Image generated with Nightcafe. Prompt: "A texture of multiple colorful synth waves with gold accents."
See your stimuli move a little (or a lot!) using the RAISE methodology.
This is a Web version of the Companion Appendix for RAISE: A New Method to Develop Experimental Stimuli for Advertising Research with Image Generative Artificial Intelligence, developed by César Zamudio, Jamie Grigsby, and Meg Michelsen, and published in the Journal of Advertising. Questions? Feel free to contact us!
The RAISE method can manipulate fine body movement. We focus on inducing a smile. Research shows that observing a smile can influence consumer perceptions. While the physical characteristics of a smile must sometimes be tightly controlled (e.g., measuring a Duchenne smile: Ilicic, Kulczynski, and Baxter, 2018), in other situations, the mere presence, or the intensity, of a smile is sufficient for experimental manipulation.
We focus on this latter approach – an example is Chang et al. (2021), who manipulate smile intensity. In our case, we will manipulate the presence or absence of a smile. RAISE can be applied to manipulate smile presence. Similar to the services marketing and waiter gender example, the process begins with an initial prompt indicating the desired features of Stimulus A –in this case, the smiling condition:
We focus on this latter approach – an example is Chang et al. (2021), who manipulate smile intensity. In our case, we will manipulate the presence or absence of a smile. RAISE can be applied to manipulate smile presence. Similar to the services marketing and waiter gender example, the process begins with an initial prompt indicating the desired features of Stimulus A –in this case, the smiling condition:
Prompt: An Asian office clerk is standing, wearing a white suit and a black blouse. She has short hair. She has a smiling look. The background is white. Negative terms: Sober.
The desired image is generated. Per the RAISE methodology, Stimulus B is then generated conditional on the image of Stimulus A, a suitable image strength (40%), and an updated text prompt:
Below is a handy summary card outlining the process you just learned:
Summary card to create a woman smiling and serious. Feel free to save and share!
As can be seen, the presence or absence of a smile is evident across stimuli. However, even though the text prompt required a white background, our Stimulus A (and, thus, B as well) instead depicts a blurred background. Head to the Technical Details section for more information on how to refine stimuli backgrounds.
Ready to learn more?
Feel free to browse our gallery of examples with full tutorials, and the technical details section to learn the finer points of generating visual experimental stimuli using the RAISE methodology.