Storyfier: Exploring Vocabulary Learning Support with Text Generation Models

TL;DR

Storyfier is a text generation tool designed to support vocabulary learning by providing coherent stories with target words, but it shows mixed effectiveness in improving word recall and usage among learners.

Contribution

This paper introduces Storyfier, a novel AI-powered platform that generates customized stories for vocabulary learning, integrating story reading, cloze tests, and writing tasks.

Findings

Learners prefer generated stories for connecting words and writing support.

Participants using Storyfier performed worse in recall and usage than baseline.

Study highlights challenges in using generative models for effective vocabulary learning.

Abstract

Vocabulary learning support tools have widely exploited existing materials, e.g., stories or video clips, as contexts to help users memorize each target word. However, these tools could not provide a coherent context for any target words of learners' interests, and they seldom help practice word usage. In this paper, we work with teachers and students to iteratively develop Storyfier, which leverages text generation models to enable learners to read a generated story that covers any target words, conduct a story cloze test, and use these words to write a new story with adaptive AI assistance. Our within-subjects study (N=28) shows that learners generally favor the generated stories for connecting target words and writing assistance for easing their learning workload. However, in the read-cloze-write learning sessions, participants using Storyfier perform worse in recalling and using target words than learning with a baseline tool without our AI features. We discuss insights into supporting learning tasks with generative models.