This study examines the potential of large language models for sentiment analysis in marketing. Using the empirical setting of online customer reviews, we further explore implications for prediction of review helpfulness. Relying on a dataset of 28,900 product reviews from a consumer platform and an experiment with N = 1063 participants, we find that the LLM’s accuracy in assessing intended meaning (as in the star-rating) in customer-written text depends on the degree of emotionality, as in purchases of hedonic (vs. utilitarian) goods. We further demonstrate that deviations between LLM classification and original star rating predict lower review helpfulness. This effect is mediated by the deviation of human readers’ assumption on the intended star rating from the actual star rating and moderated by the degree of information asymmetry before the purchase; that is, a greater deviation between the LLM classification and the original star rating indicates lower review helpfulness for search goods than for experience goods.
Winter, Christian G. H., Zacharias, Nicolas A., Hartwig, Mattis. Using LLMs as sentiment analyzers to predict review helpfulness: first insights to open the black box. // Marketing Letters. – 2026. – DOI: 10.1007/s11002-026-09824-7. – URL: http://link.springer.com/openurl/fulltext?id=doi:10.1007/s11002-026-09824-7
Winter, Christian G. H, Zacharias, Nicolas A, Hartwig, & Mattis (2026). Using LLMs as sentiment analyzers to predict review helpfulness: first insights to open the black box. Marketing Letters. https://doi.org/10.1007/s11002-026-09824-7
Winter, et al. “Using LLMs as sentiment analyzers to predict review helpfulness: first insights to open the black box.” Marketing Letters, 2026. doi:10.1007/s11002-026-09824-7.
@article{Winter2026,
title = {Using LLMs as sentiment analyzers to predict review helpfulness: first insights to open the black box},
author = {Winter and H., Christian G. and Zacharias and A., Nicolas and Hartwig and Mattis},
journal = {Marketing Letters},
year = {2026},
doi = {10.1007/s11002-026-09824-7},
url = {http://link.springer.com/openurl/fulltext?id=doi:10.1007/s11002-026-09824-7}
}
The rising popularity of digital wealth management platforms (DWPs) has transformed how retail investors manage their portfolios. This study examines key factors related to the successful adoption of DWPs and their outcomes, using an...
Much academic research is focused on the application of predictive data, forecasts, and models to inform practical marketing decision-making. Such work offers powerful insights to marketers directing their firms and interacting with the...
Migrant tourism entrepreneurs (MTEs) are emerging as important actors in rural destination branding. However, the mechanisms through which they shape brand formation through everyday practices remain insufficiently understood. Drawing...
Authenticity drives customer decision-making and firm success, yet research remains fragmented due to the diversity of conceptualizations, mediators and outcomes, and empirical contexts investigated. Utilizing the entity–referent...
Signaling theory predicts that communication, such as by CEOs, might complement observable environmental engagement by a firm, by reducing information asymmetry. Yet it remains unclear whether firms with stronger environmental...