Impact of window size on the generalizability of collaboration quality estimation models developed using Multimodal Learning Analytics

Abstract

Multimodal Learning Analytics (MMLA) has been applied to collaborative learning, often to estimate collaboration quality with the use of multimodal data, which often have uneven time scales. The difference in time scales is usually handled by dividing and aggregating data using a fixed-size time window. So far, the current MMLA research lacks a systematic exploration of whether and how much window size affects the generalizability of collaboration quality estimation models. In this paper, we investigate the impact of different window sizes (e.g., 30 seconds, 60s, 90s, 120s, 180s, 240s) on the generalizability of classification models for collaboration quality and its underlying dimensions (e.g., argumentation). Our results from an MMLA study involving the use of audio and log data showed that a 60 seconds window size enabled the development of more generalizable models for collaboration quality (AUC 61%) and argumentation (AUC 64%). In contrast, for modeling dimensions focusing on coordination, interpersonal relationship, and joint information processing, a window size of 180 seconds led to better performance in terms of across-context generalizability (on average from 56% AUC to 63% AUC). These findings have implications for the eventual application of MMLA in authentic practice.