Recognizing English Learners' Native Language from Their Writings

Native Language Identification (NLI), which tries to identify the native language (L1) of a second language learner based on their writings, is helpful for advancing second language learning and authorship profiling in forensic linguistics. With the availability of relevant data resources, much work has been done to explore the native language of a foreign language learner. In this report, we present our system for the first shared task in Native Language Identification (NLI). We use a linear SVM classifier and explore features of words, word and character n-grams, style, and metadata. Our official system achieves accuracy of 0.773, which ranks it 18 th among the 29 teams in the closed track.