TY - BOOK ID - 77917980 TI - Approaching language transfer through text classification : explorations in the detection-based approach AU - Jarvis, Scott AU - Crossley, Scott A. PY - 2012 SN - 1280998830 9786613770448 1847696996 9781847696991 9781847696991 9781847696984 9781847696977 1847696988 184769697X PB - Bristol ; Buffalo : Multilingual Matters, DB - UniCat KW - Language transfer (Language learning) KW - English language KW - Transfer, Language (Language learning) KW - Language acquisition KW - Language and languages KW - Rhetoric KW - Study and teaching. KW - Study and teaching KW - Germanic languages KW - computer classifiers to detect language background. KW - crosslinguistic influence in SLA. KW - crosslinguistic influence. KW - detection-based approach. KW - learners’ native-language backgrounds. KW - transfer in SLA. KW - transfer in language learning. UR - https://www.unicat.be/uniCat?func=search&query=sysid:77917980 AB - Recent work has pointed to the need for a detection-based approach to transfer capable of discovering elusive crosslinguistic effects through the use of human judges and computer classifiers that can learn to predict learners’ language backgrounds based on their patterns of language use. This book addresses that need. It details the nature of the detection-based approach, discusses how this approach fits into the overall scope of transfer research, and discusses the few previous studies that have laid the groundwork for this approach. The core of the book consists of five empirical studies that use computer classifiers to detect the native-language affiliations of texts written by foreign language learners of English. The results highlight combinations of language features that are the most reliable predictors of learners’ language backgrounds. ER -