Effects of an artificial agent as a behavioral model on motivational and learning outcomes

Research output: Contribution to journalArticleAcademicpeer-review

Abstract

Earlier research provides inconsistent evidence for effects of pedagogical agents on learning outcomes. We claim that the agent's instructional method helps to explain the inconsistency, with agents that offer behavioral modeling as an instructional method leading to better learning. We conducted two studies to investigate effects of the use of an artificial agent as a persuasive behavioral model on individuals' learning outcomes in the context of computer training. Specifically, in both studies, participants watched an instructional video on how to perform a web search with their eyes using a novel eye-tracking software. Study 1 examined the effects of agent-delivered modeling vs. two non-modeling instructional methods (agent-delivered instructional narration and no agent, text-only instruction) on participants' (N = 197) self-efficacy and system-specific perceptions of ease of use. Study 2 extends findings of Study 1 by examining effects of agent-delivered modeling vs. two non-modeling instructional methods (agent-delivered instructional narration and no agent, voice-only instructional narration) on participants' (N = 99) declarative knowledge and task performance. Previous work with human behavioral models showed an advantage of behavioral modeling over other non-modeling instructional methods in influencing learning outcomes. Therefore, agent-delivered modeling was predicted to be more effective in influencing motivational (i.e., self-efficacy) and learning outcomes (i.e., declarative knowledge, task performance). In accordance with our hypotheses, results revealed that participants who received instructions from an artificial agent as a behavioral model reported significantly stronger self-efficacy beliefs, tended to have higher system-specific ease of use, exhibited enhanced declarative knowledge, and better task performance skills.

LanguageEnglish
Pages84-93
Number of pages10
JournalComputers in Human Behavior
Volume97
DOIs
StatePublished - 1 Aug 2019

Fingerprint

Narration
Learning
Task Performance and Analysis
Self Efficacy
Software
Artificial Agents
Learning Outcomes
Research
Modeling

Keywords

  • Artificial agent
  • Behavioral modeling
  • Learning
  • Motivation
  • Persuasive technology

Cite this

@article{fdd777b6543c4387b7ee45387722cb6a,
title = "Effects of an artificial agent as a behavioral model on motivational and learning outcomes",
abstract = "Earlier research provides inconsistent evidence for effects of pedagogical agents on learning outcomes. We claim that the agent's instructional method helps to explain the inconsistency, with agents that offer behavioral modeling as an instructional method leading to better learning. We conducted two studies to investigate effects of the use of an artificial agent as a persuasive behavioral model on individuals' learning outcomes in the context of computer training. Specifically, in both studies, participants watched an instructional video on how to perform a web search with their eyes using a novel eye-tracking software. Study 1 examined the effects of agent-delivered modeling vs. two non-modeling instructional methods (agent-delivered instructional narration and no agent, text-only instruction) on participants' (N = 197) self-efficacy and system-specific perceptions of ease of use. Study 2 extends findings of Study 1 by examining effects of agent-delivered modeling vs. two non-modeling instructional methods (agent-delivered instructional narration and no agent, voice-only instructional narration) on participants' (N = 99) declarative knowledge and task performance. Previous work with human behavioral models showed an advantage of behavioral modeling over other non-modeling instructional methods in influencing learning outcomes. Therefore, agent-delivered modeling was predicted to be more effective in influencing motivational (i.e., self-efficacy) and learning outcomes (i.e., declarative knowledge, task performance). In accordance with our hypotheses, results revealed that participants who received instructions from an artificial agent as a behavioral model reported significantly stronger self-efficacy beliefs, tended to have higher system-specific ease of use, exhibited enhanced declarative knowledge, and better task performance skills.",
keywords = "Artificial agent, Behavioral modeling, Learning, Motivation, Persuasive technology",
author = "Sofia Fountoukidou and Jaap Ham and Uwe Matzat and Cees Midden",
year = "2019",
month = "8",
day = "1",
doi = "10.1016/j.chb.2019.03.013",
language = "English",
volume = "97",
pages = "84--93",
journal = "Computers in Human Behavior",
issn = "0747-5632",
publisher = "Elsevier",

