English vocabulary learning through recommender system based on sentence complexity and vocabulary difficulty

Based on consideration of learner needs for expanding vocabulary and the complexity of educational content, this paper introduces a model aimed at facilitating English vocabulary learning.

By measuring a set of effective variables regarding simplicity of English sentences, a ranking algorithm is presented in the proposed model. According to this ranking, the simplest sentence in the recommender system (RS) is selected and recommended to the user. Furthermore, Pearson correlation coefficient was used for checking the degree of correlation among the respective parameters on sentence simplicity. For evaluating the efficiency of the recommended algorithm, a prototype was designed by programming using Embarcadero Delphi XE2.

The results of the study indicated that the correlation among the parameters of word frequency, sentence length and average dependency distance were 0.723, 0.683 and 0.589, respectively. The computed final score is considered to be more accurate.

The application of RS in language learning and education sheds light on the theoretical validity of system thinking by highlighting its key features: its multidisciplinary nature, complexity, dynamicity and the interdependence and relation of micro and macro levels in a system.

The proposed method has significant pedagogical implications; it can be used by second language teachers and learners for checking the degree of complexity/learnability of discourse and text.

This paper proposes an alternate model with a significantly higher speed for computing final sentence score.