English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

This report analyzes the potential for large language models (LLMs) toexpedite accurate replication and generalization of published research aboutmessage effects in marketing. LLM-powered participants (personas) were testedby replicating 133 experimental findings from 14 papers containing 45 recentstudies published in the Journal of Marketing. For each study, the measures,stimuli, and sampling specifications were used to generate prompts for LLMs toact as unique personas. The AI personas, 19,447 in total across all of thestudies, generated complete datasets and statistical analyses were thencompared with the original human study results. The LLM replicationssuccessfully reproduced 76% of the original main effects (84 out of 111),demonstrating strong potential for AI-assisted replication. The overallreplication rate including interaction effects was 68% (90 out of 133).Furthermore, a test of how human results generalized to different participantsamples, media stimuli, and measures showed that replication results can changewhen tests go beyond the parameters of the original human studies. Implicationsare discussed for the replication and generalizability crises in socialscience, the acceleration of theory building in media and marketing psychology,and the practical advantages of rapid message testing for consumer products.Limitations of AI replications are addressed with respect to complexinteraction effects, biases in AI models, and establishing benchmarks for AImetrics in marketing research.

Using Large Language Models to Create AI Personas for Replication,  Generalization and Prediction of Media Effects: An Empirical Test of 133  Published Experimental Research Findings