Yilang Peng

• PhD
• Professor (Assistant) at University of Georgia

Automated image analysis has received increasing attention in social scientific research, yet existing scholarship has mostly covered the application of supervised learning to classify images into predefined categories. This study focuses on the task of unsupervised image clustering, which aims to automatically discover categories from unlabelled i...

Previous research on the success of politicians' messages on social media has so far focused on a limited number of platforms, especially Facebook and Twitter, and predominately studied the effects of textual content. This research reported here applies computer vision analysis to a total of 59,020 image posts published by 172 Instagram accounts of...

Digital gatekeepers have greatly shaped the gatekeeping process of news consumption and news engagement, but how digital gatekeepers work is understudied. This study focuses on one example of digital gatekeepers, trending topics on social media, which aggregate the most popular search terms and present them to the public. We utilize a natural exper...

How do today’s partisan media outlets produce ideological bias in their visual coverage of political candidates? Applying computer vision techniques, this study examined 13,026 images from 15 news websites about the two candidates in the 2016 U.S. presidential election. The analysis unveils a set of visual attributes (e.g., facial expressions, face...

In today's visually dominated social media landscape, predicting the perceived credibility of visual content and understanding what drives human judgment are crucial for countering misinformation. However, these tasks are challenging due to the diversity and richness of visual features. We introduce a Large Language Model (LLM)-informed feature dis...

Advances in generative models have created Artificial Intelligence-Generated Images (AIGIs) nearly indistinguishable from real photographs. Leveraging a large corpus of 30,824 AIGIs collected from Instagram and Twitter, and combining quantitative content analysis with qualitative analysis, this study unpacks AI photorealism of AIGIs from four key d...

To amplify their audience reach, far-right outlets need a calculated and coordinated array of acts to set the stage for audience attention and to build a communication network that spreads their messages. We examined the Facebook newsfeed history of The Epoch Times ( N = 117,274 posts from 2013 to 2020), which transitioned from a niche anti-China p...

Social media metrics allow media outlets to get a granular, real-time understanding of audience preferences, and may therefore be used to decide what content to prioritize in the future. We test this mechanism in the context of Facebook, by using topic modeling and longitudinal data analysis on a large dataset comprising all posts published by majo...

Social media metrics allow media outlets to get a granular, real-time understanding of audience preferences, and may therefore be used to decide what content to prioritize in the future. We test this mechanism in the context of Facebook, by using topic modelling and longitudinal data analysis on a large dataset comprising all posts published by maj...

Today’s political misinformation has increasingly been created and consumed in visual formats, such as photographs, memes, and videos. Despite the ubiquity of visual media and the growing scholarly attention to misinformation, there is a relative dearth of research on visual misinformation. It remains unclear which specific visual formats (e.g., me...

Social media have become an important source where people are exposed to visual representations of foods. This study aims to understand what content factors contribute to the popularity of food images on Instagram. We collected 53,894 images from 90 popular food influencer accounts on Instagram over two years. Applying computer vision methods, we i...

While partisan selective exposure could drive audience fragmentation, other individual factors might also differentiate news diets. This study applies a method that disentangles the differential contributions of the individual characteristics to audience duplication networks. By analyzing a nationally representative survey about US adults’ media us...

Facial recognition technology has been introduced into various aspects of social life, yet it has raised concerns over its infringement of civil liberties and biases against minorities. This study investigates how three ideological dimensions—social dominance orientation, right-wing authoritarianism, and libertarianism—shape facial recognition acce...

Mandatory and punitive vaccination policies, such as requiring vaccination certificates for public activities and firing employees who refuse vaccination, have raised considerable objections. With a sample of U.S. crowdsourced workers (N = 983), this study investigates how four ideologies–left-wing authoritarianism (LWA), right-wing authoritarianis...

While previous research has revealed an ideological divide in Americans’ perceptions of COVID‐19, specific ideological components can additionally explain public reactions to the pandemic. With two surveys—one sample of crowdsourced workers (N = 482) and a nationally representative sample of American adults (N = 7449)—this research investigates how...

While previous research has revealed an ideological divide in Americans' perceptions of COVID-19, specific ideological components can additionally explain public reactions to the pandemic. With two surveys-one sample of crowdsourced workers (N = 482) and a nationally representative sample of American adults (N = 7,449)-this research investigates ho...

Visual aesthetics are related to a broad range of communication and psychological outcomes, yet the tools of computational aesthetic analysis are not widely available in the community of social science scholars. This article addresses this gap and provides a tutorial for social scientists to measure a broad range of hand-crafted aesthetic attribute...

Automated image analysis has received increasing attention in social scientific research, yet existing scholarship has focused on the application of supervised machine learning to classify images into predefined categories. This study focuses on the task of unsupervised image clustering, which automatically finds categories from image data. First,...

This study aimed to examine features of objectified images in popular fitspiration accounts on social media, identify the most prevalent user discussion topics about these images, and investigate the linkages between specific objectification cues and discussion topics. We employed content analysis to identify gender-specific objectification element...

Applications in artificial intelligence such as self-driving cars may profoundly transform our society, yet emerging technologies are frequently faced with suspicion or even hostility. Meanwhile, public opinions about scientific issues are increasingly polarized along the ideological line. By analyzing a nationally representative panel in the Unite...

Although visual content prevails in the digital media environment, previous scholarship that attempts to detect bias and stereotypes in media content has mostly focused on textual data. Meanwhile, recent advances in computer vision have made the analysis of visual data on a large scale possible. Drawing theoretical insights from media bias, social...

The widely circulated food photos online have become an important part of our visual culture. Combining human ratings of food characteristics and computational analysis of visual aesthetics, we examined what contributed to the aesthetic appeal of a diversity of food photographs (N = 300) and likes and comments they received in an artificial newsfee...

Today's digital photographs are being heavily "filtered." By simple clicks on mobile apps like Hipstamatic and Instagram, users can easily apply digital filters to their pictures to create effects such as faux-vintage and light leaks. To understand the potential impacts of photo filters, we conducted an online experiment and investigated how the us...

Controversy in science news accounts attracts audiences and draws attention to important science issues. But sometimes covering multiple sides of a science issue does the audience a disservice. Counterbalancing a truth claim backed by strong scientific support with a poorly backed argument can unnecessarily heighten audience perceptions of uncertai...