mlsanityData to 7 Oct 2026

A Survey of Active Learning for Text Classification using Deep Neural Networks

arXiv 2008.07267 ↗First posted 17 Aug 2020cs.CL cs.LGcited by 50

Not on the map. Why?

Abstract (arXiv)

Natural language processing (NLP) and neural networks (NNs) have both undergone significant changes in recent years. For active learning (AL) purposes, NNs are, however, less commonly used -- despite their current popularity. By using the superior text classification performance of NNs for AL, we can either increase a model's performance using the same amount of data or reduce the data and therefore the required annotation efforts while keeping the same performance. We review AL for text classification using deep neural networks (DNNs) and elaborate on two main causes which used to hinder the adoption: (a) the inability of NNs to provide reliable uncertainty estimates, on which the most commonly used query strategies rely, and (b) the challenge of training DNNs on small data. To investigate the former, we construct a taxonomy of query strategies, which distinguishes between data-based, model-based, and prediction-based instance selection, and investigate the prevalence of these classes in recent research. Moreover, we review recent NN-based advances in NLP like word embeddings or language models in the context of (D)NNs, survey the current state-of-the-art at the intersection of AL, text classification, and DNNs and relate recent advances in NLP to AL. Finally, we analyze recent work in AL for text classification, connect the respective query strategies to the taxonomy, and outline commonalities and shortcomings. As a result, we highlight gaps in current research and present open research questions.

Key facts. Cited by 50 papers in the map (data through 7 Oct 2026). First posted on arXiv 17 Aug 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 7; 2022: 13; 2023: 16; 2024: 6; 2025: 4; 2026: 4.

50 papers.

Sort:

  1. 2022Active Learning on a Budget: Opposite Strategies Suit High and Low Budgetscited by 131
  2. 2023Active Learning Principles for In-Context Learning with Large Language Modelscited by 53
  3. 2022A Survey of Active Learning for Natural Language Processingcited by 40
  4. 2023Which Examples to Annotate for In-Context Learning? Towards Effective and Efficient Selectioncited by 36
  5. 2023Continuous Learning for Android Malware Detectioncited by 33
  6. 2021Diversity Enhanced Active Learning with Strictly Proper Scoring Rulescited by 22
  7. 2022A Survey of Methods for Addressing Class Imbalance in Deep-Learning Based Natural Language Processingcited by 20
  8. 2021A Tale Of Two Long Tailscited by 19
  9. 2025From Selection to Generation: A Survey of LLM-based Active Learningcited by 18
  10. 2023How to Select Which Active Learning Strategy is Best Suited for Your Specific Problem and Budgetcited by 16
  11. 2022Improving Generalizability in Implicitly Abusive Language Detection with Concept Activation Vectorscited by 14
  12. 2023More Samples or More Prompts? Exploring Effective In-Context Sampling for LLM Few-Shot Prompt Engineeringcited by 13
38 more
  1. 2023Human Still Wins over LLM: An Empirical Study of Active Learning on Domain-Specific Annotation Taskscited by 13
  2. 2022Human-Centric Artificial Intelligence Architecture for Industry 5.0 Applicationscited by 11
  3. 2022Improved Algorithms for Neural Active Learningcited by 11
  4. 2023Beyond Labels: Empowering Human Annotators with Natural Language Explanations through a Novel Active-Learning Architecturecited by 10
  5. 2023On the Limitations of Simulating Active Learningcited by 9
  6. 2021LMTurk: Few-Shot Learners as Crowdsourcing Workers in a Language-Model-as-a-Service Frameworkcited by 8
  7. 2022ER-Test: Evaluating Explanation Regularization Methods for Language Modelscited by 6
  8. 2023Bayesian Estimate of Mean Proper Scores for Diversity-Enhanced Active Learningcited by 6
  9. 2024Fine-Tuning Large Language Models for Scientific Text Classification: A Comparative Studycited by 5
  10. 2021A Survey on Active Deep Learning: From Model-driven to Data-drivencited by 4
  11. 2021Active learning for reducing labeling effort in text classification taskscited by 4
  12. 2022A Framework for Interactive Knowledge-Aided Machine Teachingcited by 3
  13. 2023Learning towards Selective Data Augmentation for Dialogue Generationcited by 3
  14. 2022Impact of Stop Sets on Stopping Active Learning for Text Classificationcited by 2
  15. 2023Analyzing Text Representations by Measuring Task Alignmentcited by 2
  16. 2023A Pre-trained Data Deduplication Model based on Active Learningcited by 2
  17. 2023ALE: A Simulation-Based Active Learning Evaluation Framework for the Parameter-Driven Comparison of Query Strategies for NLPcited by 2
  18. 2023On Active Learning for Gaussian Process-based Global Sensitivity Analysiscited by 2
  19. 2024Hands-On Tutorial: Labeling with LLM and Human-in-the-Loopcited by 2
  20. 2025Reassessing Active Learning Adoption in Contemporary NLP: A Community Surveycited by 2
  21. 2026Retrieving Floods without Floodlights: Topic Models as Binary Classifiers for Extreme Climate Events in German Newscited by 2
  22. 2021Active learning based generative design for the discovery of wide bandgap materialscited by 1
  23. 2022ImitAL: Learned Active Learning Strategy on Synthetic Datacited by 1
  24. 2022MAViC: Multimodal Active Learning for Video Captioningcited by 1
  25. 2023Deep active learning for nonlinear system identificationcited by 1
  26. 2026Active Learning for Decision Trees with Provable Guaranteescited by 1
  27. 2021Knowledge Modelling and Active Learning in Manufacturingcited by 0
  28. 2022Analyzing Text Representations under Tight Annotation Budgets: Measuring Structural Alignmentcited by 0
  29. 2022Label-Efficient Interactive Time-Series Anomaly Detectioncited by 0
  30. 2023Taming Small-sample Bias in Low-budget Active Learningcited by 0
  31. 2024Towards Efficient Active Learning in NLP via Pretrained Representationscited by 0
  32. 2024A Utility-Mining-Driven Active Learning Approach for Analyzing Clickstream Sequencescited by 0
  33. 2024Maximally Separated Active Learningcited by 0
  34. 2024The Power of Adaptation: Boosting In-Context Learning through Adaptive Promptingcited by 0
  35. 2025Advancing Scientific Text Classification: Fine-Tuned Models with Dataset Expansion and Hard-Votingcited by 0
  36. 2025Survey of Active Learning Hyperparameters: Insights from a Large-Scale Experimental Gridcited by 0
  37. 2026Goal-Oriented Influence-Maximizing Data Acquisition for Learning and Optimizationcited by 0
  38. 2026Do We Still Need Humans in the Loop? Human vs. LLM Annotation in Active Learning for TikTok Hate Speech Detectioncited by 0