Predicting the Personal Appeal of Marketing Images Using Computational Methods

Abstract

Images play a central role in digital marketing. They attract attention, trigger emotions, and shape consumers' first impressions of products and brands. We propose that the shift from one-to-many mass communication to highly personalized one-to-one communication requires an understanding of image appeal at a personal level. Instead of asking "How appealing is this image?" we ask "How appealing is this image to this particular consumer?" Using the well-established five-factor model of personality, we apply machine learning algorithms to predict an image's personality appeal-the personality of consumers to which the image appeals most-from a set of 89 automatically extracted image features (Study 1). We subsequently apply the same algorithm on new images to predict consequential outcomes from the fit between consumer and image personality. We show that image-person fit adds incremental predictive power over the images' general appeal when predicting (a) consumers' liking of new images (Study 2) and (b) consumers' attitudes and purchase intentions (Study 3).

Identification of Speech Characteristics to Distinguish Human Personality of Introversive and Extroversive Male Groups

“…The digital footprints people leave on online sites can be vigorously used to customize advertisement for each individual while they are online. A recent study by Dr. Sandra Matz at Columbia Business School demonstrated that extroverted individual preferred simple images and images that featured people, while more open-minded individuals favored pictures with no people and with cool colors like blue and black [1]. Therefore, capturing a customer's personality and emotions will eventually shape the advertisement industry to a level unprecedented so far.…”

Towards a new framework of personalized psychological interventions to improve intergroup relations and promote peace

“…The most challenging question when tackling the issue of personalizing intergroup interventions is: what are the key mechanisms that would enable us to match individual difference parameters to the most effective intervention? Relying mainly on evidence from persuasion literature (Haddock, Maio, Arnold, & Huskinson, ; Hirsh et al, ; Moon, ) and some very initial evidence from the more recent digital mass persuasion literature (Kosinski, Matz, Gosling, Popov, & Stillwell, ; Matz, Kosinski, Nave, & Stillwell, ; Matz, Segalin, Stillwell, Müller, & Bos, ), we suggest two mechanisms: a content‐based mechanism (i.e., level of message congruency) and a needs‐based or motivational mechanism. In addition, we suggest an emotional mechanism, which follows previous conceptualization and research on indirect emotion regulation interventions (Halperin, , ).…”

Automated Visual Content Analysis (AVCA) in Communication Research: A Protocol for Large Scale Image Classification with Pre-Trained Computer Vision Models

“…Investigating the factors influencing likability and shareability of visual social media content, Peng and Jemmott (2018) used automated visual content analysis to analyze food images. Marketing researchers have predicted an image's appeal to consumers based on automatically extracted features such as color, composition, or content (Matz et al, 2019). In political communication, computer vision was applied to detect gestures, facial expressions, and emotions in presidential candidates (Joo et al, 2019) or the political ideology of legislators (Xi et al, 2020).…”

“…Communication historians can find AVCA useful in exploring -for instance, in an inductive fashion, propaganda posters as collected by the Washington State University 16 and compare their visual attributes (e.g., color, composition, content; Matz et al, 2019) to posters of more recent campaigns.…”