pith. sign in

arxiv: 2508.17008 · v2 · submitted 2025-08-23 · 💻 cs.CL · cs.LG

EduRABSA: An Education Review Dataset for Aspect-based Sentiment Analysis Tasks

Yan Cathy Hua , Paul Denny , J\"org Wicker , Katerina Taskova This is my paper

Pith reviewed 2026-05-18 21:34 UTC · model grok-4.3

classification 💻 cs.CL cs.LG
keywords EduRABSAaspect-based sentiment analysiseducation reviewsimplicit aspect extractionstudent feedbackABSA dataset
0
0 comments X

The pith

EduRABSA is the first public annotated dataset for aspect-based sentiment analysis of education reviews covering courses, staff and universities in English.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper introduces EduRABSA to fill a gap where automatic analysis of student feedback has been limited by scarce public datasets and data protection rules. It creates an annotated collection of reviews that supports aspect-based sentiment analysis across three subject types and includes all main tasks such as implicit aspect and implicit opinion extraction. The authors also release a lightweight offline tool that turns single-task annotations into full multi-task labelled data. Together these resources remove the main barrier to applying fine-grained opinion mining in education and allow institutions to turn raw comments into targeted insights.

Core claim

We present EduRABSA, the first public, annotated ABSA education review dataset that covers three review subject types (course, teaching staff, university) in the English language and all main ABSA tasks, including the under-explored implicit aspect and implicit opinion extraction. We also share ASQE-DPT, an offline, lightweight, installation-free manual data annotation tool that generates labelled datasets for comprehensive ABSA tasks from a single-task annotation.

What carries the argument

EduRABSA dataset of manually annotated student reviews for aspects, opinions, sentiments and their implicit variants across course, staff and university subjects.

If this is right

  • ABSA models can be trained and tested on education review text for the first time with a public benchmark.
  • Extraction of implicit aspects and opinions becomes feasible in student feedback analysis.
  • Educational institutions can obtain sub-sentence level insights to target specific improvements in teaching or courses.
  • The annotation tool supports efficient creation of additional multi-task datasets in the same domain.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • Models trained on this data may identify recurring student concerns that general sentiment tools miss.
  • The resource could transfer to other feedback-heavy domains such as healthcare or public services.
  • Public scripts and statistics encourage community extensions like multilingual versions or larger samples.

Load-bearing premise

The released annotations are of high enough quality for research use and the underlying student comments can be shared publicly without violating data-protection rules.

What would settle it

Independent re-annotation of a sample showing low agreement with the released labels, or discovery that the dataset contains identifiable student information that should not have been released.

Figures

Figures reproduced from arXiv: 2508.17008 by J\"org Wicker, Katerina Taskova, Paul Denny, Yan Cathy Hua.

Figure 1
Figure 1. Figure 1: The overall workflow of creating the EduRABSA dataset [PITH_FULL_IMAGE:figures/full_fig_p003_1.png] view at source ↗
Figure 2
Figure 2. Figure 2: Counts and percentages of review entries [PITH_FULL_IMAGE:figures/full_fig_p006_2.png] view at source ↗
Figure 3
Figure 3. Figure 3: Screenshot of the ASQE-DPT Annotation Tool [PITH_FULL_IMAGE:figures/full_fig_p007_3.png] view at source ↗
read the original abstract

Every year, most educational institutions seek and receive an enormous volume of text feedback from students on courses, teaching, and overall experience. Yet, turning this raw feedback into useful insights is far from straightforward. It has been a long-standing challenge to adopt automatic opinion mining solutions for such education review text data due to the content complexity and low-granularity reporting requirements. Aspect-based Sentiment Analysis (ABSA) offers a promising solution with its rich, sub-sentence-level opinion mining capabilities. However, existing ABSA research and resources are very heavily focused on the commercial domain. In education, they are scarce and hard to develop due to limited public datasets and strict data protection. A high-quality, annotated dataset is urgently needed to advance research in this under-resourced area. In this work, we present EduRABSA (Education Review ABSA), the first public, annotated ABSA education review dataset that covers three review subject types (course, teaching staff, university) in the English language and all main ABSA tasks, including the under-explored implicit aspect and implicit opinion extraction. We also share ASQE-DPT (Data Processing Tool), an offline, lightweight, installation-free manual data annotation tool that generates labelled datasets for comprehensive ABSA tasks from a single-task annotation. Together, these resources contribute to the ABSA community and education domain by removing the dataset barrier, supporting research transparency and reproducibility, and enabling the creation and sharing of further resources. The dataset, annotation tool, and scripts and statistics for dataset processing and sampling are available at https://github.com/yhua219/edurabsa_dataset_and_annotation_tool.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

