A Reading Recommendation System for ESL Learners Based on Linguistic Features

This paper presents a reading recommendation system based on morpho-phonological, lexical, and syntactic features reflecting both textual complexity and the learner’s linguistic proficiency. The goal of this system is to optimize the reading process of ESL learners by proposing the fittest text to their needs given their incrementally built profile (weighted history of read texts). Fifteen features out of an initial pool of 90 candidates were selected. A corpus of 5052 texts of different levels was collected and used to build the system. To make the system more adaptive, a Progress Rate (PRate) measure was also proposed and integrated into the search process. Finally, the evaluation of the system showed positive results.