Sentiment Analysis of Product Reviews Using Fine-Tuned LLaMa-3 Model: Evaluation with Comprehensive Benchmark Metrics
Sentiment analysis, a crucial subfield of natural language processing, enables businesses and policymakers to understand public emotions and opinions, essential for crafting effective strategies across industries like marketing and customer service. As the volume of online reviews grows, automated s...
Saved in:
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
EDP Sciences
2025-01-01
|
| Series: | ITM Web of Conferences |
| Online Access: | https://www.itm-conferences.org/articles/itmconf/pdf/2025/01/itmconf_dai2024_04021.pdf |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1825206539558846464 |
|---|---|
| author | Wang Yili |
| author_facet | Wang Yili |
| author_sort | Wang Yili |
| collection | DOAJ |
| description | Sentiment analysis, a crucial subfield of natural language processing, enables businesses and policymakers to understand public emotions and opinions, essential for crafting effective strategies across industries like marketing and customer service. As the volume of online reviews grows, automated sentiment classification models have become vital for efficiently processing this data. This study explores fine-tuning the LLaMA-8B large language model based on the Amazon Product Reviews dataset from Kaggle, aiming to improve sentiment classification accuracy. Using the LoRA fine-tuning approach combined with the Variant Greedy Search Technique (VGST) and TextBlob for polarity handling, the research addresses dataset size challenges. The model’s fine-tuning process includes one-shot learning and chain-of-thought prompting to better capture nuanced sentiment expressions. Evaluated using comprehensive metrics, LLaMA-8B demonstrates superior precision compared to Qwen2-7B and achieves near LLaVA performance with enhanced speed. Additionally, it outperforms models like Decision Tree, SVM, Multinomial NB, and XLNet in accuracy. This work underscores the potential of large language models for sentiment analysis and sets the stage for future extensions to multimodal input scenarios. |
| format | Article |
| id | doaj-art-0577809e8b474d8a9589c128bcc6f039 |
| institution | Kabale University |
| issn | 2271-2097 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | EDP Sciences |
| record_format | Article |
| series | ITM Web of Conferences |
| spelling | doaj-art-0577809e8b474d8a9589c128bcc6f0392025-02-07T08:21:11ZengEDP SciencesITM Web of Conferences2271-20972025-01-01700402110.1051/itmconf/20257004021itmconf_dai2024_04021Sentiment Analysis of Product Reviews Using Fine-Tuned LLaMa-3 Model: Evaluation with Comprehensive Benchmark MetricsWang Yili0School of Computer Science and Technology, China University of Mining and TechnologySentiment analysis, a crucial subfield of natural language processing, enables businesses and policymakers to understand public emotions and opinions, essential for crafting effective strategies across industries like marketing and customer service. As the volume of online reviews grows, automated sentiment classification models have become vital for efficiently processing this data. This study explores fine-tuning the LLaMA-8B large language model based on the Amazon Product Reviews dataset from Kaggle, aiming to improve sentiment classification accuracy. Using the LoRA fine-tuning approach combined with the Variant Greedy Search Technique (VGST) and TextBlob for polarity handling, the research addresses dataset size challenges. The model’s fine-tuning process includes one-shot learning and chain-of-thought prompting to better capture nuanced sentiment expressions. Evaluated using comprehensive metrics, LLaMA-8B demonstrates superior precision compared to Qwen2-7B and achieves near LLaVA performance with enhanced speed. Additionally, it outperforms models like Decision Tree, SVM, Multinomial NB, and XLNet in accuracy. This work underscores the potential of large language models for sentiment analysis and sets the stage for future extensions to multimodal input scenarios.https://www.itm-conferences.org/articles/itmconf/pdf/2025/01/itmconf_dai2024_04021.pdf |
| spellingShingle | Wang Yili Sentiment Analysis of Product Reviews Using Fine-Tuned LLaMa-3 Model: Evaluation with Comprehensive Benchmark Metrics ITM Web of Conferences |
| title | Sentiment Analysis of Product Reviews Using Fine-Tuned LLaMa-3 Model: Evaluation with Comprehensive Benchmark Metrics |
| title_full | Sentiment Analysis of Product Reviews Using Fine-Tuned LLaMa-3 Model: Evaluation with Comprehensive Benchmark Metrics |
| title_fullStr | Sentiment Analysis of Product Reviews Using Fine-Tuned LLaMa-3 Model: Evaluation with Comprehensive Benchmark Metrics |
| title_full_unstemmed | Sentiment Analysis of Product Reviews Using Fine-Tuned LLaMa-3 Model: Evaluation with Comprehensive Benchmark Metrics |
| title_short | Sentiment Analysis of Product Reviews Using Fine-Tuned LLaMa-3 Model: Evaluation with Comprehensive Benchmark Metrics |
| title_sort | sentiment analysis of product reviews using fine tuned llama 3 model evaluation with comprehensive benchmark metrics |
| url | https://www.itm-conferences.org/articles/itmconf/pdf/2025/01/itmconf_dai2024_04021.pdf |
| work_keys_str_mv | AT wangyili sentimentanalysisofproductreviewsusingfinetunedllama3modelevaluationwithcomprehensivebenchmarkmetrics |