Computer Assisted Language Learning (CALL) has a long history of helping learners to develop their second language (L2) abilities. Mobile Assisted Language Learning (MALL) is a developing sub-area of CALL that uses mobile devices, like the iPhone or Android’s Nexus One, instead of a computer to deliver educational materials. However, most current MALL applications fail to fully exploit the affordances provided by mobile devices. One affordance that they could better explore is the use of contextual information (e.g., location or preferences) to provide learners with more appropriate support.
This MALL application for Android platforms will provide learners with context-specific vocabulary in order to support their L2 communication. To enable this scaffolding, a model of the learner’s preferences and vocabulary use will be built. This learner model will be built using a combination of learner entered data and logs of the learner’s actions as input to standard machine learning and statistical modeling techniques.
The created learner model will then be used to recommend personalized vocabulary that meets the learner’s communication needs and preferences based on the learner’s ever-changing context (location, activity, and preferences). This personalization will help ensure that the vocabulary support that is provided through the application will be relevant to each learner regardless of what he or she is doing.