Yilang Peng

Yilang Peng

Auto-generated profile, based on publicly available information

Yilang Peng

University of Georgia, Athens, USA

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

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

Representative Publications

View All Publications
13 October 2020 in The International Journal of Press/Politics
Verified
Journal Article
Closed access
PDF file
YPYilang Peng
Yilang Peng
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 U.S. politicians, both candidates and office holders, and examines how visual attributes influence audience engagement such as likes and comments. In particular, this study introduces an unsupervised approach that combines transfer learning and clustering techniques to discover hidden categories from large-scale visual data. The results reveal that different self-personalization strategies in visual media, for example, images featuring politicians in private, nonpolitical settings, showing faces, and displaying emotions, generally increase audience engagement. Yet, a significant portion of politician’s Instagram posts still fell into the traditional, “politics-as-usual” type of political communication, showing professional settings and activities. The analysis explains how self-personalization is embodied in specific visual portrayals and how different self-presentation strategies affect audience engagement on a popular but less studied social media platform.

28 February 2023 in Political Communication
Verified
Journal Article
Closed access
YPYilang Peng
Yilang Peng
YLYingdan Lu
Yingdan Lu
CSCuihua Shen
Cuihua Shen
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., memes, visualizations) and features (e.g., color, human faces) contribute to visual misinformation's influence, either on their own or in combination with non-visual features and heuristics, and through what mechanisms. In response to these gaps, we identify a theoretical framework that explains the persuasive mechanisms and pathways of visual features in lending credibility (e.g., as arguments, heuristics, and attention determinants). We propose a list of relevant visual attributes to credibility perceptions and a research agenda that integrates methods including computational visual analysis, crowdsourced annotations, and experiments to advance our understanding of visual misinformation.

19 June 2020 in Communication Research
Verified
Journal Article
Closed access
PDF file
TYTian Yang
Tian Yang
YPYilang Peng
Yilang Peng
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 experiment on Weibo by analyzing user engagement data of 36,239 posts in three consecutive weeks, during which trending topics were removed for 1 week. We show that trending topics implemented two layers of gatekeeping: trending topics increased user engagement with top news posts within each news outlet and widened the engagement gap between popular posts and less popular ones (intra-outlet gatekeeping), and the increases in engagement with top news items were most salient among the least popular news outlets, thus reducing the inequality among outlets (inter-outlet gatekeeping).

20 May 2020 in Public Understanding of Science
Verified
Journal Article
Closed access
PDF file
YPYilang Peng
Yilang Peng
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 United States, we reveal an emerging ideological divide in public reactions to self-driving cars. Compared with liberals and Democrats, conservatives and Republicans express more concern about autonomous vehicles and more support for restrictively regulating autonomous vehicles. This ideological gap is largely driven by social conservatism. Moreover, both familiarity with driverless vehicles and scientific literacy reduce respondents’ concerns over driverless vehicles and support for regulation policies. Still, the effects of familiarity and scientific literacy are weaker among social conservatives, indicating that people may assimilate new information in a biased manner that promotes their worldviews.

7 April 2022 in Sociological Methods & Research
Verified
Journal Article
Closed access
HZHan Zhang
Han Zhang
YPYilang Peng
Yilang Peng
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 image data. We first review the steps to perform image clustering and then focus on one key challenge in this task—finding intermediate representations of images. We present several methods of extracting intermediate image representations, including the bag-of-visual-words model, self-supervised learning, and transfer learning (in particular, feature extraction with pretrained models). We compare these methods using various visual datasets, including images related to protests in China from Weibo, images about climate change on Instagram, and profile images of the Russian Internet Research Agency on Twitter. In addition, we propose a systematic way to interpret and validate clustering solutions. Results show that transfer learning significantly outperforms the other methods. The dataset used in the pretrained model critically determines what categories the algorithms can discover.

22 April 2023 in Journal of Communication
Verified
Journal Article
Closed access
PDF file
SMSubhayan Mukerjee
Subhayan Mukerjee
TYTian Yang
Tian Yang
YPYilang Peng
Yilang Peng
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 major media outlets used by American citizens (⁠ N≈2.23M⁠, 2015–2019). We find that while the overall effect of audience engagement on future news coverage is significant, there is substantial heterogeneity in how individual outlets respond to different kinds of topics. A handful of right-wing media outlets are more likely to respond to audience engagement metrics than other outlets, but with partisan politics topics and not with entertainment-oriented content. Our research sheds new light on how social media platforms have shaped journalistic practices and has implications for the future health of journalism in the United States.