Automatic Dialogic Instruction Detection for K-12 Online One-on-one Classes

TL;DR

This paper develops six dialogic instructions for online K-12 one-on-one classes and employs LSTM neural models to automatically detect these instructions, enhancing interactive learning experiences.

Contribution

It introduces a set of six dialogic instructions and applies LSTM models for their automatic detection in online education settings, improving instructional analysis.

Findings

LSTM models achieve AUC scores from 0.840 to 0.979

Six dialogic instructions effectively enhance online teaching

Demonstrates feasibility of automatic instruction detection in real-world data

Abstract

Online one-on-one class is created for highly interactive and immersive learning experience. It demands a large number of qualified online instructors. In this work, we develop six dialogic instructions and help teachers achieve the benefits of one-on-one learning paradigm. Moreover, we utilize neural language models, i.e., long short-term memory (LSTM), to detect above six instructions automatically. Experiments demonstrate that the LSTM approach achieves AUC scores from 0.840 to 0.979 among all six types of instructions on our real-world educational dataset.