}

TY - JOUR

T1 - Effects of an artificial agent as a behavioral model on motivational and learning outcomes

AU - Fountoukidou,Sofia

AU - Ham,Jaap

AU - Matzat,Uwe

AU - Midden,Cees

PY - 2019/8/1

Y1 - 2019/8/1

N2 - Earlier research provides inconsistent evidence for effects of pedagogical agents on learning outcomes. We claim that the agent's instructional method helps to explain the inconsistency, with agents that offer behavioral modeling as an instructional method leading to better learning. We conducted two studies to investigate effects of the use of an artificial agent as a persuasive behavioral model on individuals' learning outcomes in the context of computer training. Specifically, in both studies, participants watched an instructional video on how to perform a web search with their eyes using a novel eye-tracking software. Study 1 examined the effects of agent-delivered modeling vs. two non-modeling instructional methods (agent-delivered instructional narration and no agent, text-only instruction) on participants' (N = 197) self-efficacy and system-specific perceptions of ease of use. Study 2 extends findings of Study 1 by examining effects of agent-delivered modeling vs. two non-modeling instructional methods (agent-delivered instructional narration and no agent, voice-only instructional narration) on participants' (N = 99) declarative knowledge and task performance. Previous work with human behavioral models showed an advantage of behavioral modeling over other non-modeling instructional methods in influencing learning outcomes. Therefore, agent-delivered modeling was predicted to be more effective in influencing motivational (i.e., self-efficacy) and learning outcomes (i.e., declarative knowledge, task performance). In accordance with our hypotheses, results revealed that participants who received instructions from an artificial agent as a behavioral model reported significantly stronger self-efficacy beliefs, tended to have higher system-specific ease of use, exhibited enhanced declarative knowledge, and better task performance skills.

AB - Earlier research provides inconsistent evidence for effects of pedagogical agents on learning outcomes. We claim that the agent's instructional method helps to explain the inconsistency, with agents that offer behavioral modeling as an instructional method leading to better learning. We conducted two studies to investigate effects of the use of an artificial agent as a persuasive behavioral model on individuals' learning outcomes in the context of computer training. Specifically, in both studies, participants watched an instructional video on how to perform a web search with their eyes using a novel eye-tracking software. Study 1 examined the effects of agent-delivered modeling vs. two non-modeling instructional methods (agent-delivered instructional narration and no agent, text-only instruction) on participants' (N = 197) self-efficacy and system-specific perceptions of ease of use. Study 2 extends findings of Study 1 by examining effects of agent-delivered modeling vs. two non-modeling instructional methods (agent-delivered instructional narration and no agent, voice-only instructional narration) on participants' (N = 99) declarative knowledge and task performance. Previous work with human behavioral models showed an advantage of behavioral modeling over other non-modeling instructional methods in influencing learning outcomes. Therefore, agent-delivered modeling was predicted to be more effective in influencing motivational (i.e., self-efficacy) and learning outcomes (i.e., declarative knowledge, task performance). In accordance with our hypotheses, results revealed that participants who received instructions from an artificial agent as a behavioral model reported significantly stronger self-efficacy beliefs, tended to have higher system-specific ease of use, exhibited enhanced declarative knowledge, and better task performance skills.

KW - Artificial agent

KW - Behavioral modeling

KW - Learning

KW - Motivation

KW - Persuasive technology

UR - http://www.scopus.com/inward/record.url?scp=85062963545&partnerID=8YFLogxK

U2 - 10.1016/j.chb.2019.03.013

DO - 10.1016/j.chb.2019.03.013

M3 - Article

VL - 97

SP - 84

EP - 93

JO - Computers in Human Behavior

T2 - Computers in Human Behavior

JF - Computers in Human Behavior

SN - 0747-5632

ER -