mlsanityData to 14 Oct 2026

Dynamic Sentiment Analysis with Local Large Language Models using Majority Voting: A Study on Factors Affecting Restaurant Evaluation

arXiv 2407.13069 ↗First posted 18 Jul 2024cs.CL cs.IRcited by 5

Not on the map. Why?

Abstract (arXiv)

User-generated contents (UGCs) on online platforms allow marketing researchers to understand consumer preferences for products and services. With the advance of large language models (LLMs), some studies utilized the models for annotation and sentiment analysis. However, the relationship between the accuracy and the hyper-parameters of LLMs is yet to be thoroughly examined. In addition, the issues of variability and reproducibility of results from each trial of LLMs have rarely been considered in existing literature. Since actual human annotation uses majority voting to resolve disagreements among annotators, this study introduces a majority voting mechanism to a sentiment analysis model using local LLMs. By a series of three analyses of online reviews on restaurant evaluations, we demonstrate that majority voting with multiple attempts using a medium-sized model produces more robust results than using a large model with a single attempt. Furthermore, we conducted further analysis to investigate the effect of each aspect on the overall evaluation.

Key facts. Cited by 5 papers in the map (data through 14 Oct 2026). Builds on 35 of its 91 references that are in the map. First posted on arXiv 18 Jul 2024.

Builds on

35 of 91 references.

References · 35

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2020Language Models are Few-Shot Learnerscited by 32,419
  3. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,372
  4. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 13,028
  5. 2014Neural Machine Translation by Jointly Learning to Align and Translatecited by 4,548
  6. 2013Efficient Estimation of Word Representations in Vector Spacecited by 4,375
  7. 2019DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lightercited by 4,307
  8. 2014Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translationcited by 4,057
  9. 2017Deep reinforcement learning from human preferencescited by 3,912
  10. 2021Finetuned Language Models Are Zero-Shot Learnerscited by 3,780
  11. 2018Deep contextualized word representationscited by 2,290
  12. 2022GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformerscited by 1,919
23 more
  1. 2016Enriching Word Vectors with Subword Informationcited by 1,583
  2. 2016Bag of Tricks for Efficient Text Classificationcited by 876
  3. 2023ChatGPT Outperforms Crowd-Workers for Text-Annotation Taskscited by 870
  4. 2023SpQR: A Sparse-Quantized Representation for Near-Lossless LLM Weight Compressioncited by 367
  5. 2023Multimodal Deep Learningcited by 258
  6. 2022Is GPT-3 a Good Data Annotator?cited by 208
  7. 2018Deep Learning for Sentiment Analysis : A Surveycited by 139
  8. 2023CodeGen2: Lessons for Training LLMs on Programming and Natural Languagescited by 125
  9. 2023Is ChatGPT a Good Sentiment Analyzer? A Preliminary Studycited by 96
  10. 2016Yelp Dataset Challenge: Review Rating Predictioncited by 84
  11. 2023ZeroQuant-V2: Exploring Post-training Quantization in LLMs from Comprehensive Study to Low Rank Compensationcited by 79
  12. 2023Automated Annotation with Generative AI Requires Validationcited by 76
  13. 2023Testing the Reliability of ChatGPT for Text Annotation and Classification: A Cautionary Remarkcited by 54
  14. 2024A Comprehensive Evaluation of Quantization Strategies for Large Language Modelscited by 48
  15. 2023Do Emergent Abilities Exist in Quantized Large Language Models: An Empirical Studycited by 43
  16. 2024What Makes Quantization for Large Language Models Hard? An Empirical Study from the Lens of Perturbationcited by 23
  17. 2024Quantifying the Capabilities of LLMs across Scale and Precisioncited by 19
  18. 2018An Improved Text Sentiment Classification Model Using TF-IDF and Next Word Negationcited by 16
  19. 2023QIGen: Generating Efficient Kernels for Quantized Inference on Large Language Modelscited by 6
  20. 2016Sentiment Analysis of Review Datasets Using Naive Bayes and K-NN Classifiercited by 5
  21. 2020Yelp Review Rating Prediction: Machine Learning and Deep Learning Modelscited by 5
  22. 2024Multimodal Deep Learning of Word-of-Mouth Text and Demographics to Predict Customer Rating: Handling Consumer Heterogeneity in Marketingcited by 4
  23. 2023Understanding the Impact of Post-Training Quantization on Large Language Modelscited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 4; 2026: 1.

5 papers.

  1. 2025SafeLawBench: Towards Safe Alignment of Large Language Modelscited by 9
  2. 2025A Simple Ensemble Strategy for LLM Inference: Towards More Stable Text Classificationcited by 8
  3. 2025Agentic LLM Framework for Adaptive Decision Discoursecited by 6
  4. 2025Shift Parallelism: Low-Latency, High-Throughput LLM Inference for Dynamic Workloadscited by 5
  5. 2026Test-Time Augmentation for LLMs: When Input Diversity Beats Output Diversity at Matched Computecited by 0