Dynamic Sentiment Analysis with Local Large Language Models using Majority Voting: A Study on Factors Affecting Restaurant Evaluation
This addresses reproducibility issues in marketing research using LLMs for sentiment analysis, but it is incremental as it applies an existing human annotation technique (majority voting) to LLMs.
This study tackled the problem of variability and reproducibility in sentiment analysis using large language models (LLMs) by introducing a majority voting mechanism with local LLMs, demonstrating that majority voting with multiple attempts using a medium-sized model produces more robust results than using a large model with a single attempt in restaurant review analysis.
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.