Visual-based social media are growing exponentially and have become an integrated part of the customer engagement strategy of many brands. Prior work points to the textual message content as a driver of customer engagement behavior. So far, little is known about the impact of visual message content, specifically visual emotional and informative appeals. We extract emotional and informative appeals from Instagram posts using machine learning models and use a Negative Binomial model to explain customer engagement. We test our model on 46.9 K Instagram posts from 59 brands in six sectors. Our results show that visual emotional and informative appeals encoded in brand-generated content influence customer engagement in terms of likes and comments. Specifically, we demonstrate that positive high and negative low arousal images drive customer engagement. Informative appeals do not drive customer engagement with the exception of informative brand-related appeals. These findings help brand managers in developing an effective customer engagement strategy on visual social media.

Brand-related user posts on social networks are growing at a staggering rate, where users express their opinions about brands by sharing multimodal posts. However, while some posts become popular, others are ignored. In this paper, we present an approach for identifying what aspects of posts determine their popularity. We hypothesize that brandrelated posts may be popular due to several cues related to factual information, sentiment, vividness and entertainment parameters about the brand. We call the ensemble of cues engagement parameters. In our approach, we propose to use these parameters for predicting brand-related user post popularity. Experiments on a collection of fast food brand-related user posts crawled from Instagram show that: visual and textual features are complementary in predicting the popularity of a post; predicting popularity using our proposed engagement parameters is more accurate than predicting popularity directly from visual and textual features; and our proposed approach makes it possible to understand what drives post popularity in general as well as isolate the brand specific drivers.

No abstract