Sequence alignment and clustering for collaborative-learning process analysis

Research Method · All research methods
Evidence · 2 claims (2 for) · 1 study (1 associational), q2 · 0 of 1 report an effect size · 2 claims rest on one study

Description

The article adapts sequence alignment from bioinformatics: group action logs are human-coded into contribution types — "coordination, monitoring, minor contribution, and major contribution" — plus a "gap" code for more than 24 hours of inactivity. Pairwise edit distances (a Levenshtein variant, with gap operations costed 2) form a similarity matrix that is clustered with partitioning around medoids (PAM), with k chosen by silhouette analysis. The authors claim this method "can serve as a kind of microscope to capture differences in the underlying collaboration processes", and distinguish it from sequential pattern mining, which finds recurring subsequences rather than whole-string similarity.

Accounts

• Sequence alignment and clustering as an analytic method ('microscope') for characterizing collaboration quality in asynchronous group work: The article adapts sequence alignment from bioinformatics: group action logs are human-coded into contribution types — "coordination, monitoring, minor contribution, and major contribution" — plus a "gap" code for more than 24 hours of inactivity. Pairwise edit distances (a Levenshtein variant, with gap operations costed 2) form a similarity matrix that is clustered with partitioning around medoids (PAM), with k chosen by silhouette analysis. The authors claim this method "can serve as a kind of microscope to capture differences in the underlying collaboration processes", and distinguish it from sequential pattern mining, which finds recurring subsequences rather than whole-string similarity. (H. Ulrich Hoppe (2021))

Claims

• Sequence-alignment clusters of small-group action logs differ in productivity and balance of contribution, with the largest cluster showing the lowest word count and highest imbalance [+W]
• Coordination actions discriminate well-functioning groups better than inactivity: a CART decision tree splits clusters on coordination counts (value 3.5), revising the assumption that gaps are the key failure indicator [+W]

Related Research Methods

-

Key Sources

• H. Ulrich Hoppe, et al. (2021). Using Sequence Analysis to Determine the Well-Functioning of Small Groups in Large Online Courses. International Journal of Artificial Intelligence in Education. https://doi.org/10.1007/s40593-020-00229-9

Page metadata

Field	Value
type	research-method
id	sequence-alignment-and-clustering-for-collaborative-learning-process-analysis
title	Sequence alignment and clustering for collaborative-learning process analysis
description	The article adapts sequence alignment from bioinformatics: group action logs are human-coded into contribution types — "coordination, monitoring, minor contribution, and major contribution" — plus a "gap" code for more than 24 hours of inactivity.
status	review
generated	by process:settle-candidates on 2026-10-27
trust	unverified — no one has confirmed this page's content

Frontmatter is the page's machine-readable record — see the Schema & Guide.