Cited by 341Creativity in Education and NeuroscienceTopic ModelingComputational and Text Analysis Methods

Automating creativity assessment with SemDis: An open platform for computing semantic distance

Open access
Beaty, Roger E., Johnson, Dan R.·2021·Behavior Research Methods

Abstract

Creativity research requires assessing the quality of ideas and products. In practice, conducting creativity research often involves asking several human raters to judge participants’ responses to creativity tasks, such as judging the novelty of ideas from the alternate uses task (AUT). Although such subjective scoring methods have proved useful, they have two inherent limitations—labor cost (raters typically code thousands of responses) and subjectivity (raters vary on their perceptions and preferences)—raising classic psychometric threats to reliability and validity. We sought to address the limitations of subjective scoring by capitalizing on recent developments in automated scoring of verbal creativity via semantic distance, a computational method that uses natural language processing to quantify the semantic relatedness of texts. In five studies, we compare the top performing semantic models (e.g., GloVe, continuous bag of words) previously shown to have the highest correspondence to human relatedness judgements. We assessed these semantic models in relation to human creativity ratings from a canonical verbal creativity task (AUT; Studies 1–3) and novelty/creativity ratings from two word association tasks (Studies 4–5). We find that a latent semantic distance factor—comprised of the common variance from five semantic models—reliably and strongly predicts human creativity and novelty ratings across a range of creativity tasks. We also replicate an established experimental effect in the creativity literature (i.e., the serial order effect) and show that semantic distance correlates with other creativity measures, demonstrating convergent validity. We provide an open platform to efficiently compute semantic distance, including tutorials and documentation ( https://osf.io/gz4fc/ ).

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.3758/s13428-020-01453-w

Cites

95 of 95 references verified0 citation errors · 0 not checkable

Statistics

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

  • Sentence embedding models whose direct predecessors have been found to agree well with human judgments of originality in creativity research are used to assess originality via semantic similarity.

    “we investigate originality primarily by means of semantic similarity, using a well-performing sentence embedding model [72] whose direct predecessors [70] have been found to agree well with human judgments of originality in creativity research [6, 26].”
  • Cosine similarity between aggregated word embeddings has been found to agree well with human judgments of semantic similarity.

    “a metric which has been found to agree well with human judgments of semantic similarity [6, 26].”

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Cites

Flagged first, then by citations

1 of the 96 references couldn’t be matched to a known paper.

Research works printed but not linked: 1

  1. Cattell, R. B., & Cattell, A. K. S. (1961/2008). Measuring intelligence with the Culture Fair Tests. Oxford, UK: Hogrefe.

Cited by

Sorted by citations

Authors
Beaty, R. E., & Johnson, D. R.
Affiliations
  • Pennsylvania State University (US)
  • Washington and Lee University (US)
Corresponding author
  • Beaty, Roger E.
  • Johnson, Dan R.
Venue
Behavior Research Methods
Published
2020-08-31
Volume
53
Issue
2
Pages
757-780
ISSN
  • 1554-351X (ISSN-L)
  • 1554-3528
OpenAlex
W3081924543
Cited by
341
References
96
Citations by year
2026: 57 · 2025: 66 · 2024: 79 · 2023: 58 · 2022: 54 · 2021: 23 · 2020: 4
FWCI
33.62
Type
journal article
Language
en
Open access
Locations
  • Behavior Research Methods (publishedVersion, cc-by)
  • PubMed Central (publishedVersion, cc-by)
  • PubMed (publishedVersion)
  • PsyArXiv (OSF Preprints) (submittedVersion, cc-by)
  • PsyArXiv (OSF Preprints) (submittedVersion)
Funders
National Science Foundation (1920653)
Topics
  • Social Sciences › Psychology › Experimental and Cognitive Psychology › Creativity in Education and Neuroscience
  • Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
  • Social Sciences › General Social Sciences › Computational and Text Analysis Methods
Keywords
creativity assessment, semantic distance, alternative uses task, word association task, automated grading, semantic relatedness, gloves, CBOW, serial order effects, convergent validity, open platform
MeSH terms
Creativity, Humans, Psychometrics, Semantics, Reproducibility of Results

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review