mlsanityData to 14 Oct 2026

Explainable Sentiment Analysis with DeepSeek-R1: Performance, Efficiency, and Few-Shot Learning

arXiv 2503.11655 ↗First posted 3 Feb 2025cs.CL cs.AIcited by 5

On the map: LLM reasoning → Reasoning benchmarks and evaluation

Abstract (arXiv)

Large language models (LLMs) have transformed sentiment analysis, yet balancing accuracy, efficiency, and explainability remains a critical challenge. This study presents the first comprehensive evaluation of DeepSeek-R1--an open-source reasoning model--against OpenAI's GPT-4o and GPT-4o-mini. We test the full 671B model and its distilled variants, systematically documenting few-shot learning curves. Our experiments show DeepSeek-R1 achieves a 91.39% F1 score on 5-class sentiment and 99.31% accuracy on binary tasks with just 5 shots, an eightfold improvement in few-shot efficiency over GPT-4o. Architecture-specific distillation effects emerge, where a 32B Qwen2.5-based model outperforms the 70B Llama-based variant by 6.69 percentage points. While its reasoning process reduces throughput, DeepSeek-R1 offers superior explainability via transparent, step-by-step traces, establishing it as a powerful, interpretable open-source alternative.

Key facts. Cited by 5 papers in the map (data through 14 Oct 2026). Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning. Builds on 8 of its 24 references that are in the map. First posted on arXiv 3 Feb 2025.

Builds on

8 of 24 references.

References · 8

  1. 2020Language Models are Few-Shot Learnerscited by 32,419
  2. 2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learningcited by 6,330
  3. 2020GoEmotions: A Dataset of Fine-Grained Emotionscited by 486
  4. 2023Sentiment Analysis in the Era of Large Language Models: A Reality Checkcited by 268
  5. 2023Reasoning Implicit Sentiment with Chain-of-Thought Promptingcited by 80
  6. 2021Local Interpretations for Explainable Natural Language Processing: A Surveycited by 31
  7. 2023A Wide Evaluation of ChatGPT on Affective Computing Taskscited by 30
  8. 2024Enhancing Chain of Thought Prompting in Large Language Models via Reasoning Patternscited by 13

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 2; 2026: 3.

5 papers.

  1. 2026Task Complexity Matters: An Empirical Study of Reasoning in LLMs for Sentiment Analysiscited by 2
  2. 2025Learning-to-Context Slope: Evaluating In-Context Learning Effectiveness Beyond Performance Illusionscited by 1
  3. 2025Fine-tuning of lightweight large language models for sentiment classification on heterogeneous financial textual datacited by 1
  4. 2026A Hormone-inspired Emotion Layer for Transformer language models (HELT)cited by 0
  5. 2026F2Agent: Financial Fusion of Agentic Intelligence for Multimodal Tradingcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Comparative Evaluation of ChatGPT and DeepSeek Across Key NLP Tasks: Strengths, Weaknesses, and Domain-Specific Performance
  2. 2025Analysis of LLM Bias (Chinese Propaganda & Anti-US Sentiment) in DeepSeek-R1 vs. ChatGPT o3-mini-high
  3. 2025A Review of DeepSeek Models' Key Innovative Techniques
  4. 2026Large-Scale Aspect-Based Sentiment Analysis with Reasoning-Infused LLMs
  5. 2024RVISA: Reasoning and Verification for Implicit Sentiment Analysis
  6. 2024DeepSeek LLM: Scaling Open-Source Language Models with Longtermism
  7. 2025DeepSeek-R1 Thoughtology: Let's think about LLM Reasoning
  8. 2025100 Days After DeepSeek-R1: A Survey on Replication Studies and More Directions for Reasoning Language Models