Estimating Unknown English Words From User Smartphone Reading Behaviors

Abstract

Vocabulary learning is essential for language study, and it is crucial to identify unknown words for users. Conventional English vocabulary learning methods specify words to be learned based on the frequency of vocabulary use and cannot suggest unknown words tailored to individual learners. In this study, we propose a novel smartphone-based unknown English word estimating system called VocabMe. We leverage learner-independent textual features and learner-dependent reading activity behavior data from smartphone sensors. We combined reading time, smartphone acceleration, scroll speed, and rereading patterns to reflect the learners’ reading comprehension abilities. The results showed that the proposed method, including smartphone sensors, outperformed the accuracy of unknown English word estimation in 75 out of 79 participants with different cultural backgrounds, compared to the conventional method of estimating unknown words from texts. This study shows that mobile technology for personalized language learning opens new possibilities for learners to engage more effectively in English vocabulary acquisition.

Keywords

• Mobile application
• mobile learning
• education
• language learning
• personalized learning
• smartphone sensors