1 major / 2 minor

Summary. The paper presents EduRABSA, claimed as the first public annotated ABSA dataset for English-language education reviews covering three subject types (course, teaching staff, university) and all core ABSA tasks including implicit aspect and implicit opinion extraction. It also releases the ASQE-DPT offline annotation tool and associated processing scripts, with all resources hosted on GitHub.

Significance. If the annotations are shown to be high-quality, this release would address a documented scarcity of public ABSA resources in the education domain and support reproducibility through the accompanying tool and scripts. The explicit provision of dataset, tool, and sampling/processing code on GitHub is a concrete strength that lowers barriers for follow-on work.

major comments (1)
  1. [Dataset creation and annotation] Dataset creation section: the manuscript provides no quantitative details on inter-annotator agreement, number of annotators, annotation guidelines, sampling procedure for the underlying student comments, or any validation steps. These omissions directly undermine the central claim that EduRABSA constitutes a high-quality, comprehensive resource suitable for advancing ABSA research.
minor comments (2)
  1. [Abstract] Abstract: consider including at least summary statistics (e.g., number of reviews, aspect/opinion counts, task coverage) to give readers an immediate sense of scale.
  2. [Resources] GitHub link: verify that the repository contains clear documentation on data provenance and any licensing or privacy statements.

Simulated Author's Rebuttal

1 responses · 0 unresolved

We thank the referee for the constructive feedback and the recommendation for major revision. We agree that quantitative details on the annotation process are necessary to substantiate claims of dataset quality and will revise the manuscript accordingly.

read point-by-point responses

  1. Referee: Dataset creation section: the manuscript provides no quantitative details on inter-annotator agreement, number of annotators, annotation guidelines, sampling procedure for the underlying student comments, or any validation steps. These omissions directly undermine the central claim that EduRABSA constitutes a high-quality, comprehensive resource suitable for advancing ABSA research.

    Authors: We acknowledge this omission in the current manuscript. While the paper emphasizes the release of the dataset, tool, and scripts to support reproducibility, it does not report the requested quantitative details. In the revised version, we will add a new subsection under Dataset Creation and Annotation that includes: the exact number of annotators, inter-annotator agreement metrics (e.g., Cohen's or Fleiss' kappa values), a summary of the annotation guidelines provided to annotators, the sampling procedure used to select student comments, and any validation or quality-control steps performed. These additions will directly strengthen the evidence for the dataset's quality and address the referee's concern without altering the core contributions. revision: yes

Circularity Check

0 steps flagged

No significant circularity: dataset release paper with no derivation chain

full rationale

This is a dataset and annotation tool release paper. The central claims concern the existence, coverage, and public availability of EduRABSA (three review subject types, English, all main ABSA tasks including implicit aspects/opinions) plus the ASQE-DPT tool. These are supported directly by the GitHub repository link and the described creation process. No equations, fitted parameters, predictions, or mathematical derivations appear. No load-bearing self-citations or uniqueness theorems are invoked. The paper is self-contained against external benchmarks (the released data itself) and does not reduce any result to its own inputs by construction.

Axiom & Free-Parameter Ledger

0 free parameters · 1 axioms · 0 invented entities

The contribution rests on the domain assumption that ABSA tasks are well-defined for education text and that privacy-compliant public release is feasible; no free parameters or new invented entities are introduced.

axioms (1)
  • domain assumption ABSA includes implicit aspect and implicit opinion extraction as standard tasks
    Invoked when the abstract claims coverage of 'all main ABSA tasks, including the under-explored implicit aspect and implicit opinion extraction'

pith-pipeline@v0.9.0 · 5834 in / 1309 out tokens · 51849 ms · 2026-05-18T21:34:02.235212+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Reference graph

Works this paper leans on

43 extracted references · 43 canonical work pages

  1. [1]

