Extracting Consumer Insight from Text: A Large Language Model Approach to Emotion and Evaluation Measurement

2026-02-16

AI Summary

Accurately identifying multidimensional consumer emotions and key marketing evaluation constructs in unstructured text remains a critical challenge in marketing research. This work proposes Linguistic eXtractor (LX), a large language model fine-tuned on consumer-generated text to jointly recognize 16 consumption-related emotions alongside four core evaluative constructs: trust, commitment, recommendation, and affect. LX achieves high-precision joint modeling of emotions and evaluations for the first time and reveals that certain emotions can directly influence purchase behavior independent of explicit ratings. Empirical evaluations demonstrate that LX attains a macro F1-score of 81% on open-ended survey responses and exceeds 95% accuracy on Amazon and Yelp reviews. The study further provides a free, no-code web application interface, underscoring both its methodological innovation and practical utility for researchers and practitioners.

Technology Category

• Natural Language Processing: Interpretability, Analysis, and Evaluation of NLP Models
• Machine Learning: Large Multimodal Models (LMMs)
• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval

Application Category

• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

Accurately measuring consumer emotions and evaluations from unstructured text remains a core challenge for marketing research and practice. This study introduces the Linguistic eXtractor (LX), a fine-tuned, large language model trained on consumer-authored text that also has been labeled with consumers' self-reported ratings of 16 consumption-related emotions and four evaluation constructs: trust, commitment, recommendation, and sentiment. LX consistently outperforms leading models, including GPT-4 Turbo, RoBERTa, and DeepSeek, achieving 81% macro-F1 accuracy on open-ended survey responses and greater than 95% accuracy on third-party-annotated Amazon and Yelp reviews. An application of LX to online retail data, using seemingly unrelated regression, affirms that review-expressed emotions predict product ratings, which in turn predict purchase behavior. Most emotional effects are mediated by product ratings, though some emotions, such as discontent and peacefulness, influence purchase directly, indicating that emotional tone provides meaningful signals beyond star ratings. To support its use, a no-code, cost-free, LX web application is available, enabling scalable analyses of consumer-authored text. In establishing a new methodological foundation for consumer perception measurement, this research demonstrates new methods for leveraging large language models to advance marketing research and practice, thereby achieving validated detection of marketing constructs from consumer data.

Problem

• consumer emotion
• evaluation measurement
• unstructured text
• marketing research
• consumer insight

Innovation

• Large Language Model
• Consumer Emotion Measurement
• Fine-tuned LLM
• Marketing Construct Detection
• Text-based Consumer Insight