Research

“Influencing Identities: Creator Identity and Character Representation in Children’s Literature”

with Anjali Adukia, Emileigh Harrison, and Celia Zhu

Abstract

Books convey messages about social values and norms to children, especially through characters that are personally relevant to them. We quantify representation in books that have won or received honorable mentions from the Newbery, Caldecott, or Coretta Scott King awards. We extend the idea of representation from whether people of diverse groups appear to how they are depicted in a book. Using modern techniques in natural language processing and computer vision, we develop metrics to quantify the presence and portrayal of people of diverse groups in children’s books. We apply our metrics to assess how creator identity and award selection criteria influence the supply of representation in children’s books. We find that, conditional on the award, books by Black authors depict darker-skinned characters than books by White authors. Additionally, independent of the award, females are increasingly present in female-authored books over time, whereas their relative lack of presence in male-authored books remains somewhat stable across decades. In terms of depiction, we see that females are portrayed in relational to men, whereas men are portrayed in relation to occupations. Surprisingly, this pattern is consistent across author genders. On the demand side, we find that, conditional on the award, Black purchasers are more likely to purchase books by Black authors than White authors.

“How do we Teach Emotions?”

with Anjali Adukia, Matthew Bonci, Paula Dastres Gallardo, Emileigh Harrison, and Teodora Tsasz

Abstract

The ability to recognize, process, and manage our own emotions, as well as the emotions of others, is a core component of social emotional development, which has powerful long-term implications. Children learn about emotions in part through media such as textbooks and children’s literature. In this study, we apply artificial intelligence tools from the fields of computer vision and natural language processing to analyze the representation of emotions in these media. We find that, while children are exposed to a range of different emotions in the text, the images predominantly depict happy and calm characters. This leaves many emotions without visual models. These patterns hold in different subcollections of our content and are consistent across both time and the identity of the characters expressing the emotion. Even within a single page, we see large discrepancies between the emotions shown in text from those shown in images. Frequently, when negatively-valenced emotions are displayed in the text, children are presented with images on the same page showing happy and calm characters. Using micro-level book purchase data, we investigate the extent to which this imbalance in the representation of emotions in images could be due to demand-side factors. While we do observe that consumers prefer books with exclusively happy and calm characters on their covers, the analysis does not suggest that the imbalance is exclusively a supply-side response to consumer demand.