Linguistic Indicators of the Growth Mindset

<a href="https://embed.stanford.edu/iframe/?url=https%3A%2F%2Fpurl.stanford.edu%2Fqd944cz3242" class="su-underline">Show Content</a>

Abstract/Contents

Abstract: We use data from the synergistic mindsets intervention to find how language in student essays might correlate with self-reported stress levels n= 2000. We use word count based approaches, topic modeling, and word embedding based methods to find the linguistic patterns that correlate with stress levels. Our results show that in comparison to students who cope poorly with stress, those that cope well make greater use of negative over positive emotions, past and present tense over future tense, higher cognitive processing words, and more action over bodily sensation words in their writing. Our text classification models predict stress appraisals with an accuracy of 68 ± 0.4%. However, the length of the text students write is a major confounder in all our results. We discuss the text length as a confounder along with our other qualitative findings in relation to previous linguistic studies of mindfulness and stress.

Author	Kamath, Akshatha
Advisor	Demszky, Dora

DOI	https://doi.org/10.25740/qd944cz3242
Location	https://purl.stanford.edu/qd944cz3242

Use and reproduction: User agrees that, where applicable, content will not be used to identify or to otherwise infringe the privacy or confidentiality rights of individuals. Content distributed via the Stanford Digital Repository may be subject to additional license and use restrictions applied by the depositor.
License: This work is licensed under a Creative Commons Attribution Non Commercial 4.0 International license (CC BY-NC).

Preferred citation: Kamath, A. and Demszky, D. (2023). Linguistic Indicators of the Growth Mindset. Stanford Digital Repository. Available at https://purl.stanford.edu/qd944cz3242. https://doi.org/10.25740/qd944cz3242.

Education Data Science (EDS) Capstone Projects, Graduate School of Education

Loading usage metrics...