College application essays in an era of machine reading
We utilize a corpus of 240,000 admissions essays submitted by 60,000 applicants to the University of California in November 2016 to measure the relationship between the content of application essays, reported household income, and standardized test scores (SAT) at scale. We find that essays have a stronger correlation to reported household income than SAT scores.
What role does course consideration play in college students' pathways?
Using digital trace data to observe this process at scale at a private research university, together with qualitative student interviews, we provide a novel empirical study of course consideration as part of the course selection process.
What good is a MOOC?
As low-status academic offerings purveyed by high-status institutions, massively open online courses (MOOCs) are ambiguous credentials. In interviews with 60 people who devoted substantial time to at least one MOOC between 2014-2017, we find that people use MOOCs to build skills for application at work and home, build relationships, navigate life transitions, and enhance formal presentations of self.
How is self-confidence related to the gender wage gap in STEM?
Is there a gender pay gap among graduates in some science, technology, engineering, and math (STEM) fields? Women and men have near-identical human capital at college exit, but cultural beliefs about men as more fit for STEM professions than women may lead to self-beliefs that affect pay. We hypothesized that women and men would be paid differently upon college exit, and that gender gaps in self-beliefs about one’s abilities, or self-efficacy, would correspond to this difference. Using data from a three-wave longitudinal study of graduates of engineering programs from 2015–2017, we find a confidence gap that aligns with a gender pay gap. Overall, these findings point to the role that cultural beliefs play in creating gender disparities among STEM degree-holders.
A federal policy proposal to assist adult learners in the wake of the pandemic
The US federal government has serially called upon colleges and universities to assist the nation in moments of national crisis. This brief outlines an ambitious plan to enlist the postsecondary sector in helping millions of Americans get back to work in the wake of the pandemic and equip them for ongoing prosperity in a highly dynamic economy.
What happened in college classrooms in the wake of COVID?
The authors attended discussions and interviewed instructors in Stanford’s Computer Science Department to identify successful approaches and problem areas in the rapid transition to online learning.
What is merit?
The authors combine qualitative and quantitative techniques to observe how 55,016 applicants to a highly selective public university narrate their cases for admission.
What's in a course review?
College and university students submit millions of course reviews each year, yet these instruments are only rarely leveraged for scientific inquiry. This paper examines 11,255 reviews submitted to computer science courses to illustrate how such inquiry might proceed.
Can reinforcement models improve learning?
We show that a Reinforcement Learning (RL) model produces better learning gains using fewer educational activities than a linear assignment condition, and produces similar learning gains to a self-directed condition using fewer educational activities and with lower dropout rates.
Can AI improve holistic review?
We use a variety of text classification algorithms on a large corpus of college admissions essays to model the extent and ways that AI might inform human evaluation.
Intriguing relationships between video pacing, course persistence and academic achievement.
What is a university?
An appraisal of universities as distinctive institutions, on three dimensions.
Are word vector evaluation methods biased?
Widely used word vector evaluation methods are biased towards the language of high income students. This problematically suggests that some students’ language is closer to the “ground truth” than others.
How are student enrollment decisions best modeled with large-scale datasets?
Using ten years of anonymized transcript data, the authors use a probabilistic modeling approach to model and predict student choices. This allows us to capture the complex relationships between courses, such as the tendency of some courses to serve as prerequisites for others without a formal requirement.
Which courses, and why?
We offer an analytic toolkit, called Via, which transforms commonly available enrollment data into formal graphs that are amenable to interactive visualizations and computational exploration. The tool is intended for a variety of stakeholders: college students, instructors, and administrators.
How do students choose their courses?
Drawing on preliminary empirical research involving a web-based course exploration and planning tool in use at a private U.S. research university, we develop a conceptual framework for studying college students’ academic choices.
How does a course planning tool affect college students’ grades?
We conducted a large-scale field experiment in which all undergraduates were randomly encouraged to use Carta, a web-based course planning tool. We found that use of the platform lowered students’ GPA by 0.28 standard deviations on average.
How can learning analytics systems improve online education?
Our study suggests new design goals for learning analytics systems, the importance of real-time analytics to many instructors, and the value of flexibility in data selection and aggregation for an instructor when working with an analytics system.
What do universities owe the future?
What does it mean to use student data responsibly?
The higher education community must set the table and invite others to help us define ethical practice and responsible use of student data in the rapidly changing digital world of the academic enterprise.
How does online learners' course engagement evolve?
How do we pivot from rule compliance to ethical proaction?