In this article, we argue that social media platforms communicate their governance strategies both about and through values across diverse sites of communication— about values in presenting normative ideals and through values to justify their content moderation practices. Moreover, we highlight the significance of analyzing platform values across temporal and regional contexts, especially beyond the Western sphere. Focusing on X and Weibo, we employed content and network analysis to examine how they articulated values in different venues to regulate public expression from 2007 to 2024. Our findings reveal an increasing convergence in how the two platforms communicate about values in their community guidelines, suggesting a trend of institutional isomorphism in response to shared challenges such as misinformation and online safety. However, they diverged in communicating through values in administrative posts. While X emphasized personal-level values such as self-expression, Weibo prioritized social-level values, particularly social and political security, often in the context of addressing concrete cases.

This study introduces the “framing element” method, an alternative approach to computational news framing detection. Rooted in a constructionist framing analysis framework, it identifies frames as packages of framing elements, including actors (individuals and organizations) and topics, extending beyond topic-focused methods in prior unsupervised analyses. Compared with latent Dirichlet allocation (LDA)- and Bidirectional Encoder Representations from Transformers (BERT)-based approaches on 1,300 U.S. gun violence news articles, this method addresses LDA’s limitations by focusing on high-level framing elements rather than keywords and is less labor-intensive than BERT-based supervised learning. Supporting both inductive and deductive analyses, it achieves comparable results to LDA while uncovering a previously unidentified gun violence frame.

With the wider penetration of information and communication technologies (ICTs), digital divide scholars have turned attention from physical access to the difference in usage. Based on a national representative survey conducted in mainland China (N = l,004), this exploratory study contributes to the literature by explicating a new typology of social media usage divides predicted by demographic factors and personality traits (the Big Five) and by adding the context of an authoritarian country. The results show that even controlling for personality traits, age shows strong negative effects on most usages. Males and educated populations are also savvier in some of the usages. Interestingly, "reverse divides" were found in mainstream informational use, indicating that the older generations and the lower-income groups use social media for getting information from mainstream media relatively more frequently. This paper also reveals significant predicting and interaction effects of individuals' personality traits on some usage divides.

Media framing refers to highlighting certain aspect of an issue in the news to promote a particular interpretation to the audience. Supervised learning has often been used to recognize frames in news articles, requiring a known pool of frames for a particular issue, which must be identified by communication researchers through thorough manual content analysis. In this work, we devise an unsupervised learning approach to discover the frames in news articles automatically. Given a set of news articles for a given issue, e.g., gun violence, our method first extracts frame elements from these articles using related Wikipedia articles and the Wikipedia category system. It then uses a community detection approach to identify frames from these frame elements. We discuss the effectiveness of our approach by comparing the frames it generates in an unsupervised manner to the domain-expert-derived frames for the issue of gun violence, for which a supervised learning model for frame recognition exists.

This study incorporates the examination of citizenship norms in testing the Citizen Communication Mediation Model (CCMM) in China, exploring to what extent online political expression mediates the impact of informational use of social media on offline civic engagement and how beliefs in citizenship norms moderate the CCMM. Results based on a two-wave panel survey among a national sample of 1,199 Chinese adults provide strong support for the CCMM in the Chinese context. In addition, embracing the democratic citizenship norm significantly enhances the CCMM effect, whereas embracing the pro-government citizenship norm that encourages pro-government speech does not show the same effect.

We aim to develop methods for understanding how multimedia news exposure can affect people’s emotional responses, and we especially focus on news content related to gun violence, a very important yet polarizing issue in the U.S. We created the dataset NEmo+ by significantly extending the U.S. gun violence news-to-emotions dataset, BU-NEmo, from 320 to 1,297 news headline and lead image pairings and collecting 38,910 annotations in a large crowdsourcing experiment. In curating the NEmo+ dataset, we developed methods to identify news items that will trigger similar versus divergent emotional responses. For news items that trigger similar emotional responses, we compiled them into the NEmo+-Consensus dataset. We benchmark models on this dataset that predict a person’s dominant emotional response toward the target news item (single-label prediction). On the full NEmo+ dataset, containing news items that would lead to both differing and similar emotional responses, we also benchmark models for the novel task of predicting the distribution of evoked emotional responses in humans when presented with multi-modal news content. Our single-label and multi-label prediction models outperform baselines by large margins across several metrics.

