Estimating the Impact of User Personality Traits on Electronic Word-of-Mouth: Text-mining Social Media Platforms
Panos Adamopoulos, Anindya Ghose, and Vilma Todri , 2018, 18-100-01
As users share opinions, choices, and decisions on social media, nurturing positive online word of mouth is a critical aim of marketing activity. In this report, Panos Adamopoulos, Anindya Ghose, and Vilma Todri examine whether personality traits of social media users attenuate or accentuate the effectiveness of WOM. Specifically, using recent advancements in big data and machine-learning techniques to extract information from unstructured textual content, they examine whether and how latent personality characteristics of a user affect purchases of actual products.
Their empirical setting is a social commerce venture launched by American Express on Twitter. The data span all the confirmed transactions over two weeks in 2013, complemented by unstructured data from users’ profiles and timelines. The researchers leverage a novel combination of machine-learning-based text-mining techniques with more conventional econometric methods and a quasi-experiment to disentangle the effects of personality on WOM from correlated user behaviors and homophily.
There is a positive and statistically significant effect of the level of personality similarity between two social media users on the likelihood of a subsequent purchase after exposure to WOM. In particular, exposure to WOM messages from similar users in terms of personality, rather than dissimilar users, increases the likelihood of a post-purchase by 47.58%.
Unraveling the impact of various personality types, the authors find that WOM originating from users who exhibit high levels of agreeableness, conscientiousness, and openness is more likely to be more effective, whereas for users with low levels of conscientiousness or agreeableness the opposite effect is more likely. In addition, introvert users are susceptible to WOM, in contrast to extrovert users. In particular, a WOM message from an extrovert user to an introvert peer increases the likelihood of a subsequent purchase by 71.28%. Finally, WOM originating from users with low levels of emotional range affects similar users whereas for high levels of emotional range increased similarity has usually the opposite effect.
These findings suggest strategies for managers who would like to effectively utilize and engineer WOM.
- To increase sales and spur buzz around their brands, marketers might take action to encourage social media users characterized by distinct personality traits and attributes to generate or disseminate positive WOM messages.
- Marketers might also associate their brands with certain characteristics and attributes or foster particular perceptions that might be more appealing to specific types of personalities of users in social media platforms.
Overall, their analysis demonstrates the value of directly observing WOM instances and extracting knowledge from analyzing granular-level data. Leveraging the abundance of unstructured data of digital communications, they demonstrate the feasibility of such analysis with low cost and at a large scale.
These results have important implications for other parties of the social media ecosystem as well, particularly regarding the monetization of social media and user-generated content. Social media companies, including microblogging platforms, are increasingly moving towards a model of sponsored posts (tweets) in which advertisers can bid based on various targeting criteria. The asymmetric WOM effects across different types of personalities suggest that they can charge different prices to advertisers for sponsored messages based on users’ personality.
Similarly, social media platforms can use the latent personality characteristics of the social media users in order to curate and rank user-generated content more effectively and drive engagement in their platforms. Finally, the latent characteristics of users can also be used to better predict the diffusion of information and products in social media.
Panos Adamopoulos is Assistant Professor of Information Systems and Operations Management, Goizueta Business School, Emory University. Anindya Ghose is Heinz Riehl Professor of Business, Professor of Information, Operations, and Management Sciences, and Professor of Marketing, Stern School of Business, New York University. Vilma Todri is Assistant Professor of Information Systems and Operations Management, Goizueta Business School, Emory University.
- Corporate: FREE
- Academic: FREE
- Subscribers: FREE
- Public: $18.00
3 WAYS to GET CONNECTED
Employees of MSI Member Companies enjoy the benefits of complete online access to content, member conferences and networking with the MSI community.
Qualified academics benefit from a relationship with MSI through access to msi.org, conferences and research opportunities.
The public is invited to enjoy partial access to msi.org content, a free e-newsletter, selected reports and more.