Synapse
⌘+K
Synapse
PulseExploreJournal ClubResearchersJournals
Instagram
HomeJournal ClubExplore
June 20, 2026Open Access

Personalizing Second Language Learning: Integrating AI with Learner Preference, Proficiency, and Engagement

View Full Paper
Ask AI
Bookmark
Share

Authors

AGAlireza GharahighehiPIPedro IlídioSSSameh Said-Metwaly

Discussion

Loading...

Member takes

Overview

Randomized trial integrates AI personalization in second language learning, enhancing engagement and proficiency matching.

Key Points

  • The aim is to explore how AI can personalize language learning based on individual learner preferences, proficiency levels, and engagement metrics.
  • Explored personalization in an online platform using data from the NedBox language learning tool.
  • Utilized lightweight recommender systems, DeepIRT for proficiency estimates, and random survival forest for engagement modeling.
  • Focused on three key learner variables: preference, proficiency, and engagement.
  • Lightweight recommender systems performed better than deep models for predicting learner preferences.
  • DeepIRT provided the most robust proficiency estimates.
  • Random survival forest with proficiency estimates effectively modeled learner engagement.

Cite This Study

Gharahighehi et al. (2026) studied this question.

synapsesocial.com/papers/6a3630f5db0793dc1a53800ahttps://doi.org/10.5281/zenodo.20748300
View Full Paper
Ask AI
Bookmark
Share