ZENING DUAN
Ph.D. candidate
School of Journalism and Mass Communication
University of Wisconsin-Madison
Email: zening.duan [at] wisc.edu
Emerging Media Technology | Information Engagement |
Newsroom-Social Media | Media Ecosystem |
Computational Social Science
My name is Zening Duan (pronounced ZEH-ning DWAN). I am currently a Ph.D. candidate at the School of Journalism and Mass Communication at the University of Wisconsin-Madison, where I actively contribute to the Social Media and Democracy Group (SMAD), Computational Approaches and Message Effects Research Group (CAMER), and Center for Communication and Civil Renewal (CCCR). Since Spring 2023, I have been leading the Computational Methods Research Group (CMRG) in Madison. Starting from January 2026, I’ll be joining the Department of Communications and New Media at the National University of Singapore as a tenure-track Assistant Professor under the Presidential Young Professorship.
I am continuously interested in how generative artificial intelligence (AI) functions as a communicator, competing for attention across newsrooms and social media. I believe it is essential to explore AI’s broader impacts, such as how it influences online content virality on controversial issues and exacerbates to asymmetries in partisan information flow. From a sociotechnical perspective, my recent studies found that AI-powered bots amplified topics in social media posts aligned with partisan narratives and predicted subsequent news coverage in media outlets. These findings suggest that AI plays a distinct role in selectively influencing online discussion and news attention. This work is among the first to quantitatively examine and conceptualize “selective attention amplification” in the context of AI, offering insights into how and when emerging technologies capture attention and where that attention is directed in today’s hybrid media ecosystem.
As a computational researcher, I also contribute to methodological advancements in our field. My recent work introduces “vec-tionaries,” a novel computational model for measuring latent message features in texts (e.g., social media posts and news stories). My team released a free, open-access Python package to support open science. Currently, I’m leading some collaborative efforts exploring generative AI’s potential in research practices, particularly using large language models for multimodal content processing, source categorization, and simulation. This work contributes to the broader conversation on AI in research, aiming to develop an interpretable and reproducible AI-as-method framework for computational social science.
Building on these two strands, my dissertation, titled “Selective Attention Amplification through Algorithms and Consequences on Information Flow,” formally discusses the phenomenon of “selective attention amplification,” examining its multi-layered factors and implications for the contemporary media ecosystem, particularly when both AI and human communicators get involved.
My leading authored and/or co-first authored work has appeared and forthcoming in leading peer-reviewed journals including Human Communication Research, Journal of Computer-Mediated Communication, Political Analysis, The International Journal of Press/Politics, among others. Much of this work has been supported by grants and awards from internal and external institutions such as the Holtz Center, WARF, Hewlett Foundation, Knight Foundation, and NSF. a Prior to Madison, I worked as a journalist and media specialist in a tech-finance news and marketing startup with coverage across China and Asia.
In my free time, I enjoy skiing, gardening, bouldering, and spending time with family, friends, and my two feline co-PIs, Toree and Ritto.
Constructing Vec-tionaries to Extract Message Features from Texts: A Case Study of Moral Content with Anqi Shao, Yicheng Hu, Heysung Lee, Xining Liao, Yoo Ji Suh, Jisoo Kim, Kai-Cheng Yang, Kaiping Chen, and Sijia Yang. Political Analysis, 2025
While researchers often study message features like moral content in text, such as party manifestos and social media, their quantification remains a challenge. Conventional human coding struggles with scalability and intercoder reliability. While dictionary-based methods are cost-effective and computationally efficient, they often lack contextual sensitivity and are limited by the vocabularies developed for the original applications. In this paper, we present an approach to construct vec-tionary measurement tools that boost validated dictionaries with word embeddings through nonlinear optimization. By harnessing semantic relationships encoded by embeddings, vec-tionaries improve the measurement of message features from text, especially those in short format, by expanding the applicability of original vocabularies to other contexts. Importantly, a vec-tionary can produce additional metrics to capture the valence and ambivalence of a message feature beyond its strength in texts. Using moral content in tweets as a case study, we illustrate the steps to construct the moral foundations vec-tionary, showcasing its ability to process texts missed by conventional dictionaries and word embedding methods and to produce measurements better aligned with crowdsourced human assessments. Furthermore, additional metrics from the vec-tionary unveiled unique insights that facilitated predicting outcomes such as message retransmission.
Uncovering gender stereotypes in controversial science discourse: Evidence from computational text and visual analyses across digital platforms with Kaiping Chen and Sang Jung Kim. Journal of Computer-Mediated Communication, Volume 29, Issue 1, January 2024
This study examines how gender stereotypes are reflected in discourses around controversial science issues across two platforms, YouTube and TikTok. Utilizing the Social Identity Model of Deindividuation Effects, we developed hypotheses and research questions about how content creators might use gender-related stereotypes to engage audiences. Our analyses of climate change and vaccination videos, considering various modalities such as captions and thumbnails, revealed that themes related to children and health often appeared in videos mentioning women, while science misinformation was more common in videos mentioning men. We observed cross-platform differences in portraying gender stereotypes. YouTube’s video descriptions often highlighted women-associated moral language, whereas TikTok emphasized men-associated moral language. YouTube’s thumbnails frequently featured climate activists or women with nature, while TikTok’s thumbnails showed women in Vlog-style selfies and with feminine gestures. These findings advance understanding about gender and science through a cross-platform, multi-modal approach and offer potential intervention strategies.
Algorithmic Agents in the Hybrid Media System: Social Bots, Selective Amplification, and Partisan News about COVID-19 with Jianing Li, Josephine Lukito, Kai-Cheng Yang, Fan Chen, Dhavan V Shah, and Sijia Yang. Human Communication Research. Volume 48, Issue 3, July 2022, Pages 516–542
Social bots, or algorithmic agents that amplify certain viewpoints and interact with selected actors on social media, may influence online discussion, news attention, or even public opinion through coordinated action. Previous research has documented the presence of bot activities and developed detection algorithms. Yet, how social bots influence attention dynamics of the hybrid media system remains understudied. Leveraging a large collection of both tweets (N = 1,657,551) and news stories (N = 50,356) about the early COVID-19 pandemic, we employed bot detection techniques, structural topic modeling, and time series analysis to characterize the temporal associations between the topics Twitter bots tend to amplify and subsequent news coverage across the partisan spectrum. We found that bots represented 8.98% of total accounts, selectively promoted certain topics and predicted coverage aligned with partisan narratives. Our macro-level longitudinal description highlights the role of bots as algorithmic communicators and invites future research to explain micro-level causal mechanisms.
▣ General
I’m excited to share my ongoing research on AI communicators and social media information flows at an upcoming seminar hosted by the Department of Media and Communication, City University of Hong Kong, my alma mater
▣ General
Our panel proposal “GenAI for Computational Communication Research” has been accepted by ICA Denver 2025
▣ General
Manuscript “Leveraging Large Language Models in Message Stimuli Generation and Validation for Experimental Research” has been accepted by ICA Denver 2025
▣ General
I submitted my first job application dossier
▣ Preprint
New preprint “Constructing Vec-tionaries to Extract Latent Message Features from Texts” available. This paper has been conditionally accepted by Political Analysis
Copyright © Zening Duan 2025. All Rights Reserved.
ZENING DUAN 