Automatic generation of leveled visual assessments for young learners

Abstract

Images are an essential tool for communicating with children, particularly at younger ages when they are still developing their emergent literacy skills. Hence, assessments that use images to assess their conceptual knowledge and visual literacy, are an important component of their learning process. Creating assessments at scale is a challenging task, which has led to several techniques being proposed for automatic generation of textual assessments. However, none of them focuses on generating image-based assessments. To understand the manual process of creating visual assessments, we interviewed primary school teachers. Based on the findings from the preliminary study, we present a novel approach which uses image semantics to generate visual multiple choice questions (VMCQs) for young learners, wherein options are presented in the form of images. We propose a metric to measure the semantic similarity between two images, which we use to identify the four options - one answer and three distractor images - for a given question. We also use this metric for generating VMCQs at two difficulty levels - easy and hard. Through a quantitative evaluation, we show that the system-generated VMCQs are comparable to VMCQs created by experts, hence establishing the effectiveness of our approach.