Predicting the Personal Appeal of Marketing Images Using Computational Methods

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).     

Sense of agency in continuous action: Assistance-induced performance improvement is self-attributed even with knowledge of assistance

In a task involving continuous action to achieve a goal, the sense of agency increases with an improvement in task performance that is induced by unnoticed computer assistance. This study investigated how explicit instruction about the existence of computer assistance affects the increase of sense of agency that accompanies performance improvement. Participants performed a continuous action task in which they controlled the direction of motion of a dot to a goal by pressing keys. When instructions indicated the absence of assistance, the sense of agency increased with performance improvement induced by computer assistance, replicating previous findings. Interestingly, this increase of sense of agency was also observed even when instructions indicated the presence of assistance. These results suggest that even when a plausible cause of performance improvement other than one’s own action exists, the improvement can be misattributed to one’s own control of action, resulting in an increased sense of agency.     

Computer simulation through an error-statistical lens

After showing how Deborah Mayo’s error-statistical philosophy of science might be applied to address important questions about the evidential status of computer simulation results, I argue that an error-statistical perspective offers an interesting new way of thinking about computer simulation models and has the potential to significantly improve the practice of simulation model evaluation. Though intended primarily as a contribution to the epistemology of simulation, the analysis also serves to fill in details of Mayo’s epistemology of experiment.     

How extraverted is honey.bunny77@hotmail.de? Inferring personality from e-mail addresses

Computer mediated communication (CMC) plays a rapidly growing role in our social lives. Within this domain, e-mail addresses represent the thinnest slice of information that people receive from one another. Using 599 e-mail addresses of young adults, their self-reported personality scores and the personality judgments of 100 independent observers, it was shown that personality impressions based solely on e-mail addresses were consensually shared by observers. Moreover, these impressions contained some degree of validity. This was true for neuroticism, openness, agreeableness, conscientiousness, and narcissism but not for extraversion. Level of accuracy was explained using lens model analyses: Lay observers made broad use of perceivable e-mail address features in their personality judgments, features were slightly valid and observers were sensitive to subtle differences in validity between cues. Altogether, even the thinnest slice of CMC—the mere e-mail address—contains valid information about the personality of its owner.     

Bootstrapping cognition from behavior-a computerized thought experiment

We show that simple perceptual competences can emerge from an internal simulation of action effects and are thus grounded in behavior. A simulated agent learns to distinguish between dead ends and corridors without the necessity to represent these concepts in the sensory domain. Initially, the agent is only endowed with a simple value system and the means to extract low-level features from an image. In the interaction with the environment, it acquires a visuo-tactile forward model that allows the agent to predict how the visual input is changing under its movements, and whether movements will lead to a collision. From short-term predictions based on the forward model, the agent learns an inverse model. The inverse model in turn produces suggestions about which actions should be simulated in long-term predictions, and long-term predictions eventually give rise to the perceptual ability.     

A Critique of Positive Responsibility in Computing

It has been claimed that (1) computer professionals should be held responsible for an undisclosed list of "undesirable events" associated with their work and (2) most if not all computer disasters can be avoided by truly understanding responsibility. Programmers, software developers, and other computer professionals should be defended against such vague, counterproductive, and impossible ideals because these imply the mandatory satisfaction of social needs and the equation of ethics with a kind of altruism. The concept of social needs is debatable with no one possessing the authority to impose their version of them. Similarly, the notion of "positive responsibility" is difficult to apply, does not effectively change computing practice, and confuses good (i.e., efficient) computer engineering with good (i.e. moral) computer engineering.     

Playing counter-strike versus running: The impact of leisure time activities and cortisol on intermediate-term memory in male students

The everyday life of students is characterized by hours of learning in order to pass exams. After learning they tend to opt for an occupation that provides them with a great deal of entertainment. It is obvious that it would be advantageous if the chosen activity had a positive impact on memory consolidation. Due to the circumstance that such activities can lead to stress and that memory is affected by stress we wanted to look at these coherences. We examined the effect of two different common leisure time activities on cortisol and memory to be able to formulate recommendations for society. For this purpose, a group was tested before and after playing a violent computer game while the second group was tested before and after running. In addition, a control group was set up. Salivary cortisol was measured at the beginning, during, and at the end of the experiment.Our data demonstrates that running increases cortisol levels and, performed immediately after a learning period, facilitates memorization of neutral information. In contrast, playing a violent computer game tends to impair memorization.The results of the present study have practical implications for the choice of recreational activities in the context of learning.     

Dream engineering: Simulating worlds through sensory stimulation

We explore the application of a wide range of sensory stimulation technologies to the area of sleep and dream engineering. We begin by emphasizing the causal role of the body in dream generation, and describe a circuitry between the sleeping body and the dreaming mind. We suggest that nearly any sensory stimuli has potential for modulating experience in sleep. Considering other areas that might afford tools for engineering sensory content in simulated worlds, we turn to Virtual Reality (VR). We outline a collection of relevant VR technologies, including devices engineered to stimulate haptic, temperature, vestibular, olfactory, and auditory sensations. We believe these technologies, which have been developed for high mobility and low cost, can be translated to the field of dream engineering. We close by discussing possible future directions in this field and the ethics of a world in which targeted dream direction and sleep manipulation are feasible.     

Intrinsic cognitive models

Theories concerning the structure, or format, of mental representation should (1) be formulated in mechanistic, rather than metaphorical terms; (2) do justice to several philosophical intuitions about mental representation; and (3) explain the human capacity to predict the consequences of worldly alterations (i.e., to think before we act). The hypothesis that thinking involves the application of syntax‐sensitive inference rules to syntactically structured mental representations has been said to satisfy all three conditions. An alternative hypothesis is that thinking requires the construction and manipulation of the cognitive equivalent of scale models. A reading of this hypothesis is provided that satisfies condition (1) and which, even though it may not fully satisfy condition (2), turns out (in light of the frame problem) to be the only known way to satisfy condition (3).     

Cognitive determinants of the success of inventors: Complex problem solving and deliberate use of divergent and convergent thinking

With reference to Henderson's (2004) assumption that inventors are “expert problem solvers”, we studied the ability of inventors to solve complex problems (CPS) using a sample of 46 German inventors. The participants had to use FSYS 2.0, a computer-simulated microworld. Additionally, we assessed metacognition, in particular the participants' ability to make deliberate use of divergent and convergent thinking. This ability was expected to be an important skill involved in solving complex problems (Dörner, Kreuzig, Reither, & Stäudel, 1983). We assumed a positive correlation between the individual success of inventors (number of granted and marketed patents) and CPS abilities. Controllability of divergent and convergent thinking turned out to be a predictor of the success of inventors and allowed us to identify the top 10% performers. Oddly however, the best problem solvers were inventors with exactly one granted patent. Data from a posteriori conducted interviews help explaining the results.