Skip to main content

A Data Science Analysis

The image on the left shows a confusion matrix that demonstrates that the computer can correctly guess the positionality of the author with a 60% accuracy, indicating that positionality likely has an influence on the portrayal of mental health in literature. The right image shows the sentiment around mental health terms by positionality, white male seeming to be more positive than both black and white female.
math project image.jpg
Class of 2023
Francophone Studies

Alexandra Hill '23, born and raised in Los Angeles, California, is a triple major in English, French, and mathematics, with a minor in statistics. Her passion for mental health is a keystone for much of her academia; she presented her research on mental health accessibility in writing centers at a national conference in 2021, and her three senior honors projects each respectively analyze mental health in literature in unique ways.


In this research project, I analyzed and visualized the interaction between positionality and mental health portrayal in literature utilizing data science techniques coding with R. Specifically, I looked at about 40 YA fiction novels dealing with mental health issues and comparing those with black characters/authors to those with white characters/authors, as well as looking at differences in gender and the impacts of intersectionality. I used data science and textual analysis techniques to find statistical differences between the novels based on positionality and to make meaning from the data gathered, interpreting the implications of my findings on representation of positionalities in mental health literature. For example, I found a correlation between female positionality and the lack of a parental figure -- fathers absent from the black female novels and mothers absent from the white female novels. I am continuing this research throughout the year, continuing to discover other significant interactions between positionality and mental health portrayal in literature.