mlsanityData to 14 Oct 2026

The Sentiment Problem: A Critical Survey towards Deconstructing Sentiment Analysis

arXiv 2310.12318 ↗First posted 18 Oct 2023cs.CL cs.AI cs.CYcited by 12

Not on the map. Why?

Abstract (arXiv)

We conduct an inquiry into the sociotechnical aspects of sentiment analysis (SA) by critically examining 189 peer-reviewed papers on their applications, models, and datasets. Our investigation stems from the recognition that SA has become an integral component of diverse sociotechnical systems, exerting influence on both social and technical users. By delving into sociological and technological literature on sentiment, we unveil distinct conceptualizations of this term in domains such as finance, government, and medicine. Our study exposes a lack of explicit definitions and frameworks for characterizing sentiment, resulting in potential challenges and biases. To tackle this issue, we propose an ethics sheet encompassing critical inquiries to guide practitioners in ensuring equitable utilization of SA. Our findings underscore the significance of adopting an interdisciplinary approach to defining sentiment in SA and offer a pragmatic solution for its implementation.

Key facts. Cited by 12 papers in the map (data through 14 Oct 2026). Builds on 42 of its 191 references that are in the map. First posted on arXiv 18 Oct 2023.

Builds on

42 of 191 references.

References · 42

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,599
  3. 2019XLNet: Generalized Autoregressive Pretraining for Language Understandingcited by 2,811
  4. 2018Datasheets for Datasetscited by 1,386
  5. 2020Language (Technology) is Power: A Critical Survey of "Bias" in NLPcited by 956
  6. 2016Ups and Downs: Modeling the Visual Evolution of Fashion Trends with One-Class Collaborative Filteringcited by 520
  7. 2020TweetEval: Unified Benchmark and Comparative Evaluation for Tweet Classificationcited by 417
  8. 2018Examining Gender and Race Bias in Two Hundred Sentiment Analysis Systemscited by 234
  9. 2019SemEval-2017 Task 4: Sentiment Analysis in Twittercited by 210
  10. 2019Racial Bias in Hate Speech and Abusive Language Detection Datasetscited by 209
  11. 2020Social Biases in NLP Models as Barriers for Persons with Disabilitiescited by 182
  12. 2018Towards Deep Conversational Recommendationscited by 176
30 more
  1. 2019BERT Post-Training for Review Reading Comprehension and Aspect-based Sentiment Analysiscited by 176
  2. 2019Reducing Sentiment Bias in Language Models via Counterfactual Evaluationcited by 148
  3. 2018Deep Learning for Sentiment Analysis : A Surveycited by 139
  4. 2019Utilizing BERT for Aspect-Based Sentiment Analysis via Constructing Auxiliary Sentencecited by 122
  5. 2021On Measures of Biases and Harms in NLPcited by 81
  6. 2019Perturbation Sensitivity Analysis to Detect Unintended Model Biasescited by 74
  7. 2019Adapt or Get Left Behind: Domain Adaptation through BERT Language Model Finetuning for Aspect-Target Sentiment Classificationcited by 63
  8. 2019Generating Personalized Recipes from Historical User Preferencescited by 53
  9. 2023Bias Against 93 Stigmatized Groups in Masked Language Models and Downstream Sentiment Classification Taskscited by 51
  10. 2016Recursive Neural Conditional Random Fields for Aspect-based Sentiment Analysiscited by 35
  11. 2013NRC-Canada: Building the State-of-the-Art in Sentiment Analysis of Tweetscited by 33
  12. 2016SentiHood: Targeted Aspect Based Sentiment Analysis Dataset for Urban Neighbourhoodscited by 32
  13. 2021BiasFinder: Metamorphic Test Generation to Uncover Bias for Sentiment Analysis Systemscited by 24
  14. 2019SemEval-2013 Task 2: Sentiment Analysis in Twittercited by 22
  15. 2023Automated Ableism: An Exploration of Explicit Disability Biases in Sentiment and Toxicity Analysis Modelscited by 20
  16. 2019Good Secretaries, Bad Truck Drivers? Occupational Gender Stereotypes in Sentiment Analysiscited by 19
  17. 2020Context-Guided BERT for Targeted Aspect-Based Sentiment Analysiscited by 18
  18. 2023Unmasking Nationality Bias: A Study of Human Perception of Nationalities in AI-Generated Articlescited by 16
  19. 2023Out of Context: Investigating the Bias and Fairness Concerns of "Artificial Intelligence as a Service"cited by 15
  20. 2021Identification of Bias Against People with Disabilities in Sentiment Analysis and Toxicity Detection Modelscited by 13
  21. 2019Vector of Locally-Aggregated Word Embeddings (VLAWE): A Novel Document-level Representationcited by 10
  22. 2019Rethinking Attribute Representation and Injection for Sentiment Classificationcited by 8
  23. 2020Improving Document-Level Sentiment Analysis with User and Product Contextcited by 7
  24. 2015SentiWords: Deriving a High Precision and High Coverage Lexicon for Sentiment Analysiscited by 5
  25. 2019Natural Language Processing, Sentiment Analysis and Clinical Analyticscited by 4
  26. 2015Social Media Analysis for Product Safety using Text Mining and Sentiment Analysiscited by 3
  27. 2021A `Sourceful' Twist: Emoji Prediction Based on Sentiment, Hashtags and Application Sourcecited by 3
  28. 2013PANAS-t: A Pychometric Scale for Measuring Sentiments on Twittercited by 2
  29. 2017What we really want to find by Sentiment Analysis: The Relationship between Computational Models and Psychological Statecited by 2
  30. 2023GMNLP at SemEval-2023 Task 12: Sentiment Analysis with Phylogeny-Based Adapterscited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 1; 2024: 7; 2025: 3; 2026: 1.

12 papers.

  1. 2024Do Generative AI Models Output Harm while Representing Non-Western Cultures: Evidence from A Community-Centered Approachcited by 26
  2. 2024An Audit on the Perspectives and Challenges of Hallucinations in NLPcited by 17
  3. 2024The "Colonial Impulse" of Natural Language Processing: An Audit of Bengali Sentiment Analysis Tools and Their Identity-based Biasescited by 16
  4. 2024Search Engines in an AI Era: The False Promise of Factual and Verifiable Source-Cited Responsescited by 15
  5. 2024From Melting Pots to Misrepresentations: Exploring Harms in Generative AIcited by 13
  6. 2025A Tale of Two Identities: An Ethical Audit of Human and AI-Crafted Personascited by 8
  7. 2025Can Third-parties Read Our Emotions?cited by 4
  8. 2024Race and Privacy in Broadcast Police Communicationscited by 1
  9. 2023Sentiment Analysis in Digital Spaces: An Overview of Reviewscited by 0
  10. 2024ARTiST: Automated Text Simplification for Task Guidance in Augmented Realitycited by 0
  11. 2025Exploring Subjective Tasks in Farsi: A Survey Analysis and Evaluation of Language Modelscited by 0
  12. 2026ViTOED: A Dataset for Target-Oriented Emotion Detection on Vietnamese Social Media Textscited by 0