Matching an Arabic Text to a Learners’ Curriculum (original) (raw)

Abstract

We describe an exploratory study whose goal is to build a predictive model to automatically assess whether a given text is suitable for a learner of Modern Standard Arabic as a foreign language studying at the intermediate level. Before describing the initial version of the model, which focuses on vocabulary content of the learners’ curriculum and the texts, and on other word-related text characteristics, we review the literature on text readability for first and second language reading to extract some text features already found useful for other languages, and examine their appropriateness for our task. The resulting model, tested on different collections of unseen texts, has good predictive accuracy for clustered curriculum stages, reaching 86.95% and 91.3% respectively for k-means clusters and balanced clusters. Accuracy is poorer in some cases, around 60%, when trying to predict the exact stage in the curriculum for which a text should be used.

Violetta Cavalli-Sforza hasn't uploaded this paper.

Let Violetta know you want this paper to be uploaded.

Ask for this paper to be uploaded.