From Small Seeds Grow Fruitful Trees: How the PHelpS Peer Help System Stimulated a Diverse and Innovative Research Agenda over 15 Years

Article

DOI: 10.1007/s40593-015-0073-9

Cite this article as:
Vassileva, J., McCalla, G.I. & Greer, J.E. Int J Artif Intell Educ (2016) 26: 431. doi:10.1007/s40593-015-0073-9

Abstract

PHelpS was a system that helped Correctional Service Canada (CSC) workers to find appropriate helpers among their peers when they were encountering problems while interacting with the CSC database. This seemingly simple system had substantial, and surprising, ramifications. Over time it transformed each of our perspectives as to the issues facing AIED. In this paper we reflect on the influence of the PHelpS peer help system on our subsequent research agenda as well as some of the broader influences of our work. In particular, we discuss a number of research projects arising out of PHelpS directly or indirectly, including the I-Help (aka iHelp) system, a peer help system that has been widely deployed in university courses; a distributed multi-agent architecture for peer help systems that uses fragmented learner modelling to support its activities; the active user modelling paradigm which views “learner model” as a computation not a knowledge structure; the ecological approach, a general architecture for learning systems in which patterns mined from learner interactions with learning objects inform pedagogical decisions; investigations, especially into privacy and reputation, arising from the large scale deployment of iHelp supported by evidence mined from iHelp data; and research into novel affective and social motivation techniques. We conclude by discussing the implications of the common perspective that has emerged from these interrelated research projects. This perspective views the goal of learning technology design to be to track learners as they carry out authentic activities, to deeply understand these learners and their learning context, and to provide just in time support for their learning.

Keywords

Peer help Active learner modeling Open learner modeling Ecological approach Privacy Reputation Motivation Affect Educational data mining Agent based learning architectures Simulation Scalability 

Copyright information

© International Artificial Intelligence in Education Society 2015

Authors and Affiliations

  1. 1.ARIES Laboratory, Department of Computer ScienceUniversity of SaskatchewanSaskatoonCanada