Taxonomy of student free-text evaluation

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

Description

The survey organises the field of student free-text evaluation — the automatic evaluation of students' free-text production including short answers and essays — along two axes. By text type, it distinguishes automatic essay evaluation (AEE), where the survey uses "evaluation instead of scoring to emphasise that our survey is not limited to models that predict scores", and automatic short-answer scoring (ASAS). By method, it distinguishes feature-based models, neural architectures (RNN/LSTM, CNN, pre-trained BERT), and hybrid combinations. AEE is further split into holistic essay grading and evaluation of specific aspects of essays; ASAS into evaluation without and based on reference answers. The survey presents state-of-the-art model performance on popular datasets within this structure.

Accounts

• Taxonomy of student free-text evaluation: automatic essay evaluation (holistic and aspect-based) and automatic short-answer scoring (with or without reference answers): The survey organises the field of student free-text evaluation — the automatic evaluation of students' free-text production including short answers and essays — along two axes. By text type, it distinguishes automatic essay evaluation (AEE), where the survey uses "evaluation instead of scoring to emphasise that our survey is not limited to models that predict scores", and automatic short-answer scoring (ASAS). By method, it distinguishes feature-based models, neural architectures (RNN/LSTM, CNN, pre-trained BERT), and hybrid combinations. AEE is further split into holistic essay grading and evaluation of specific aspects of essays; ASAS into evaluation without and based on reference answers. The survey presents state-of-the-art model performance on popular datasets within this structure. (Xiaoyu Bai · Manfred Stede (2023))

Claims

• Concatenating hand-crafted linguistic features with neural essay representations significantly increases essay scoring performance [+M]
• Where labelled training data is limited, adding hand-crafted features improves the performance of neural text evaluation models [+M]

Related Research Methods

-

Key Sources

• Xiaoyu Bai · Manfred Stede. (2023). A Survey of Current Machine Learning Approaches to Student Free-Text Evaluation for Intelligent Tutoring. International Journal of Artificial Intelligence in Education (2023) 33:994–1032. https://doi.org/10.1007/s40593-022-00323-0

Page metadata

Field	Value
type	research-method
id	taxonomy-of-student-free-text-evaluation
title	Taxonomy of student free-text evaluation
description	The survey organises the field of student free-text evaluation — the automatic evaluation of students' free-text production including short answers and essays — along two axes.
status	review
generated	by process:settle-candidates on 2026-10-28
trust	unverified — no one has confirmed this page's content

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