Does It Really Matter If You Collaborate With a Computer or a Human Partner?

• In Event: Poster Session 11
  In Poster Session: Machines and Digital Agents

Abstract

In order to understand how students perform on collaborative problem-solving (CPS) computer-based assessment, it is necessary to examine empirically the multifaceted performance that may be distributed across environments, collaboration methods, and problem-solving spaces. The aim of this study was to explore patterns in student CPS performance and motivation in human-to-agent (H-A) settings compared to human-to-human (H-H) settings. One hundred seventy-nine 14-year-old students from the United States, Singapore, and Israel participated in the study. Students in both H-A mode and H-H mode were able to collaborate and communicate by using identical methods and resources. However, while in the H-A mode, students collaborated with a simulated computer-driven partner; in the H-H mode, students collaborated with others student to solve a problem.

Authors

• Yigal Rosen, Pearson

• Maryam Mosharraf, Pearson