Affective computational advertising based on perceptual metrics

We present ACAD, an Affective Computational ADvertising framework expressly derived from perceptual metrics. Differing from advertising methods that either ignore the emotional nature of (most) programmes and advertisements (ads), or are based on axiomatic rules, our framework incorporates findings from a user study examining the effect of within-programme ad placements on ad perception. A linear programme formulation seeking to achieve (a) genuine ad assessments, and (b) maximal ad recall is then proposed. The effectiveness of the framework is confirmed via a validation user study, where ACAD-induced ad placements are found to be optimal with respect to objectives (a) and (b) against competing approaches.