About
Anthony Lising Antonio is an Associate Professor of Education at Stanford University and the Associate Director of the Stanford Institute for Higher Education Research. He is also the founding faculty director of LifeWorks at Stanford, an undergraduate program for integrative learning. His research focuses on stratification and postsecondary access, racial diversity and its impact on students and institutions, student friendship networks, and student development. Antonio holds a PhD in Higher Education from the University of California, Los Angeles, an MA in Education from UCLA, an MS in Mechanical Engineering from Stanford University, and a BS in Mechanical Engineering from the University of California, Berkeley.
Research topics
- Sociology
- Artificial Intelligence
- Political Science
- Computer Science
- Psychology
- Social Science
- Economics
- Law
- Machine Learning
- Social psychology
- Cartography
- History
- Public relations
- Management
- Mathematics
- Accounting
- Epistemology
- Gender studies
- Geography
Selected publications
2025-08-23
articleOpen accessComputational text analysis has grown in popularity among social scientists due to the massive influx of digitized data available to study. However, much of this research disconnects patterns observed in text from information about the original authors. Eliding authorship considerations from sociological analysis of text can potentially lead to claims and assertions of trends that are independent from the social actors, conditions, interactions, and contexts which the text was produced. While text analysis without authorship information can yield reasonable inferences about society, complementing that approach with research that explicitly considers the people producing the text could expand the theoretical and empirical scope of work in this area. In this paper, we adapt perspectives from sociolinguistics and explicitly consider categorical identity markers of authors and geography as foundational axes of variation in textual data. We explore these dimensions in a large corpus of college admissions essays (n = 254,820 essays submitted by 83,538 applicants) and metadata about applicant identity, including the ZIP code of their high school. After generating features of the essays using computational methods, we find that author identity markers, such as gender, parental education, and socioeconomic status are highly salient. We also find that ZIP code level socioeconomic measures are extremely correlated with the writing style and content of local applicants. We also find that individuals whose personal identities are spatially unique–that is, demographically different from others in their immediate content–were most likely to be misclassified by our models, indicating that writing is influenced both socially and spatially. This work clarifies how authorship characteristics, like identity and spatial context, constrain the breadth of what we write and how we write by showing strong alignment between text and authors that is observable through machine reading of text.
Education Sciences · 2025-03-14
articleOpen accessSenior authorThe objective of this article is to discuss the advantages of effective educational monitoring in the context of a longitudinal RCT. Intentional data collection and monitoring enables the important assessment of issues of both internal and external validity. We discuss how we used mixed methods data collection to reveal important changing contextual factors in an evaluation of a postsecondary access program in the U.S. state of Texas. Specifically, we employed quantitative analysis of the RCT to compare the college enrollment rates of high schools that were randomly assigned a college adviser with schools that were not assigned a college adviser. We employed survey data collection, qualitative interviews, and site visits to monitor the fidelity of treatment implementation and compliance to treatment assignment over time. In the absence of monitoring treatment fidelity and compliance over time in both treatment and control schools, we would have missed critical changes that explain the observed attenuation of treatment effect estimates. We also discuss how monitoring can inform defenses of the stable unit treatment value assumption and suggest how effective the program will be when applied more widely or to other contexts.
2025-01-31
preprintOpen accessComputational text analysis has grown in popularity among social scientists due to the massive influx of digitized data available to study. However, much of this research disconnects patterns observed in text from information about the original authors. Eliding authorship considerations from sociological analysis of text can potentially lead to claims and assertions of trends that are independent from the social actors, conditions, interactions, and contexts which the text was produced. While text analysis without authorship information can yield reasonable inferences about society, complementing that approach with research that explicitly considers the people producing the text could expand the theoretical and empirical scope of work in this area. In this paper, we adapt perspectives from sociolinguistics and explicitly consider categorical identity markers of authors and geography as foundational axes of variation in textual data. We explore these dimensions in a large corpus of college admissions essays (n = 254,820 essays submitted by 83,538 applicants) and metadata about applicant identity, including the ZIP code of their high school. After generating features of the essays using computational methods, we find that author identity markers, such as gender, parental education, and socioeconomic status are highly salient. We also find that ZIP code level socioeconomic measures are extremely correlated with the writing style and content of local applicants. We also find that individuals whose personal identities are spatially unique–that is, demographically different from others in their immediate content–were most likely to be misclassified by our models, indicating that writing is influenced both socially and spatially. This work clarifies how authorship characteristics, like identity and spatial context, constrain the breadth of what we write and how we write by showing strong alignment between text and authors that is observable through machine reading of text.
