Constructing a Data-Driven Learning Tool with Recycled Learner Data

Constructing a Data-Driven Learning Tool with Recycled Learner Data

Trude Heift (Department of Linguistics, Simon Fraser University, Burnaby, Canada) and Catherine Caws (French Department, University of Victoria, Victoria, Canada)
DOI: 10.4018/ijcallt.2014100106
OnDemand PDF Download:
No Current Special Offers


This paper discusses a data-driven learning (DDL) tool, which consists of a learner corpus for L2 learners of German. The learner corpus, in addition to submissions from ongoing current users, has been constructed from millions of submissions from a variety of activity types of approximately 5000 learners who used the E-Tutor CALL system over a period of five years. By following a cyclical process of development, implementation, and evaluation, adapted from the ADDIE model, E-Tutor helped us not only to inform language teaching pedagogy and to provide system enhancements generated by the outcomes of vast data collections, but also to expand an existing learning environment (e.g., Tutorial CALL) to include DDL. The article discusses the cyclical process of collecting and recycling learner data by also focusing on the design features of the DDL tool of E-Tutor within the ADDIE framework and providing data on student usage.
Article Preview

2. A Cyclical Approach To Language Software Engineering

A traditional, commonly employed model for instructional system design is the ADDIE framework (analysis, design, development, implementation, evaluation), which represents a guideline for building effective training and performance support tools (see Colpaert, 2004). As explained by Colpaert (2006a), this model presents the advantage of being compatible with a “research-based” and “research-oriented” (RBRO) methodology (p. 115).

Complete Article List

Search this Journal:
Open Access Articles
Volume 12: 4 Issues (2022): Forthcoming, Available for Pre-Order
Volume 11: 4 Issues (2021)
Volume 10: 4 Issues (2020)
Volume 9: 4 Issues (2019)
Volume 8: 4 Issues (2018)
Volume 7: 4 Issues (2017)
Volume 6: 4 Issues (2016)
Volume 5: 4 Issues (2015)
Volume 4: 4 Issues (2014)
Volume 3: 4 Issues (2013)
Volume 2: 4 Issues (2012)
Volume 1: 4 Issues (2011)
View Complete Journal Contents Listing