Zackary Okun Dunivin

Zackary Okun Dunivin

Auto-generated profile, based on publicly available information

Zackary Okun Dunivin

Department of Communication, University of California, Davis, Davis, USA

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
3 March 2022 in Proceedings of the National Academy of Sciences
Verified
Journal Article
Open access
ZDZackary Okun Dunivin
Zackary Okun Dunivin
HYHarry Yaojun Yan
Harry Yaojun Yan
JIJelani Ince
Jelani Ince
FRFabio Rojas
Fabio Rojas
Significance: This study uses large-scale news media and social media data to show that nationwide Black Lives Matter (BLM) protests occur concurrently with sharp increases in public attention to components of the BLM agenda. We also show that attention to BLM and related concepts is not limited to these brief periods of protest but is sustained after protest has ceased. This suggests that protest events incited a change in public awareness of BLM’s vision of social change and the dissemination of antiracist ideas into popular discourse.

2 April 2025 in EPJ Data Science
Verified
Journal Article
Open access
PDF file
ZDZackary Okun Dunivin
Zackary Okun Dunivin
Qualitative coding, or content analysis, is more than just labeling text: it is a reflexive interpretive practice that shapes research questions, refines theoretical insights, and illuminates subtle social dynamics. As large language models (LLMs) become increasingly adept at nuanced language tasks, questions arise about whether—and how—they can assist in large-scale coding without eroding the interpretive depth that distinguishes qualitative analysis from traditional machine learning and other quantitative approaches to natural language processing. In this paper, we present a hybrid approach that preserves hermeneutic value while incorporating LLMs to scale the application of codes to large data sets that are impractical for manual coding. Our workflow retains the traditional cycle of codebook development and refinement, adding an iterative step to adapt definitions for machine comprehension, before ultimately replacing manual with automated text categorization. We demonstrate how to rewrite code descriptions for LLM-interpretation, as well as how structured prompts and prompting the model to explain its coding decisions (chain-of-thought) can substantially improve fidelity. Empirically, our case study of socio-historical codes highlights the promise of frontier AI language models to reliably interpret paragraph-long passages representative of a humanistic study. Throughout, we emphasize ethical and practical considerations, preserving space for critical reflection, and the ongoing need for human researchers’ interpretive leadership. These strategies can guide both traditional and computational scholars aiming to harness automation effectively and responsibly—maintaining the creative, reflexive rigor of qualitative coding while capitalizing on the efficiency afforded by LLMs.

30 July 2020 in Journal of Medical Internet Research
Verified
Journal Article
Open access
ZDZackary Dunivin
Zackary Dunivin
LZLindsay Zadunayski
Lindsay Zadunayski
UBUjjwal Baskota
Ujjwal Baskota
KSKatie Siek
Katie Siek
JMJennifer Mankoff
Jennifer Mankoff
Background: Online physician reviews are an important source of information for prospective patients. In addition, they represent an untapped resource for studying the effects of gender on the doctor-patient relationship. Understanding gender differences in online reviews is important because it may impact the value of those reviews to patients. Documenting gender differences in patient experience may also help to improve the doctor-patient relationship. This is the first large-scale study of physician reviews to extensively investigate gender bias in online reviews or offer recommendations for improvements to online review systems to correct for gender bias and aid patients in selecting a physician. Objective: This study examines 154,305 reviews from across the United States for all medical specialties. Our analysis includes a qualitative and quantitative examination of review content and physician rating with regard to doctor and reviewer gender. Methods: A total of 154,305 reviews were sampled from Google Place reviews. Reviewer and doctor gender were inferred from names. Reviews were coded for overall patient experience (negative or positive) by collapsing a 5-star scale and coded for general categories (process, positive/negative soft skills), which were further subdivided into themes. Computational text processing methods were employed to apply this codebook to the entire data set, rendering it tractable to quantitative methods. Specifically, we estimated binary regression models to examine relationships between physician rating, patient experience themes, physician gender, and reviewer gender). Results: Female reviewers wrote 60% more reviews than men. Male reviewers were more likely to give negative reviews (odds ratio [OR] 1.15, 95% CI 1.10-1.19; P<.001). Reviews of female physicians were considerably more negative than those of male physicians (OR 1.99, 95% CI 1.94-2.14; P<.001). Soft skills were more likely to be mentioned in the reviews written by female reviewers and about female physicians. Negative reviews of female doctors were more likely to mention candor (OR 1.61, 95% CI 1.42-1.82; P<.001) and amicability (OR 1.63, 95% CI 1.47-1.90; P<.001). Disrespect was associated with both female physicians (OR 1.42, 95% CI 1.35-1.51; P<.001) and female reviewers (OR 1.27, 95% CI 1.19-1.35; P<.001). Female patients were less likely to report disrespect from female doctors than expected from the base ORs (OR 1.19, 95% CI 1.04-1.32; P=.008), but this effect overrode only the effect for female reviewers. Conclusions: This work reinforces findings in the extensive literature on gender differences and gender bias in patient-physician interaction. Its novel contribution lies in highlighting gender differences in online reviews. These reviews inform patients’ choice of doctor and thus affect both patients and physicians. The evidence of gender bias documented here suggests review sites may be improved by providing information about gender differences, controlling for gender when presenting composite ratings for physicians, and helping users write less biased reviews.