2024-04-12 · 11 citations
preprintOpen accessSenior author** Final version published open-access in the Journal of Big Data: https://link.springer.com/article/10.1186/s40537-024-00986-7?utm_source=rct_congratemailt&utm_medium=email&utm_campaign=oa_20240927&utm_content=10.1186/s40537-024-00986-7#article-info** Large language models have become popular over a short period of time because they can generate text that resembles human writing across various domains and tasks. The popularity and breadth of use also put this technology in the position to fundamentally reshape how written language is perceived and evaluated. It is also the case that spoken language has long played a role in maintaining power and hegemony in society, especially through ideas of social identity and ``correct'' forms of language. But as human communication becomes even more reliant on text and writing, it is important to understand how these processes might shift and who is more likely to see their writing styles reflected back at them through modern AI. We therefore ask the following question: \textit{who} does generative AI write like? To answer this, we compare writing style features in over 150,000 college admissions essays submitted to a large public university system and an engineering program at an elite private university with a corpus of over 25,000 essays generated with GPT-3.5 and GPT-4 to the same writing prompts. We find that human-authored essays exhibit more variability across various individual writing style features (e.g., verb usage) than AI-generated essays. Overall, we find that the AI-generated essays are most similar to essays authored by students who are males with higher levels of social privilege. These findings demonstrate critical misalignments between human and AI authorship characteristics, which may affect the evaluation of writing and calls for research on control strategies to improve alignment.
Journal Of Big Data · 2024-09-27 · 29 citations
articleOpen accessSenior authorLarge language models have become popular over a short period of time because they can generate text that resembles human writing across various domains and tasks. The popularity and breadth of use also put this technology in the position to fundamentally reshape how written language is perceived and evaluated. It is also the case that spoken language has long played a role in maintaining power and hegemony in society, especially through ideas of social identity and “correct” forms of language. But as human communication becomes even more reliant on text and writing, it is important to understand how these processes might shift and who is more likely to see their writing styles reflected back at them through modern AI. We therefore ask the following question: who does generative AI write like? To answer this, we compare writing style features in over 150,000 college admissions essays submitted to a large public university system and an engineering program at an elite private university with a corpus of over 25,000 essays generated with GPT-3.5 and GPT-4 to the same writing prompts. We find that human-authored essays exhibit more variability across various individual writing style features (e.g., verb usage) than AI-generated essays. Overall, we find that the AI-generated essays are most similar to essays authored by students who are males with higher levels of social privilege. These findings demonstrate critical misalignments between human and AI authorship characteristics, which may affect the evaluation of writing and calls for research on control strategies to improve alignment.
Scientometrics · 2024-09-22 · 16 citations
articleOpen accessSenior authorAbstract Systematic literature reviews are attempts to understand conversations between researchers working to develop solutions to common problems. These conversations often stretch back decades and can involve the participation of dozens of authors. Traditional approaches to systematic reviews are ill-equipped to make sense of the sheer volume of relevant literature when exploring the emergence and evolution of ambiguous ideas across large knowledge communities. This article presents three innovative applications of Social Network Analysis (SNA) methods to explore the emergence and evolution of accountability in higher education across a collection of 450 peer-reviewed articles published from 1974-2017 and their corresponding 12,270 references. First, qualitative data from articles and references were integrated into new interactive joint displays called Narrated Network Diagrams, creating opportunities to more accurately assess themes and meanings in literature by connecting structures in co-citation networks with relevant relational stories. Second, time was elevated in the analysis procedure to capture the dynamism of knowledge formation. Third, underutilized descriptive network statistics were applied to the co-citation network analysis to generate new insights such as different mechanisms for authors gaining influence in a knowledge community. Ultimately, this article presents an innovative longitudinal Mixed Methods Social Network Analysis (MMSNA) approach to systematic literature reviews, significantly advancing previous SNA methods integration in this critical research practice.
