Automatic Extraction and Prediction of Word Order Errors from Language Learning SNS

Recent research into writing tools to support foreign language learners of English has focused on prevalent errors in learner writing, while other errors, such as word order errors, have received little attention. As the word order of some languages are similar, there are also large differences between languages which can affect foreign language learning. In this paper, we automatically extract corrected sentences that contain word order errors samples from a language learning SNS to create a word order error corpus for machine learning. This corpus is then analyzed to train and evaluate the effectiveness of SVM classifiers to automatically classify word order errors in learner writing.