    Y .C. Hua, P. Denny, J. Wicker, et al. A systematic review of aspect-based sentiment analysis: Domains, methods, and trends. Artificial Intelligence Review, 57:296, 2024

    work page 2024

  2. [2]

    A survey on aspect-based sentiment analysis: Tasks, methods, and challenges

    Wenxuan Zhang, Xin Li, Yang Deng, Lidong Bing, and Wai Lam. A survey on aspect-based sentiment analysis: Tasks, methods, and challenges. IEEE Trans. on Knowl. and Data Eng., 35(11):11019–11038, dec 2022

    work page 2022

  3. [3]

    Identification of effective deep learning approaches for classifying sentiments at aspect level in different domain

    Shailendra Satyarthi and Sanjiv Sharma. Identification of effective deep learning approaches for classifying sentiments at aspect level in different domain. In 2023 IEEE International Conference on Paradigm Shift in Information Technologies with Innovative Applications in Global Scenario (ICPSITIAGS), pages 496–508, 2023

    work page 2023

  4. [4]

    Uae e-learning sentiment analysis framework

    Dana Wehbe, Ahmed Alhammadi, Hajar Almaskari, Kholoud Alsereidi, and Heba Ismail. Uae e-learning sentiment analysis framework. In The 7th Annual International Conference on Arab Women in Computing in Conjunction with the 2nd Forum of Women in Research, ArabWIC 2021, New York, NY , USA, 2021. Association for Computing Machinery

    work page 2021

  5. [5]

    Domain oriented aspect detection for student feedback system

    Nilar Soe and Paing Thwe Soe. Domain oriented aspect detection for student feedback system. In 2019 International Conference on Advanced Information Technologies (ICAIT), pages 90–95, 2019

    work page 2019

  6. [6]

    Aspect-based opinion mining on student’s feedback for faculty teaching performance evaluation

    Irum Sindhu, Sher Muhammad Daudpota, Kamal Badar, Maheen Bakhtyar, Junaid Baber, and Mohammad Nurunnabi. Aspect-based opinion mining on student’s feedback for faculty teaching performance evaluation. IEEE Access, 7:108729–108741, 2019

    work page 2019

  7. [7]

    Automatic scoring of student feedback for teaching evaluation based on aspect-level sentiment analysis

    Ping Ren, Liu Yang, and Fang Luo. Automatic scoring of student feedback for teaching evaluation based on aspect-level sentiment analysis. Education and Information Technologies, 28(1):797–814, July 2022

    work page 2022

  8. [8]

    SemEval-2015 task 12: Aspect based sentiment analysis

    Maria Pontiki, Dimitris Galanis, Haris Papageorgiou, Suresh Manandhar, and Ion Androutsopoulos. SemEval-2015 task 12: Aspect based sentiment analysis. In Preslav Nakov, Torsten Zesch, Daniel Cer, and David Jurgens, editors, Proceedings of the 9th International Workshop on Semantic Evaluation (SemEval 2015), pages 486–495, Denver, Colorado, June 2015. Asso...

    work page 2015

  9. [9]

    A span-sharing joint extraction framework for harvesting aspect sentiment triplets

    You Li, Yongdong Lin, Yuming Lin, Liang Chang, and Huibing Zhang. A span-sharing joint extraction framework for harvesting aspect sentiment triplets. Knowledge-Based Systems, 242:108366, 2022

    work page 2022

  10. [10]

    A review of datasets for aspect-based sentiment analysis

    Siva Uday Sampreeth Chebolu, Franck Dernoncourt, Nedim Lipka, and Thamar Solorio. A review of datasets for aspect-based sentiment analysis. In Jong C. Park, Yuki Arase, Baotian Hu, Wei Lu, Derry Wijaya, Ayu Purwarianti, and Adila Alfa Krisnadhi, editors, Proceedings of the 13th International Joint Conference on Natural Language Processing and the 3rd Conf...

    work page 2023

  11. [11]

    A knowledge-enhanced contrastive learning network for weakly-supervised aspect detection

    Zhuoming Zheng, Yi Cai, and Liuwu Li. A knowledge-enhanced contrastive learning network for weakly-supervised aspect detection. IEEE Transactions on Audio, Speech and Language Processing , 33:506–517, 2025

    work page 2025

  12. [12]