American Journal of Education · 2023-09-28
article1st authorCorrespondingPurpose: Schoolwide college access programs are becoming increasingly ubiquitous in high schools across the country. Research on their effectiveness in improving college-going rates is inconclusive, prompting scholars to question how programs affect practices in schools. To better understand how schools and college access programs work in partnership to expand college advising resources, we study the practices of high schools partnered with a national college access program. Research Methods/Approach: We conducted case studies of two schools, interviewing 118 teachers, staff, parents, students, and program partners over 2 years of data collection. Using the concept of school social capital—the cognitive, material, and social resources that schools derive from their partnership with other organizations—we examined the different ways that school staff interact and collaborate with college access partner staff. Findings: We find that partnerships can help schools become more extensive brokers of college knowledge and advice by engaging in three practices: referrals, collaborative actions, and norm-setting practices. When engaged in collaboration and norm-setting, staff roles expand to include the provision of college advising services and contribute to increasing student access to advising schoolwide. We further find that school leadership plays a significant role in facilitating the types of practices that emerge from college access partnerships. Implications: Although college access partnerships can give rise to multiple advising agents in a school, such effects must be fostered. The alignment of values and goals between partners appears necessary to facilitate brokering practices between staff, as well as leadership to sanction those practices.
Socius Sociological Research for a Dynamic World · 2022-01-01 · 6 citations
articleOpen accessSenior authorHow does gender inform initial academic commitments and narrative self-presentation in science, technology, engineering, and mathematics (STEM) fields during the college application process? Analyzing 60,000 undergraduate applications to the University of California, the authors surface two key findings. First, extant gender segregation of academic disciplines also manifests in intended major choice. Additionally, gender and SAT Math scores together strongly predict intent to major in biology and engineering, the most popular and gender-segregated majors. Second, using natural language processing, the investigators find that author gender is more predictive of essay topics written by prospective engineers than prospective biologists. Specifically, women intending to major in engineering write about essay topics that signal their gender identity to a greater degree than women intending to major in biology, perhaps to mitigate gender-transgressive academic commitments. The authors subsequently argue that prescriptive and proscriptive ideas about men and women’s academic choices remain highly salient in a moment of imagining future academic and professional selves.
Harvard Dataverse · 2022-08-18
datasetOpen accessSenior authorReplication code and data for "Signaled or Suppressed? How Gender Informs Women’s Undergraduate Applications in Biology and Engineering".
Replication Data for: "Social Influences on Text Production"
Harvard Dataverse · 2022-09-11
datasetOpen accessSenior authorReplication data for "Social Influences on Textual Production: Intersectionality, Geography, and College Admissions Essays". Note that the raw essays are unavailable.
Frequent coauthors
- 17 shared
AJ Alvero
- 11 shared
Ben Gebre-Medhin
Mount Holyoke College
- 11 shared
Sonia Giebel
WZB Berlin Social Science Center
- 8 shared
Mitchell L. Stevens
Stanford University
- 8 shared
Benjamin W. Domingue
- 3 shared
Thorsten Joachims
- 3 shared
Alejandra Regla-Vargas
University of Pennsylvania
- 3 shared
Noah Arthurs
Stanford University
- Resume-aware match score
- Save to shortlist
- AI-drafted outreach
See your match with Anthony Lising Antonio
PhdFit ranks faculty by your research interests, methods, and publications — grounded in their actual work, not templates.
- Free to start
- No credit card
- 30-second signup