Understanding the demographics of users of online social networks has important applications for health, marketing, and public messaging. Whereas most prior approaches rely on a supervised learning approach, in which individual users are labeled with demographics for training, we instead create a distantly labeled dataset by collecting audience measurement data for 1,500 websites (e.g., 50% of visitors to gizmodo.com are estimated to have a bachelor's degree). We then fit a regression model to predict these demographics from information about the followers of each website on Twitter. Using patterns derived both from textual content and the social network of each user, our final model produces an average held-out correlation of .77 across seven different variables (age, gender, education, ethnicity, income, parental status, and political preference). We then apply this model to classify individual Twitter users by ethnicity, gender, and political preference, finding performance that is surprisingly competitive with a fully supervised approach.

Consumer perceptions are important components of brand equity and therefore marketing strategy. Segmenting these perceptions into attributes such as eco-friendliness, nutrition, and luxury enable a fine-grained understanding of the brand’s strengths and weaknesses. Traditional approaches towards monitoring such perceptions (e.g., surveys) are costly and time consuming, and their results may quickly become outdated. Extant data mining methods are unsuitable for this goal, and generally require extensive hand-annotated data or context customization, which leads to many of the same limitations as direct elicitation. Here, we investigate a novel, general, and fully automated method for inferring attribute-specific brand perception ratings by mining the brand’s social connections on Twitter. Using a set of over 200 brands and three perceptual attributes, we compare the method’s automatic ratings estimates with directly-elicited survey data, finding a consistently strong correlation. The approach provides a reliable, flexible, and scalable method for monitoring brand perceptions, and offers a foundation for future advances in understanding brand-consumer social media relationships. Data, as supplemental material, are available at http://dx.doi.org/10.1287/mksc.2015.0968 .

After completing a short form of the Boundary Questionnaire (Appendix A), 17 students with high scores indicative of thin boundaries and 13 students with low scores indicative of thick boundaries participated in a testing session in which they reported their "most recent dream'~ their "most recent daydream ", another "dream that really stands out'~ and another "daydream that really stands out." Dreams and daydreams were rated on three 8-point scales-Bizarreness, Dreamlikeness, and Emotionality-by two independent raters who remained blind to Boundary Questionnaire scores. The dream reports were rated significantly more bizarre, more dreamlike, and more emotional than the daydream reports. In addition, the thin boundaried subjects' reports were significantly more bizarre than the thick boundaried subjects' reports. Indeed, the recent daydreams of subjects with thin boundaries were as bizarre as the recent dreams of those with thick boundaries.

Sensitivity and bias can be manipulated independently on a recognition test. The goal of this fMRI study was to determine whether neural activations associated with manipulations of a decision criterion would be anatomically distinct from neural activations associated with manipulations of memory strength and episodic retrieval. The results indicated that activations associated with shifting criteria (a manipulation of bias) were located in bilateral regions of the lateral cerebellum, lateral parietal lobe, and the dorsolateral prefrontal cortex extending from the supplementary motor area. These regions were anatomically distinct from activations in the prefrontal cortex produced during memory-based retrieval processes (manipulations of sensitivity), which tended to be more medial and anterior. These later activations are consistent with previous studies of episodic retrieval. Determining patterns of neural activations associated with decision-making processes relative to memory processes has important implications for Cognitive Neuroscience, including the use of these patterns to compare memory models in different paradigms.

No abstract