In response to Perloff's (this issue) essay examining the development and future of agenda setting, a series of scholars offer their own reactions to the essay and the broader issues it raises.

Given our society’s increased exposure to multimedia formats on social media platforms, efforts to understand how digital content impacts people’s emotions are burgeoning. As such, we introduce a U.S. gun violence news dataset that contains news headline and image pairings from 840 news articles with 15K high-quality, crowdsourced annotations on emotional responses to the news pairings. We created three experimental conditions for the annotation process: two with a single modality (headline or image only), and one multimodal (headline and image together). In contrast to prior works on affectively-annotated data, our dataset includes annotations on the dominant emotion experienced with the content, the intensity of the selected emotion and an open-ended, written component. By collecting annotations on different modalities of the same news content pairings, we explore the relationship between image and text influence on human emotional response. We offer initial analysis on our dataset, showing the nuanced affective differences that appear due to modality and individual factors such as political leaning and media consumption habits. Our dataset is made publicly available to facilitate future research in affective computing.

Despite several transient spikes in response to the deadliest mass shootings, the U.S. population continues to perceive gun violence as less important than other issues, and public opinion remains divided along partisan lines. Drawing upon literature of compelling arguments and partisan media, this study investigates what kind of news framing-episodic framing that focuses on individual stories or thematic framing that emphasizes broader context-makes gun violence a more or less prominent issue. Specifically, this study uses the state-of-the-art machine-learning model BERT to examine 25 news media outlets' coverage of gun violence, and then pairs the results with a two-wave panel survey conducted during the 2018 U.S. midterm elections. Results demonstrate that episodic framing of gun violence in the elite, mainstream media increased the issue salience among conservatives. However, exposure to episodically framed coverage of gun violence in like-minded partisan media made conservatives believe the issue was less important.

When journalists cover a news story, they can cover the story from multiple angles or perspectives. These perspectives are called “frames,” and usage of one frame or another may influence public perception and opinion of the issue at hand. We develop a web-based system for analyzing frames in multilingual text documents. We propose and guide users through a five-step end-to-end computational framing analysis framework grounded in media framing theory in communication research. Users can use the framework to analyze multilingual text data, starting from the exploration of frames in user’s corpora and through review of previous framing literature (step 1-3) to frame classification (step 4) and prediction (step 5). The framework combines unsupervised and supervised machine learning and leverages a state-of-the-art (SoTA) multilingual language model, which can significantly enhance frame prediction performance while requiring a considerably small sample of manual annotations. Through the interactive website, anyone can perform the proposed computational framing analysis, making advanced computational analysis available to researchers without a programming background and bridging the digital divide within the communication research discipline in particular and the academic community in general. The system is available online at http://www.openframing.org, via an API http://www.openframing.org:5000/docs/, or through our GitHub page https://github.com/vibss2397/openFraming.

While the political influence of the Internet, especially social media, on people's attitude toward their governments has been widely discussed in western democracies, the situation in authoritarian regimes such as China has not yet been adequately addressed. The current Chinese administration considers social media the main battlefield for public opinion struggle' between the official discourse and those challenging it. To provide clues about who is shaping the public opinion, this study examined how consuming news from competing information sources on social media influences Chinese citizens' satisfaction with the central and local government. Based on a nationally representative survey of 2,882 Chinese adults, the study found that consuming news from governmental sources on the country's major social media platforms - Weibo and WeChat - was positively associated with citizens' satisfaction with the central government, while exposure to alternative news sources on WeChat had a negative impact on both central and local government satisfaction. Additionally, news consumption from mainstream media sources on social media did not significantly influence the public's government satisfaction. This paper contributes to the current literature by revealing that social media do not provide a unified agenda and by emphasizing the impact of platform affordances on people's political attitudes.

