Elise Hopman will present at the upcoming Kaleidoscope Graduate Conference at the Department of Spanish and Portuguese of the University of Wisconsin-Madison. Her talk is titled “A Big Data Investigation into Predictors of Early Second Language Word Learning Accuracy” and will be part of the round-table discussion “Mastering Vocabulary: Language Learning and Teaching”. This work is a collaboration with Bill Thompson, Joe Austerweil and Gary Lupyan, and has also been submitted as a 6 page paper to CogSci 2018.
Abstract:
What makes some words harder to learn than others in a second language? Although some factors have been identified robustly based on small scale experimental studies, many relevant factors are difficult to study in such experiments due to the amount of data necessary to test them. Here, we use a large data set of users learning English as a second language through the Duolingo mobile app to investigate this question. In a regression analysis, we test and confirm the well-studied effect of cognate status on word learning accuracy. Furthermore, we find significant effects for both cross-linguistic semantic alignment and English semantic density, two novel predictors derived from large scale distributional models of lexical semantics. Finally, we provide data on several other psycholinguistically plausible word level predictors. We conclude with a discussion of the limits, benefits and potential future research benefits of using big data for investigating second language learning.
Mastering Vocabulary(2)(1)