18 March 2025 in Journal of Agrarian Change
Verified
Journal Article
Open access
CBChristian Berndt
Christian Berndt
MWMarion Werner
Marion Werner
FMFinn Mempel
Finn Mempel
ASAnnie Shattuck
Annie Shattuck
ZDZackary Okun Dunivin
Zackary Okun Dunivin
The global pesticide industry transformed from one dominated by patented products and legacy multinationals with strong manufacturing bases in the United States and EU to one dominated by generic products produced in India and China. We use proprietary market research data, data from regulatory filings, industry press and bilateral trade data to map how the ‘generics revolution’ transformed production and trade in pesticides. Tracing significant changes in sourcing over two decades, we show the emergence of major agribusiness multinationals focused on the generics market as producers, exporters or both. Industrial policy and firm strategy among Chinese firms, which now dominate the generics market, have had a global impact on the industry. Legacy R&D companies maintain dominance through strong positions in the production and marketing of generics as well, blurring the traditional distinctions between these two sectors. Overall, our analysis raises serious questions for regulation and efforts to reduce pesticide dependence.

13 February 2024 in arXiv
Verified
Preprint
Open access
PDF file
ZDZackary Okun Dunivin
Zackary Okun Dunivin
Qualitative coding, or content analysis, extracts meaning from text to discern quantitative patterns across a corpus of texts. Recently, advances in the interpretive abilities of large language models (LLMs) offer potential for automating the coding process (applying category labels to texts), thereby enabling human researchers to concentrate on more creative research aspects, while delegating these interpretive tasks to AI. Our case study comprises a set of socio-historical codes on dense, paragraph-long passages representative of a humanistic study. We show that GPT-4 is capable of human-equivalent interpretations, whereas GPT-3.5 is not. Compared to our human-derived gold standard, GPT-4 delivers excellent intercoder reliability (Cohen's $κ\geq 0.79$) for 3 of 9 codes, and substantial reliability ($κ\geq 0.6$) for 8 of 9 codes. In contrast, GPT-3.5 greatly underperforms for all codes ($mean(κ) = 0.34$; $max(κ) = 0.55$). Importantly, we find that coding fidelity improves considerably when the LLM is prompted to give rationale justifying its coding decisions (chain-of-thought reasoning). We present these and other findings along with a set of best practices for adapting traditional codebooks for LLMs. Our results indicate that for certain codebooks, state-of-the-art LLMs are already adept at large-scale content analysis. Furthermore, they suggest the next generation of models will likely render AI coding a viable option for a majority of codebooks.

1 October 2025 in Psychological Review
Verified
Journal Article
Closed access
ZDZackary Okun Dunivin
Zackary Okun Dunivin
PSPaul E. Smaldino
Paul E. Smaldino
Covert identity signals permit the communication of group membership to ingroup members while avoiding potentially costly detection by members of other groups. If individuals are incentivized to detect others' group memberships, however, covert signals may not remain covert for very long. We propose a theoretical extension to the literature on covert signaling in which conventionalized identity signals can become destabilized when learned by outgroup individuals to be replaced by the emergence of new signaling conventions. We formalize this idea with both analytical and agent-based modeling of ingroup and outgroup individuals who learn about signals of group membership. Depending on the risk and associated cost of detection by the outgroup, the model yields three dynamic classes: saturation, where all identity signals become stable conventions and never go extinct; cycling, in which new signals emerge to replace old ones as they are learned by the outgroup; and suppression, in which informative identity signals never emerge. Our analysis has implications for understanding identity signaling, the emergence of conventions, coded speech, and the ebb and flow of fashion cycles. (PsycInfo Database Record (c) 2025 APA, all rights reserved).