Pith. sign in
Pith Number

pith:I7HHKZLK

pith:2026:I7HHKZLKHOSXUWS5I4JPQITVGE
not attested not anchored not stored refs resolved

User Reviews as a Source for Usability Requirements: A Precursor Study on Using Large Language Models

Cedric Wellhausen, Kurt Schneider, Laura Reinhardt

Large language models can identify usability requirements in user reviews with F-scores comparable to human raters when the prompt is well designed.

arxiv:2605.12657 v1 · 2026-05-12 · cs.SE

Add to your LaTeX paper
\usepackage{pith}
\pithnumber{I7HHKZLKHOSXUWS5I4JPQITVGE}

Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge

Record completeness

1 Bitcoin timestamp
2 Internet Archive
3 Author claim open · sign in to claim
4 Citations open
5 Replications open
Portable graph bundle live · download bundle · merged state
The bundle contains the canonical record plus signed events. A mirror can host it anywhere and recompute the same current state with the deterministic merge algorithm.

Claims

C1strongest claim

We determine that LLMs are generally able to recognize usability as a non-functional requirement in user reviews, in terms of their F-score, but the performance and reliability is strongly dependent on the prompt.

C2weakest assumption

That the human raters provide consistent ground truth labels and that the prompt developed on this dataset will produce reliable results on new reviews or different LLMs.

C3one line summary

LLMs can detect usability content in user reviews with F-scores comparable to humans, though performance depends strongly on prompt design.

References

26 extracted · 26 resolved · 3 Pith anchors

[1] E. Bakiu, E. Guzman, Which feature is unusable? detecting usability and user experience issues from user reviews, in: 2017 IEEE 25th International Requirements Engineering Conference Workshops (REW), 2017 · doi:10.1109/rew.2017.76
[2] Groen, Crowd-Based Requirements Engineering, Doctoral thesis 2 (research not uu / graduation uu), Universiteit Utrecht, 2025 2025 · doi:10.33540/3091
[3] L. Zhao, W. Alhoshan, A. Ferrari, K. J. Letsholo, M. A. Ajagbe, E.-V. Chioasca, R. T. Batista-Navarro, Natural language processing for requirements engineering: A systematic mapping study, ACM Comput. 2021 · doi:10.1145/3444689
[4] Large language models (llms) for requirements engineering (re): A systematic literature review 2025
[5] Revisiting the Performance-Explainability Trade-Off in Explainable Artificial Intelligence (XAI) 2023 · doi:10.1109/rew57809.2023.00024
Receipt and verification
First computed 2026-05-18T03:09:50.612393Z
Builder pith-number-builder-2026-05-17-v1
Signature Pith Ed25519 (pith-v1-2026-05) · public key
Schema pith-number/v1.0

Canonical hash

47ce75656a3ba57a5a5d4712f8227531196c9d3d243737b9c3db92fde2bf330f

Aliases

arxiv: 2605.12657 · arxiv_version: 2605.12657v1 · doi: 10.48550/arxiv.2605.12657 · pith_short_12: I7HHKZLKHOSX · pith_short_16: I7HHKZLKHOSXUWS5 · pith_short_8: I7HHKZLK
Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/I7HHKZLKHOSXUWS5I4JPQITVGE \
  | jq -c '.canonical_record' \
  | python3 -c "import sys,json,hashlib; b=json.dumps(json.loads(sys.stdin.read()), sort_keys=True, separators=(',',':'), ensure_ascii=False).encode(); print(hashlib.sha256(b).hexdigest())"
# expect: 47ce75656a3ba57a5a5d4712f8227531196c9d3d243737b9c3db92fde2bf330f
Canonical record JSON
{
  "metadata": {
    "abstract_canon_sha256": "ea074e42b2341f0861fc56a6780e46339674c619f75f4b7c95a7b8232c644b22",
    "cross_cats_sorted": [],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.SE",
    "submitted_at": "2026-05-12T19:05:04Z",
    "title_canon_sha256": "07fdc213fafd41aae98ed91b52b2c9ed3691b78168d16e3e654083efb0a7975a"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.12657",
    "kind": "arxiv",
    "version": 1
  }
}