Quick Helper: peer help recommendation in a MOOC using context-aware matrix factorization

Design · All designs
Evidence · no claims cited

Description

The Quick Helper is a discussion-focused intervention integrated with DALMOOC to support help seeking and increase the chance that help requests receive satisfactory responses. Students click a button, are guided to formulate a help request posted to the MOOC discussion board, and "a context-aware matrix factorization model selects three potential help providers from the pool of student peers" based on features of students, questions, and student connections. Selected helpers receive an automatic email invitation to the thread.

Design Implications

Context

Requirements

• Requires a context-aware matrix factorization model built from students' help-request text and metadata rather than large-scale knowledge engineering about learners

Constraints

• The article states it attempts to attract help to requests as formulated but does not support the process of asking for help effectively, nor does it directly address reticent help seekers

Target Learners

• MOOC participants in the Data, Analytics, and Learning course

Learning Goals

• Effective help seeking and peer help exchange in online discussion forums

Claims

• Confusion And Unanswered Help Requests Elevate Attrition [+M]

Related Designs

Examples

-

Key Sources

• Carolyn Penstein Rosé & Oliver Ferschke. (2016). Technology Support for Discussion Based Learning: From Computer Supported Collaborative Learning to the Future of Massive Open Online Courses. Int J Artif Intell Educ. https://doi.org/10.1007/s40593-016-0107-y

Page metadata

Field	Value
type	design
id	quick-helper-peer-help-recommender
title	Quick Helper: peer help recommendation in a MOOC using context-aware matrix factorization
description	The Quick Helper is a discussion-focused intervention integrated with DALMOOC to support help seeking and increase the chance that help requests receive satisfactory responses.
status	review
generated	by process:settle-candidates on 2026-10-27
trust	unverified — no one has confirmed this page's content
sources	1 — carolyn-penstein-rosé-oliver-ferschke-2016

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