The Effect of Ad Image's Sentiment Scores and Mobile Device Attributes on Mobile Ad Response Behavior

Abstract

Using a state-of-the-art image processing algorithm applied to mobile ad creative and a unique dataset on technology features for mobile platforms, we examine how visual sentiment of mobile ad images, mobile device attributes that aid visual communication, and their interactions influence consumers’ mobile ad responses. Our results show that an increase in mobile ads’ valence and arousal levels by one-unit enhances the instantaneous probability of consumers’ mobile ad response by 2.4% and 1.6%, respectively. An increase in mobile devices’ display size and pixel density by 1 in and 1%, respectively, decreases the probability of mobile ad response by 42.6% and 0.7%. Interestingly, display size positively moderates the effect of arousal, while pixel density positively moderates the effect of valence on consumers’ mobile ad responses. This study contributes to the IS and marketing literature by examining the role of ad images’ visual sentiment scores such as valence and arousal, device-specific attributes on mobile display, such as screen display size and pixel density, and their interaction effects on consumers’ mobile ad response behaviors. Importantly, the application of computationally efficient image sentiment processing sheds new light on the extant mobile advertising and marketing literature both from a methodological and findings perspective.