}}</ref> Recently a [[meta-analysis]] of such research found a negligible improvement in learning via pedagogical agents, suggesting more work needs to be done in the area to support any claims.<ref>{{Citation|last=Mayer|first=Richard E.|editor1-first=Richard|editor1-last=Mayer|chapter=Principles Based on Social Cues in Multimedia Learning: Personalization, Voice, Image, and Embodiment Principles|pages=345–368|publisher=Cambridge University Press|isbn=9781139547369|doi=10.1017/cbo9781139547369.017|title=The Cambridge Handbook of Multimedia Learning|year=2014}}</ref>
==References== {{reflist}}
== External links == * [http://www.isi.edu/AI/isd.htm AI: Artificial Intelligence Research at USC Information Science Institute] * [http://ldt.stanford.edu/~slater/pages/agents/main.htm Stanford University: Interactive Animated Pedagogical Agents]
[[Category:Artificial intelligence]] [[Category:Virtual learning environments]] [[Category:Educational technology]]