Using AI predicted personality to enhance advertising effectiveness

Shumanov, M, Cooper, Holly and Ewing, Michael 2021, Using AI predicted personality to enhance advertising effectiveness, European Journal of Marketing, pp. 1-20, doi: 10.1108/EJM-12-2019-0941.

Attached Files
Name Description MIMEType Size Downloads

Title Using AI predicted personality to enhance advertising effectiveness
Author(s) Shumanov, M
Cooper, HollyORCID iD for Cooper, Holly orcid.org/0000-0003-0608-5239
Ewing, MichaelORCID iD for Ewing, Michael orcid.org/0000-0002-2260-2761
Journal name European Journal of Marketing
Start page 1
End page 20
Total pages 20
Publisher Emerald
Place of publication Bingley, Eng.
Publication date 2021-01-01
ISSN 0309-0566
Keyword(s) Personality
Advertising
Artificial intelligence
Machine learning
Personality traits
Summary PurposeThe 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/approachA 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.FindingsThis 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/implicationsThis 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 implicationsBuilding 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/valueAlthough 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.
Notes In Press
Language eng
DOI 10.1108/EJM-12-2019-0941
Indigenous content off
Field of Research 15 Commerce, Management, Tourism and Services
HERDC Research category C1 Refereed article in a scholarly journal
ERA Research output type C Journal article
Persistent URL http://hdl.handle.net/10536/DRO/DU:30150447

Document type: Journal Article
Collections: Faculty of Business and Law
PVC's Office - Business and Law
Connect to link resolver
 
Unless expressly stated otherwise, the copyright for items in DRO is owned by the author, with all rights reserved.

Versions
Version Filter Type
Citation counts: TR Web of Science Citation Count  Cited 0 times in TR Web of Science
Scopus Citation Count Cited 0 times in Scopus
Google Scholar Search Google Scholar
Access Statistics: 4 Abstract Views, 2 File Downloads  -  Detailed Statistics
Created: Thu, 29 Apr 2021, 20:02:21 EST

Every reasonable effort has been made to ensure that permission has been obtained for items included in DRO. If you believe that your rights have been infringed by this repository, please contact drosupport@deakin.edu.au.