One subfield of assessment of language proficiency is predicting language proficiency level.
This research aims at proposing a computational linguistic model to predict language proficiency level and to explore the general properties of the levels. To this end, we collect the data from Persian learners' textbooks and extract statistical and linguistic features from this text corpus to train 3 classifiers as learners. The performance of the model varies based on the learning algorithm and the feature set(s) used for training the model. For evaluating the models, four standard metrics, namely accuracy, precision, recall, and F-measure are used.
Based on the results, the model created by the Random Forest classifier performed the best when statistical features extracted from raw text is used. The Support Vector Machine classifier performed the best by using linguistic features extracted from the corpus annotated automatically. This determines that enriching the model and providing various kinds of information do not guarantee that a classifier (learner) performs the best.
To discover the latent teaching methodology of the textbooks, we studied the general performance of the classifiers with respect to the language level and the linguistic knowledge used for creating the model. Based on the obtained results, the amount of extracted features plays an important role during to training a classifier. Furthermore, the average best performance of the classifiers is extending the linguistic knowledge from syntactic patterns at level A to all linguistic information at levels B and C.