Introduction Method Results Conclusion

4 downloads 212251 Views 758KB Size Report
Using the Big Five for customised advertising on Facebook. Matz, S., Popov, V., Kosinski, M. & Stillwell, D. Sandra Matz (PhD candidate) email: [email protected].
Using the Big Five for customised advertising on Facebook Matz, S., Popov, V., Kosinski, M. & Stillwell, D.

Introduction

Method

Results

Research question

Target group selection

Key metrics: 6,433,120 users, 10348 clicks, 390 conversions Overall CTR: 0.16%; Overall ROI: 334% (Return-on-Investment) Results of factorial ANOVA: 1) H1: Non-sig. interaction effect of target group × advertisement style on CTR (F(1,16) = 0.03, p = .861, ω = .04) 2) H2: Sig. interaction effect of target group × advertisement style on ROI (F(1,16) = 5.67, p = .029, ω = .20)

 Effectiveness of personality-tailored advertising messages demonstrated in lab studies [1,2,3]  However, questionnaire-based nature of personality assessment has largely prohibited its application in real life marketing contexts.  Applying a Big Data approach of predicting personality of Facebook users, we test whether and how personality-tailored advertising can be used to increase the effectiveness of online marketing.

Experimental design Advertising campaign:  Promotion of an online beauty retailer  Examined personality dimension: Extraversion Manipulations of: 1) Advertisement style: extraverted vs. introverted 2) Target group: extraverted vs. introverted

Target group selection based on myPersonality database:    

Contains FB profile information and Big Five results of > 6,000,000 users. Over 36,000,000 User-Like pairs Allows for the extraction of average personality profiles for each “Like” 10 Likes with the highest and respectively lowest z-scores on Extraversion used to target Facebook users Extraverted Likes

Introverted Likes

 Socializing  Entourage  Partying

 The Silmarillion  Star Trek  Computer programming

Additional criteria: UK-based women between 18 and 40

Advertisement design Beauty doesn’t have to shout

Dance like nodgerg one’s watching (but they totally are)

 2 × 2 between-subjects design

Hypotheses H1: Higher click-through-rate (CTR) for conditions in which the advertisement characteristics corresponded to the users Extraversion trait H2: Higher Return-on-Investment (ROI) for conditions in which the advertisement characteristics corresponded to the users Extraversion trait

Conclusion Graphics designers created 5 introverted and 5 extraverted ads based on: (1) General description of Extraversion dimension (2) Semantic analysis of extraverted vs. introverted Facebook users’ status updates  Ads were validated with personality psychologists and laymen

 Tailoring messages to consumer personality increases effectiveness of digital advertising  However, the fact that there is an effect on ROI and conversion rates but not on CTR seems surprising  Future research: Effect of elaboration processes underlying CTR and conversions. Clicking on an ad might be an automatic process whereas buying is likely to involve elaboration efforts.

(1 ) Hirsh, J. B., Kang, S. K., & Bodenhausen, G. V. (2012). Personalized Persuasion: Tailoring persuasive Appeals to Recipient’s Personality Traits. Psychological Science, 23(6) 578-581. (2) Moon, Y. (2002). Personalization and Personality: Some Effects of Customizing Message Style Based on Consumer Personality. Journal of Consumer Psychology, 12(4), 313-326. (3) Wheeler, S. C., Petty, R. E., & Bizer, G. Y. (2005). Self-schema matching and attitude change: Situational and dispositional determinants of message elaboration. Journal of Consumer Research, 31, 787-797

www.psychometrics.cam.ac.uk

Sandra Matz (PhD candidate) email: [email protected] Department of Psychology