Cited by 1Sentiment Analysis and Opinion MiningTopic ModelingHate Speech and Cyberbullying Detection

Large language models for aspect-based sentiment analysis in e-commerce: A review

Huang, Huang, Li, Yu, Dong, Qiyuan, Asemi, Adeleh, Mustafa, Mumtaz Begum, Asemi, Asefeh·2026·Applied Soft Computing

Integrity signals

Registry

Crossref · 10.1016/j.asoc.2026.116083

Cites

80 of 80 references verified0 citation errors · 0 not checkable

Statistics

Recomputing p-values needs the paper’s full text.

Claims the paper makes

We couldn’t retrieve this paper’s full text, so its claims and self-check weren’t run. The registry and citation checks still apply.

Cites

Flagged first, then by citations

Research works printed but not linked: 19

  1. Verma, 2022, A Surv. Cross-Ling. Asp. -Based Sentim. Anal.
  2. Huang, 2024, Supervised and Few-Shot Learning for Aspect-Based Sentiment Analysis of Instruction Prompt, Electronics, 13, 1924, 10.3390/electronics13101924 · DOI
  3. Lewis, 2020, Retrieval-augmented generation for knowledge-intensive NLP tasks. In Advances in Neural Information Processing Systems (NeurIPS 2020), Curran Assoc. Inc.
  4. Merth, 2024, Superposition prompting: Improving and accelerating retrieval-augmented generation, arXiv Prepr. arXiv, 06910
  5. Singh, 2018, Natural language processing for information extraction, arXiv Prepr. arXiv, 02383
  6. Thogesan, 2025, Integration of explainable ai techniques with large language models for enhanced interpretability for sentiment analysis, arXiv Prepr. arXiv, 11948
  7. Beltagy, 2020, Longformer: The long-document transformer, arXiv
  8. Fedus, 2021, Switch transformers: Scaling to trillion parameter models with simple and efficient sparsity, arXiv
  9. Zaheer, 2020, Big Bird: Transformers for longer sequences. In Advances in Neural Information Processing Systems (NeurIPS 2020), arXiv
  10. Xiong, 2023, Effective long-context scaling of foundation models, arXiv Prepr. arXiv, 16039
  11. Shazeer, 2017, Outrageously large neural networks: The sparsely-gated mixture-of-experts layer, arXiv
  12. Wang, 2024, Model compression and efficient inference for large language models: A survey, arXiv Prepr. arXiv, 09748
  13. Wei, 2024, Stable knowledge editing in large language models, arXiv Prepr. arXiv, 13048
  14. Wu, 2023, Eva-kellm: A new benchmark for evaluating knowledge editing of llms, arXiv Prepr. arXiv, 09954
  15. Zhang, 2024, A comprehensive study of knowledge editing for large language models, arXiv Prepr. arXiv, 01286
  16. Nguyen, 2022, A survey of machine unlearning, arXiv
  17. Veldanda, 2024, Llm surgery: Efficient knowledge unlearning and editing in large language models, arXiv Prepr. arXiv, 13054
  18. Xu, 2024, Lmeraser: Large model unlearning through adaptive prompt tuning, arXiv Prepr. arXiv, 11056
  19. Drouin, 2024, Workarena: How capable are web agents at solving common knowledge work tasks?, arXiv Prepr. arXiv, 07718

Cited by

Still being checked.

Authors
Huang, H., Li, Y., Dong, Q., Asemi, A., Mustafa, M. B., & Asemi, A.
Affiliations
  • University of Malaya (MY)
  • Illinois Institute of Technology (US)
  • Corvinus University of Budapest (HU)
Corresponding author
  • Asemi, Adeleh
  • Mustafa, Mumtaz Begum
Venue
Applied Soft Computing
Publisher
Elsevier BV
Published
2026-11
Volume
203
Pages
116083
ISSN
1568-4946 (ISSN-L)
OpenAlex
W7170766035
Cited by
1
References
80
Citations by year
2026: 1
FWCI
3.42
Type
journal article
Language
en
Open access
closed
Locations
Applied Soft Computing (publishedVersion)
Topics
  • Physical Sciences › Computer Science › Artificial Intelligence › Sentiment Analysis and Opinion Mining
  • Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
  • Physical Sciences › Computer Science › Artificial Intelligence › Hate Speech and Cyberbullying Detection
Keywords
aspect-based sentiment analysis, large language models, online customer reviews, customer opinion mining, encoder-only models, decoder-only models, encoder-decoder architecture, few-shot learning, retrieval-augmented generation, domain adaptation, multilingual sentiment analysis, hallucinations, factual grounding, multimodal sentiment analysis

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