    Learning Implicit Sentiment in Aspect-based Sentiment Analysis with Supervised Contrastive Pre-Training

    Zhengyan Li, Yicheng Zou, Chong Zhang, Qi Zhang, and Zhongyu Wei. Learning Implicit Sentiment in Aspect-based Sentiment Analysis with Supervised Contrastive Pre-Training. In Marie-Francine Moens, Xuanjing Huang, Lucia Specia, and Scott Wen-tau Yih, editors,Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 246–25...

    work page 2021

  13. [13]

    Pyabsa: A modularized framework for reproducible aspect-based sentiment analysis

    Heng Yang, Chen Zhang, and Ke Li. Pyabsa: A modularized framework for reproducible aspect-based sentiment analysis. In Proceedings of the 32nd ACM International Conference on Information and Knowledge Management, CIKM ’23, page 5117–5122, New York, NY , USA, 2023. Association for Computing Machinery

    work page 2023

  14. [14]

    Implicit aspect-based generative model for sentiment analysis based on prompt learning

    Xinlong Wang, Xu Li, Yinghui Yin, and Yang Li. Implicit aspect-based generative model for sentiment analysis based on prompt learning. In2024 5th International Conference on Big Data & Artificial Intelligence & Software Engineering (ICBASE), pages 94–97, 2024

    work page 2024

  15. [15]

    SemEval-2014 task 4: Aspect based sentiment analysis

    Maria Pontiki, Dimitris Galanis, John Pavlopoulos, Harris Papageorgiou, Ion Androutsopoulos, and Suresh Manandhar. SemEval-2014 task 4: Aspect based sentiment analysis. In Preslav Nakov and Torsten Zesch, editors, Proceedings of the 8th International Workshop on Semantic Evaluation (SemEval 2014) , pages 27–35, Dublin, Ireland, August 2014. Association fo...

    work page 2014

  16. [16]

    Sk2: Integrating implicit sentiment knowledge and explicit syntax knowledge for aspect-based sentiment analysis

    Jia Li, Yuyuan Zhao, Zhi Jin, Ge Li, Tao Shen, Zhengwei Tao, and Chongyang Tao. Sk2: Integrating implicit sentiment knowledge and explicit syntax knowledge for aspect-based sentiment analysis. In Proceedings of the 31st ACM International Conference on Information & Knowledge Management , CIKM ’22, page 1114–1123, New York, NY , USA, 2022. Association for ...

    work page 2022

  17. [17]

    A dual-template prompted mutual learning generative model for implicit aspect-based sentiment analysis

    Zhou Lei, Yawei Zhang, and Shengbo Chen. A dual-template prompted mutual learning generative model for implicit aspect-based sentiment analysis. Applied Sciences, 14(19), 2024

    work page 2024

  18. [18]

    On the robustness of aspect-based sentiment analysis: Rethinking model, data, and training

    Hao Fei, Tat-Seng Chua, Chenliang Li, Donghong Ji, Meishan Zhang, and Yafeng Ren. On the robustness of aspect-based sentiment analysis: Rethinking model, data, and training. ACM Transactions on Information Systems, 41(2):1–32, 2023

    work page 2023

  19. [19]

    A challenge dataset and effective models for aspect-based sentiment analysis

    Qingnan Jiang, Lei Chen, Ruifeng Xu, Xiang Ao, and Min Yang. A challenge dataset and effective models for aspect-based sentiment analysis. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pages 6279–6284, Hong Kong, China, 201...

    work page 2019

  20. [20]

    Exploring progress in aspect-based sentiment analysis: An in-depth survey

    Vishal Singhi, Charulata Chauhan, and Piyush Kumar Soni. Exploring progress in aspect-based sentiment analysis: An in-depth survey. In2024 IEEE 9th International Conference for Convergence in Technology (I2CT), pages 1–10, 2024

    work page 2024

  21. [21]

    A survey on implicit aspect detection for sentiment analysis: Terminology, issues, and scope

    Piyush Kumar Soni and Radhakrishna Rambola. A survey on implicit aspect detection for sentiment analysis: Terminology, issues, and scope. IEEE Access, 10:63932–63957, 2022

    work page 2022

  22. [22]

    iACOS: Advancing implicit sentiment extraction with informative and adaptive negative examples