News media structure their reporting of events or issues using certain perspectives. When describing an incident involving gun violence, for example, some journalists may focus on mental health or gun regulation, while others may emphasize the discussion of gun rights. Such perspectives are called "frames" in communication research. We study, for the first time, the value of combining lead images and their contextual information with text to identify the frame of a given news article. We observe that using multiple modes of information(article- and image-derived features) improves prediction of news frames over any single mode of information when the images are relevant to the frames of the headlines. We also observe that frame image relevance is related to the ease of conveying frames via images, which we call frame concreteness. Additionally, we release the first multimodal news framing dataset related to gun violence in the U.S., curated and annotated by communication researchers. The dataset will allow researchers to further examine the use of multiple information modalities for studying media framing.

News framing refers to the practice in which aspects of specific issues are highlighted in the news to promote a particular interpretation. In NLP, although recent works have studied framing in English news, few have studied how the analysis can be extended to other languages and in a multi-label setting. In this work, we explore multilingual transfer learning to detect multiple frames from just the news headline in a genuinely low-resource context where there are few/no frame annotations in the target language. We propose a novel method that can leverage elementary resources consisting of a dictionary and few annotations to detect frames in the target language. Our method performs comparably or better than translating the entire target language headline to the source language for which we have annotated data. This work opens up an exciting new capability of scaling up frame analysis to many languages, even those without existing translation technologies. Lastly, we apply our method to detect frames on the issue of U.S. gun violence in multiple languages and obtain exciting insights on the relationship between different frames of the same problem across different countries with different languages.

We report results of a comparison of the accuracy of crowdworkers and seven Natural Language Processing (NLP) toolkits in solving two important NLP tasks, named-entity recognition (NER) and entity-level sentiment (ELS) analysis. We here focus on a challenging dataset, 1,000 political tweets that were collected during the U.S. presidential primary election in February 2016. Each tweet refers to at least one of four presidential candidates, i.e., four named entities. The groundtruth, established by experts in political communication, has entity-level sentiment information for each candidate mentioned in the tweet. We tested several commercial and open-source tools. Our experiments show that, for our dataset of political tweets, the most accurate NER system, Google Cloud NL, performed almost on par with crowdworkers, but the most accurate ELS analysis system, TensiStrength, did not match the accuracy of crowdworkers by a large margin of more than 30 percent points.

This study investigated the network agenda setting (NAS) model with data gathered from Taiwan's 2012 presidential election. Networks of important objects and candidate attributes in the news were compared with the counterparts generated from public opinion. The overall correlation between the media and public network agendas was positive and significant, thus supporting the NAS model in a non-Western context. In addition, this study found that the NAS model offered more predictive power at the attribute than the object level. The effects of selective exposure in a partisan media system were also incorporated into the investigation. Results showed that partisan selective exposure did not lead to consistent findings about the accentuated association between like-minded media consumption and candidate evaluation.

This study examined the echo chamber phenomenon and opinion leadership on Twitter based on the 2016 U.S. presidential election. Network analysis and 'big data' analytics were employed to analyze more than 50 million tweets about the two presidential candidates, Donald Trump and Hillary Clinton, during the election cycle. Overall, the results suggested that Twitter communities discussing Trump and Clinton differed significantly in the level of political homogeneity and opinion leadership, and that certain opinion leaders were responsible of creating homogeneous communities on Twitter. This study made a theoretical contribution to the literature by linking opinion leadership and Twitter's network structure and shedding light on what may have caused the echo chamber problem to happen in an emerging media landscape.

In China, the discussion of "fake news" often revolves around online rumor. In addition to politically motivated rumors, a large portion of profit-driven, sensational rumors permeate China's Internet. This study examines the diffusion of day-to-day online rumors on Weibo, WeChat, and mainstream news websites-the three major online news platforms in China-within an agenda-setting framework. Specifically, the study analyzed the top ten most widely distributed online rumors in China in 2016, focusing on how each rumor was reported and the transfer of rumor salience within and across the three media platforms. A total of 18,347 news items were quantitatively content analyzed and time-series analyses were conducted to discover the rumor diffusion patterns. Overall, the results show that Weibo was most likely to advance rumors, while WeChat had the greatest rumor refutation-to-advancement ratio. Mainstream news websites set the agenda of both Weibo and WeChat in refuting rumors and, ironically, also set the agenda of WeChat in advancing rumors. For rumor refuting within social media, the agenda-setting power of mainstream media remained strong on Weibo, while on WeChat governmental accounts and alternative information sources were more effective in building the mainstream media agenda.