Using AI predicted personality to enhance advertising effectiveness

Abstract

Purpose

The purpose of this study is twofold: first to demonstrate the application of an algorithm using contextual data to ascertain consumer personality traits; and second to explore the factors impacting the relationship between personality traits and advertisement persuasiveness.

Design/methodology/approach

A mixed-method approach that comprises two distinct yet complementary studies. The first uses quantitative methods and is based on a sample of 35,264 retail banking customers. Study 2 explores the findings that emerge from Study 1 using qualitative methods.

Findings

This paper finds that matching consumer personality with congruent advertising messages can lead to more effective consumer persuasion for most personality types. For consumers who exhibit neurotic personality traits, ameliorating perceived risks during purchasing and providing cues for social acceptance and goal attainment are important factors for advertising effectiveness. These factors also had a positive impact on the purchasing behaviour of extroverted consumers.

Research limitations/implications

This research focusses on understanding purchasing behaviour based on the most dominant personality trait. However, people are likely to exhibit a combination of most or even all of the Big Five personality traits.

Practical implications

Building on advances in natural language processing, enabling the identification of personality from language, this study demonstrates the possibility of influencing consumer behaviour by matching machine inferred personality to congruent persuasive advertising. It is one of the few studies to use contextual instead of social media data to capture individual personality. Such data serves to capture an authentic rather than contrived persona. Further, the study identifies the factors that may moderate this relationship and thereby provides an explanation of why some personality traits exhibit differences in purchasing behaviour from those that are anticipated by existing theory.

Originality/value

Although the idea that people are more likely to be responsive to advertising messages that are congruent with their personality type has already been successfully applied by advertising practitioners and documented by advertising scholars, this study extends existing research by identifying the factors that may moderate this relationship and thereby provides an explanation why some personality traits may exhibit differences in purchasing behaviour from those that are anticipated by existing theory.

Citation

Shumanov, M., Cooper, H. and Ewing, M. (2022), "Using AI predicted personality to enhance advertising effectiveness", European Journal of Marketing, Vol. 56 No. 6, pp. 1590-1609. https://doi.org/10.1108/EJM-12-2019-0941