    Xiancai Xu, Jia-Dong Zhang, Lei Xiong, and Zhishang Liu. iACOS: Advancing implicit sentiment extraction with informative and adaptive negative examples. In Kevin Duh, Helena Gomez, and Steven Bethard, editors, Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Vol...

    work page 2024

  23. [23]

    A dynamic graph structural framework for implicit sentiment identification based on complementary semantic and structural information.Scientific Reports, 14(1):16563, July 2024

    Yuxia Zhao, Mahpirat Mamat, Alimjan Aysa, and Kurban Ubul. A dynamic graph structural framework for implicit sentiment identification based on complementary semantic and structural information.Scientific Reports, 14(1):16563, July 2024

    work page 2024

  24. [24]

    Course reviews university of waterloo

    Anthony Susevski. Course reviews university of waterloo. https://www.kaggle.com/datasets/ anthonysusevski/course-reviews-university-of-waterloo , 2022. Accessed: 2024-09-08

    work page 2022

  25. [25]

    Big data set from ratemyprofessor.com for professors’ teaching evaluation

    Jibo He. Big data set from ratemyprofessor.com for professors’ teaching evaluation. Mendeley Data, V2, 2020. Accessed: 2024-09-08

    work page 2020

  26. [26]

    Sivakumar and U

    M. Sivakumar and U. Srinivasulu Reddy. Aspect based sentiment analysis of students opinion using machine learning techniques. In 2017 International Conference on Inventive Computing and Informatics (ICICI) , pages 726–731, 2017

    work page 2017

  27. [27]

    Aspect-based sentiment analysis of students’ feedback to improve teaching–learning process

    Ganpat Singh Chauhan, Preksha Agrawal, and Yogesh Kumar Meena. Aspect-based sentiment analysis of students’ feedback to improve teaching–learning process. In Suresh Chandra Satapathy and Amit Joshi, editors, Information and Communication Technology for Intelligent Systems, pages 259–266, Singapore, 2019. Springer Singapore

    work page 2019

  28. [28]

    Weakly supervised framework for aspect-based sentiment analysis on students’ reviews of moocs

    Zenun Kastrati, Ali Shariq Imran, and Arianit Kurti. Weakly supervised framework for aspect-based sentiment analysis on students’ reviews of moocs. IEEE Access, 8:106799–106810, 2020

    work page 2020

  29. [29]

    Aspect-based opinion mining of students’ reviews on online courses

    Zenun Kastrati, Blend Arifaj, Arianit Lubishtani, Fitim Gashi, and Engjëll Nishliu. Aspect-based opinion mining of students’ reviews on online courses. In Proceedings of the 2020 6th International Conference on Computing and Artificial Intelligence, ICCAI ’20, page 510–514, New York, NY , USA, 2020. Association for Computing Machinery

    work page 2020

  30. [30]

    Aspect-based sentiment analysis of arabic tweets in the education sector using a hybrid feature selection method

    Manar Alassaf and Ali Mustafa Qamar. Aspect-based sentiment analysis of arabic tweets in the education sector using a hybrid feature selection method. In 2020 14th International Conference on Innovations in Information Technology (IIT), pages 178–185, Al Ain, United Arab Emirates, 2020. IEEE

    work page 2020

  31. [31]

    Moller, and Hou Weiyan

    Shabir Hussain, Muhammad Ayoub, Ghulam Jilani, Yang Yu, Akmal Khan, Junaid Abdul Wahid, Muhammad Farhan Ali Butt, Guangqin Yang, Dietmar P.F. Moller, and Hou Weiyan. Aspect2labels: A novelistic decision support system for higher educational institutions by using multi-layer topic modelling approach.Expert Systems with Applications, 209:118119, 2022

    work page 2022

  32. [32]

    Improving moocs using information from discussion forums: An opinion summarization and suggestion mining approach

    Omaima Almatrafi and Aditya Johri. Improving moocs using information from discussion forums: An opinion summarization and suggestion mining approach. IEEE Access, 10:15565–15573, 2022

    work page 2022

  33. [33]

    The potential of machine learning algorithms for sentiment classification of students’ feedback on mooc

