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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Huang, Donghao, Wang, Zhaoxia
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918321700470784
author Huang, Donghao
Wang, Zhaoxia
author_facet Huang, Donghao
Wang, Zhaoxia
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2503_11655
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Explainable Sentiment Analysis with DeepSeek-R1: Performance, Efficiency, and Few-Shot Learning
Huang, Donghao
Wang, Zhaoxia
Computation and Language
Artificial Intelligence
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.
title Explainable Sentiment Analysis with DeepSeek-R1: Performance, Efficiency, and Few-Shot Learning
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2503.11655