The paper "Sentiment Analysis in the Age of Generative AI" by Jan Ole Krugmann and Jochen Hartmann explores the capabilities of Large Language Models (LLMs) in sentiment analysis, a critical task in marketing research. The authors benchmark three state-of-the-art LLMs—GPT-3.5, GPT-4, and Llama 2—against established transfer learning models to assess their performance in sentiment classification. Despite their zero-shot nature, the LLMs show competitive and, in some cases, superior performance to traditional methods. The study investigates the impact of textual data characteristics and analytical procedures on classification accuracy, finding that linguistic features like lengthy words improve performance, while single-sentence reviews and less structured text documents reduce it. Additionally, the explainability of LLM-generated sentiment classifications is evaluated, with Llama 2 performing the best in terms of understandability, detail, and trustworthiness. The findings enrich the understanding of sentiment analysis, providing valuable insights for marketing researchers and practitioners in the age of Generative AI.The paper "Sentiment Analysis in the Age of Generative AI" by Jan Ole Krugmann and Jochen Hartmann explores the capabilities of Large Language Models (LLMs) in sentiment analysis, a critical task in marketing research. The authors benchmark three state-of-the-art LLMs—GPT-3.5, GPT-4, and Llama 2—against established transfer learning models to assess their performance in sentiment classification. Despite their zero-shot nature, the LLMs show competitive and, in some cases, superior performance to traditional methods. The study investigates the impact of textual data characteristics and analytical procedures on classification accuracy, finding that linguistic features like lengthy words improve performance, while single-sentence reviews and less structured text documents reduce it. Additionally, the explainability of LLM-generated sentiment classifications is evaluated, with Llama 2 performing the best in terms of understandability, detail, and trustworthiness. The findings enrich the understanding of sentiment analysis, providing valuable insights for marketing researchers and practitioners in the age of Generative AI.