Integrating an AI-Driven Discussion Platform: The Impact of Platform on Engagement and Quality

Abstract

Online educators rely on asynchronous discussions to satisfy the bulk of student-student engagement that is lost when transferring from a face-to-face to an online format. However, not all discussion platforms are created equal and some specialized tools may offer advantages over standard tools embedded in more comprehensive learning management systems (LMS). In this study, we compare two online discussion platforms – one is the native discussion tool embedded within the Canvas LMS and the other is a specialized discussion platform, Packback, which supports students and instructors with gamified elements and artificial intelligence. Specifically, we assess whether post quality differs across these platforms, as measured by average word count, cited sources and weekly participation rate. The initial results are mixed and differ by course, leading us to conclude that the impact of platform on engagement and quality likely depends on the course content, instructor and protocol.

A Validation of AI-Enabled Discussion Platform Metrics and Relationships to Student Efforts

“…Over 800 students from 15 class sections (including, but not limited to, 1000 level biology, 2000 level research methods in psychology, 4000 level race psychology, and 4000 level investigations in human rights) consented to allowing their posts to be reflected in the 14,599 analyzed posts. While not reflected in the present study, students in Fall 2019 and Spring 2020 semesters were also concurrent participants in another study directly comparing Packback to innate LMS supported discussion boards (Hudson et al, 2020 ). As participation in the present study involved only skimming existing data (discussion posts) from students and data extracted from the platform itself, students were not given formal surveys with demographic information.…”