Composable LLM workflow for educational survey analysis

Research Method · All research methods
Evidence · 1 claim (1 for) · 1 study (1 design), q3 · 0 of 1 report an effect size · 1 claim rests on one study

Description

A framework treating educational survey analysis goals as sequences of natural language processing tasks — multi-label, multi-class, and binary classification, extraction, inductive thematic analysis, and sentiment analysis — each performed by an LLM in zero-shot mode. High-level analysis proceeds bottom-up via inductive thematic analysis or top-down via multi-label classification with predefined labels; focused analysis chains extraction followed by classification or thematic analysis, with sentiment analysis as a final step. The authors demonstrate these "composable building blocks" on real end-of-course survey comments, with quantification supported by classification counts.

Accounts

• Educational survey analysis goals achieved by chaining composable LLM-performed NLP tasks into workflows: A framework treating educational survey analysis goals as sequences of natural language processing tasks — multi-label, multi-class, and binary classification, extraction, inductive thematic analysis, and sentiment analysis — each performed by an LLM in zero-shot mode. High-level analysis proceeds bottom-up via inductive thematic analysis or top-down via multi-label classification with predefined labels; focused analysis chains extraction followed by classification or thematic analysis, with sentiment analysis as a final step. The authors demonstrate these "composable building blocks" on real end-of-course survey comments, with quantification supported by classification counts. (Michael J. Parker et al. (2024))

Claims

• GPT-4's chain-of-thought reasoning, captured via structured output, was consistently reliable and appeared to provide logical, context-grounded justification usable for prompt tuning and end-user insight [+M]

Related Research Methods

-

Key Sources

• Michael J. Parker, Caitlin Anderson, Claire Stone, YeaRim Oh. (2024). A Large Language Model Approach to Educational Survey Feedback Analysis. International Journal of Artificial Intelligence in Education. https://doi.org/10.1007/s40593-024-00414-0

Page metadata

Field	Value
type	research-method
id	composable-llm-workflow-for-educational-survey-analysis
title	Composable LLM workflow for educational survey analysis
description	A framework treating educational survey analysis goals as sequences of natural language processing tasks — multi-label, multi-class, and binary classification, extraction, inductive thematic analysis, and sentiment analysis — each performed by an LLM in zero-shot mode.
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.