Realizing Visual Question Answering for Education: GPT-4V as a Multimodal AI
Gyeong-Geon Lee, Xiaoming Zhai
TL;DR
The paper addresses the automation gap in educational image analysis by leveraging GPT-4V to realize Visual Question Answering (VQA) for education. It defines what it means to realize VQA in two senses: accessibility for educators without technical barriers and demonstration of VQA's value for educational research, then surveys VQA development, GPT-4V features, and prior/post-GPT-4V educational studies. Five concrete VQA tasks are demonstrated with prompt examples to show how GPT-4V can elicit, analyze, and assess pedagogy, engagement, learner work, and classroom resources. The work discusses implications for research methodology, teaching practice, and multimodal AI trajectories, while acknowledging safety considerations and the need for further quantitative validation.
Abstract
Educational scholars have analyzed various image data acquired from teaching and learning situations, such as photos that shows classroom dynamics, students' drawings with regard to the learning content, textbook illustrations, etc. Unquestioningly, most qualitative analysis of and explanation on image data have been conducted by human researchers, without machine-based automation. It was partially because most image processing artificial intelligence models were not accessible to general educational scholars or explainable due to their complex deep neural network architecture. However, the recent development of Visual Question Answering (VQA) techniques is accomplishing usable visual language models, which receive from the user a question about the given image and returns an answer, both in natural language. Particularly, GPT-4V released by OpenAI, has wide opened the state-of-the-art visual langauge model service so that VQA could be used for a variety of purposes. However, VQA and GPT-4V have not yet been applied to educational studies much. In this position paper, we suggest that GPT-4V contributes to realizing VQA for education. By 'realizing' VQA, we denote two meanings: (1) GPT-4V realizes the utilization of VQA techniques by any educational scholars without technical/accessibility barrier, and (2) GPT-4V makes educational scholars realize the usefulness of VQA to educational research. Given these, this paper aims to introduce VQA for educational studies so that it provides a milestone for educational research methodology. In this paper, chapter II reviews the development of VQA techniques, which primes with the release of GPT-4V. Chapter III reviews the use of image analysis in educational studies. Chapter IV demonstrates how GPT-4V can be used for each research usage reviewed in Chapter III, with operating prompts provided. Finally, chapter V discusses the future implications.