mlsanityData to 7 Oct 2026

Deep Learning-based Sentiment Classification: A Comparative Survey

arXiv 2312.17253 ↗First posted 12 Dec 2023cs.CL cs.AIcited by 4

Not on the map. Why?

Abstract (arXiv)

Recently, Deep Learning (DL) approaches have been applied to solve the Sentiment Classification (SC) problem, which is a core task in reviews mining or Sentiment Analysis (SA). The performances of these approaches are affected by different factors. This paper addresses these factors and classifies them into three categories: data preparation based factors, feature representation based factors and the classification techniques based factors. The paper is a comprehensive literature-based survey that compares the performance of more than 100 DL-based SC approaches by using 21 public datasets of reviews given by customers within three specific application domains (products, movies and restaurants). These 21 datasets have different characteristics (balanced/imbalanced, size, etc.) to give a global vision for our study. The comparison explains how the proposed factors quantitatively affect the performance of the studied DL-based SC approaches.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 58 of its 186 references that are in the map. First posted on arXiv 12 Dec 2023.

Builds on

58 of 186 references.

References · 58

  1. 2016Layer Normalizationcited by 5,579
  2. 2014Neural Machine Translation by Jointly Learning to Align and Translatecited by 4,530
  3. 2014Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translationcited by 4,016
  4. 2015Character-level Convolutional Networks for Text Classificationcited by 2,293
  5. 2018Deep contextualized word representationscited by 2,285
  6. 2014On the Properties of Neural Machine Translation: Encoder-Decoder Approachescited by 1,303
  7. 2014Convolutional Neural Networks for Sentence Classificationcited by 1,124
  8. 2016Bag of Tricks for Efficient Text Classificationcited by 869
  9. 2014Distributed Representations of Sentences and Documentscited by 677
  10. 2015Skip-Thought Vectorscited by 321
  11. 2015Improved Semantic Representations From Tree-Structured Long Short-Term Memory Networkscited by 305
  12. 2016Adversarial Training Methods for Semi-Supervised Text Classificationcited by 280
38 more
  1. 2015Named Entity Recognition with Bidirectional LSTM-CNNscited by 201
  2. 2015Semi-supervised Sequence Learningcited by 198
  3. 2018An efficient framework for learning sentence representationscited by 197
  4. 2014A Convolutional Neural Network for Modelling Sentencescited by 163
  5. 2017Learning to Generate Reviews and Discovering Sentimentcited by 147
  6. 2018Deep Learning for Sentiment Analysis : A Surveycited by 139
  7. 2016Harnessing Deep Neural Networks with Logic Rulescited by 135
  8. 2016Learning Distributed Representations of Sentences from Unlabelled Datacited by 90
  9. 2015Effective LSTMs for Target-Dependent Sentiment Classificationcited by 82
  10. 2016Aspect Level Sentiment Classification with Deep Memory Networkcited by 82
  11. 2018Interpretable Adversarial Perturbation in Input Embedding Space for Textcited by 67
  12. 2015Towards Universal Paraphrastic Sentence Embeddingscited by 59
  13. 2018Baseline Needs More Love: On Simple Word-Embedding-Based Models and Associated Pooling Mechanismscited by 53
  14. 2018Learning General Purpose Distributed Sentence Representations via Large Scale Multi-task Learningcited by 52
  15. 2017Learning to Compose Task-Specific Tree Structurescited by 48
  16. 2014Effective Use of Word Order for Text Categorization with Convolutional Neural Networkscited by 39
  17. 2016Multiplicative LSTM for sequence modellingcited by 27
  18. 2016TopicRNN: A Recurrent Neural Network with Long-Range Semantic Dependencycited by 27
  19. 2020Revisiting LSTM Networks for Semi-Supervised Text Classification via Mixed Objective Functioncited by 23
  20. 2019Parameterized Convolutional Neural Networks for Aspect Level Sentiment Classificationcited by 22
  21. 2016A Hierarchical Model of Reviews for Aspect-based Sentiment Analysiscited by 21
  22. 2017Deep Learning with Dynamic Computation Graphscited by 15
  23. 2016Neural Semantic Encoderscited by 14
  24. 2017Learning to Attend via Word-Aspect Associative Fusion for Aspect-based Sentiment Analysiscited by 14
  25. 2018A Benchmark Study on Sentiment Analysis for Software Engineering Researchcited by 14
  26. 2016Very Deep Convolutional Networks for Text Classificationcited by 12
  27. 2016Supervised and Semi-Supervised Text Categorization using LSTM for Region Embeddingscited by 11
  28. 2015Self-Adaptive Hierarchical Sentence Modelcited by 10
  29. 2018Left-Center-Right Separated Neural Network for Aspect-based Sentiment Analysis with Rotatory Attentioncited by 10
  30. 2016Neural Tree Indexers for Text Understandingcited by 9
  31. 2015Aspect-based Opinion Summarization with Convolutional Neural Networkscited by 6
  32. 2016Efficient Character-level Document Classification by Combining Convolution and Recurrent Layerscited by 6
  33. 2017Deconvolutional Paragraph Representation Learningcited by 6
  34. 2014A Statistical Parsing Framework for Sentiment Classificationcited by 5
  35. 2014Ensemble of Generative and Discriminative Techniques for Sentiment Analysis of Movie Reviewscited by 5
  36. 2016Multichannel Variable-Size Convolution for Sentence Classificationcited by 5
  37. 2018Dynamic Compositionality in Recursive Neural Networks with Structure-aware Tag Representationscited by 5
  38. 2017k-Nearest Neighbor Augmented Neural Networks for Text Classificationcited by 4

50 most cited of 58 All 58 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

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

4 papers.

  1. 2023Pneumonia Detection on chest X-ray images Using Ensemble of Deep Convolutional Neural Networkscited by 9
  2. 2024RoBERTa-BiLSTM: A Context-Aware Hybrid Model for Sentiment Analysiscited by 7
  3. 2025Multi-Modal Sentiment Analysis with Dynamic Attention Fusioncited by 0
  4. 2026Task Competence Is Not Instruction Following: Evaluating Instruction-Conflicting Behavior in Small Language Modelscited by 0