Language learning in an era of datafication and personalized learning
- PDF / 632,797 Bytes
- 4 Pages / 439.37 x 666.142 pts Page_size
- 43 Downloads / 211 Views
Language learning in an era of datafication and personalized learning Lori Fulton1 · Daniel L. Hoffman1 · Seungoh Paek1 Accepted: 14 November 2020 © Association for Educational Communications and Technology 2020
Abstract This perspective reviews the technical and educational accomplishments represented by Liu et al.’s (Educ Technol Res Dev 67: 1307–1331, 2019) computer-assisted language learning system. It then zooms out to view the system as an example of what the future of “shifting to digital” might look like. This is done by demonstrating how the authors’ system aligns with two emerging trends in education: datafication and personalized learning. The perspective concludes with constructive feedback and recommendations for future research. Keywords Computer-assisted language learning · Natural language processing · Educational technology · Datafication · Personalized learning · Second language acquisition Before discussing Liu et al.’s (2019) study from a research perspective, let’s begin with a brief summary of their work. Liu et al. (2019) created a computer-assisted language learning (CALL) system, an environment in which learners use technology in a second or other language (Heift and Chapelle 2017). In this case, the CALL system was designed to support Chinese-speaking learners studying Japanese as a second language (JSL). The system focused on Japanese functional expressions, an area of JSL learning known to be difficult for Chinese-speaking students (Han and Song, 2011). To assist learners with functional expressions, Liu et al.’s (2019) system detected real-world Japanese functional expressions and suggested sample sentences aligned to learners’ language proficiency. In terms of evaluation, Liu et al. (2019) examined the system’s technical and educational effectiveness. On the technical side, they evaluated its ability to accurately detect Japanese functional expressions, estimate sentence readability, and locate example sentences with similar meanings. On the educational side, they conducted a user study with * Daniel L. Hoffman [email protected] Lori Fulton [email protected] Seungoh Paek [email protected] 1
University of Hawai‘i at Mānoa, 1776 University Avenue, Honolulu, HI 96822, USA
13
Vol.:(0123456789)
L. Fulton et al.
18 Chinese-speaking JSL learners. These participants were asked to compose sentences involving functional expressions. Half of them completed the sentences using a paperbased dictionary, whereas the other half used the newly developed CALL system. The results revealed that the participants using the CALL system outperformed the other participants as measured by time and learning. Liu et al. (2019) concluded their system provided a “substantial advantage” (p. 1327) for participants using the system, adding that the methods used to build the system could help future researchers develop other language learning systems. From a research perspective, Liu et al.’s (2019) system is a striking example of extracting educational value from existing data. This was possible
Data Loading...