    Maryam Edalati, Ali Shariq Imran, Zenun Kastrati, and Sher Muhammad Daudpota. The potential of machine learning algorithms for sentiment classification of students’ feedback on mooc. In Kohei Arai, editor,Intelligent Systems and Applications, pages 11–22, Cham, 2022. Springer International Publishing

    work page 2022

  34. [34]

    Dissanayake and Pumudu A

    A.D.M.B.B. Dissanayake and Pumudu A. Fernando. Aspect-based sentiment analysis of student reviews on mooc platforms. In 2025 5th International Conference on Advanced Research in Computing (ICARC) , pages 1–6, 2025. 19 EduRABSA: An Education Review Dataset for Aspect-based Sentiment Analysis Tasks

    work page 2025

  35. [35]

    Advancing aspect-based sentiment analysis in course evaluation: A multi-task learning framework with selective paraphrasing

    Shahla Gul, Muhammad Asif, Fazal-E Amin, Kashif Saleem, and Muhammad Imran. Advancing aspect-based sentiment analysis in course evaluation: A multi-task learning framework with selective paraphrasing. IEEE Access, 13:7764–7779, 2025

    work page 2025

  36. [36]

    Centroid-based aspect sentiment analysis for mooc learner reviews

    Naila Marir, Akila Sarirete, and Tayeb Brahimi. Centroid-based aspect sentiment analysis for mooc learner reviews. In 2025 22nd International Learning and Technology Conference (L&T), volume 22, pages 7–12, 2025

    work page 2025

  37. [37]

    SemEval-2016 task 5: Aspect based sentiment analysis

    Maria Pontiki, Dimitris Galanis, Haris Papageorgiou, Ion Androutsopoulos, Suresh Manandhar, Mohammad AL-Smadi, Mahmoud Al-Ayyoub, Yanyan Zhao, Bing Qin, Orphée De Clercq, Véronique Hoste, Marianna Apidianaki, Xavier Tannier, Natalia Loukachevitch, Evgeniy Kotelnikov, Nuria Bel, Salud María Jiménez-Zafra, and Gül¸ sen Eryi˘git. SemEval-2016 task 5: Aspect ...

    work page 2016

  38. [38]

    Chatgpt (mar 14 version) [large language model]

    OpenAI. Chatgpt (mar 14 version) [large language model]. https://chat.openai.com/chat, 2023

    work page 2023

  39. [39]

    University of exeter reviews

    Rohit Pawar. University of exeter reviews. https://www.kaggle.com/datasets/rohitpawar1/ university-of-exeter-reviews , 2023. Accessed: 2024-09-08

    work page 2023

  40. [40]

    Natural Language Processing with Python

    Steven Bird, Edward Loper, and Ewan Klein. Natural Language Processing with Python. O’Reilly Media, Inc., 2009

    work page 2009

  41. [41]

    Super-NaturalInstructions: Generalization via declarative instructions on 1600+ NLP tasks

    Yizhong Wang, Swaroop Mishra, Pegah Alipoormolabashi, Yeganeh Kordi, Amirreza Mirzaei, Atharva Naik, Arjun Ashok, Arut Selvan Dhanasekaran, Anjana Arunkumar, David Stap, Eshaan Pathak, Giannis Karamanolakis, Haizhi Lai, Ishan Purohit, Ishani Mondal, Jacob Anderson, Kirby Kuznia, Krima Doshi, Kuntal Kumar Pal, Maitreya Patel, Mehrad Moradshahi, Mihir Parma...

    work page 2022

  42. [42]

    Two-stage aspect sentiment quadruple prediction based on mrc and text generation

    Zhijun Lil, Zhenyu Yang, Xiaoyang Li, and Yiwen Li. Two-stage aspect sentiment quadruple prediction based on mrc and text generation. In 2023 IEEE International Conference on Systems, Man, and Cybernetics (SMC) , pages 2118–2125, 2023

    work page 2023

  43. [43]

    M-absa: A multilingual dataset for aspect-based sentiment analysis, 2025

    Chengyan Wu, Bolei Ma, Yihong Liu, Zheyu Zhang, Ningyuan Deng, Yanshu Li, Baolan Chen, Yi Zhang, Yun Xue, and Barbara Plank. M-absa: A multilingual dataset for aspect-based sentiment analysis, 2025. 20

    work page 2025