Making Sense of Customer Voices on Facebook Business Pages
There are more than 60 million business pages on Facebook, through which companies seek to market their products and engage their customers. These social media business pages also allow customers to publish content. Researchers at the University of Minnesota set out to understand what customers say about businesses, and how it impacts customer engagement.
Many companies use social media platforms to engage with customers and encourage user-generated content about their products and services. For this study, University of Minnesota researched analyzed 12,000 user-generated posts from the Facebook business pages of 39 Fortune-500 companies across several different industries to understand (1) what users post on Facebook business pages, and (2) how the sentiment and content characteristics of a post affect engagement, measured as the number of likes and comments it receives.
The analysis demonstrates that negative posts are significantly more prevalent than positive posts, and negative posts also tend to attract more likes and more comments than positive posts. Importantly, engagement depends not only on the valence of a post but also on the specific post content. The researchers observed three types of customer complaints related to product and service quality, money issues, and corporate social responsibility issues. Social complaints receive more likes, but fewer comments, than quality or money complaints. Overall, the findings suggest that customers perceive Facebook business pages as a new channel to communicate directly with businesses and to receive customer service.
Many companies marched into the new territory of social media marketing with limited understanding of user behavior in this context. This study reveals the practical challenges of managing Facebook business pages as a new channel of interacting with customers, and highlights the need to explore effective response strategies to manage customer complaints and other service requests on social media.
Methods & Tools
- advanced econometric analyses, lab and online experiments, text mining
- Python, Stata, MySQL