摘要：The staggering increase in both types and amount of data in recent years is starting to impact many aspects of our lives, from politics to insurance and from self-driving cars to the monitoring of our health. It is also changing the way we carry out research. As Halfpenny and Procter (2015) predict, “It is possible that it will promote the use of new computational social science methods in place of more traditional quantitative and qualitative research methods” (p. 18). In language education research, the availability of large sets of data (from corpora to social media posts, and from attendance data to the ways and frequency with which learners interact with online resources) presents intriguing opportunities. If we can track large groups of learners over long periods of time, could we identify common patterns, facilitative and inhibitory variables, and possibly even predict future performance? Could we identify possible problems more easily and intervene more quickly? Could we observe what our learners do beyond the classroom—even after their course finishes? And could we then provide ongoing support for genuine life-long learning (Thomas, Reinders, & Gelan, 2017)?..
