Jeong-Nam Kim

Human papillomavirus (HPV) vaccines have shown significant public health benefits for both individuals and communities by lowering the rates of several cancers caused by high-risk HPV strains (Worl...

Analysis of public opinions collected from digital media helps organizations maintain positive relationships with the public. Such public relations (PR) analysis often involves assessing opinions, for example, measuring how strongly people trust an organization. Pre-trained Large Language Models (LLMs) hold great promise for supporting Organization-Public Relationship Assessment (OPRA) because they can map unstructured public text to OPRA dimensions and articulate rationales through prompting. However, adapting LLMs for PR analysis typically requires fine-tuning on large labeled datasets, which is both labor-intensive and knowledge-intensive, making it difficult for PR researchers to apply these models. In this paper, we present OPRA-Vis, a visual analytics system that leverages LLMs for OPRA without requiring extensive labeled data. Our framework employs Chain-of-Thought prompting to guide LLMs in analyzing public opinion data by incorporating PR expertise directly into the reasoning process. Furthermore, OPRA-Vis provides visualizations that reveal the clues and reasoning paths used by LLMs, enabling users to explore, critique, and refine model decisions. We demonstrate the effectiveness of OPRA-Vis through two real-world use cases and evaluate it quantitatively, through comparisons with alternative LLMs and prompting strategies, and qualitatively, through assessments of usability, effectiveness, and expert feedback.

We have collected 16 research essays on how artificial intelligence (AI) is reshaping media, communication, and public life. The authors describe and prescribe how people respond to AI in real settings, such as journalists transitioning to algorithmic newsrooms, students utilizing ChatGPT, and policymakers searching for fairness and transparency. Across all articles, trust, ethics, and context should and could surpass AI’s technical power. We classify the essays into four groups: AI adoption and professional integration; AI governance, ethics, and societal risk; pseudo-information detection and correction; and data-science methods for opinion and behavior analysis. These essays witness emerging media transformations, hinting at how AI can coevolve with, not replace, human intelligence in everyday mediated and connected life.

Background: Outbreaks of influenza-like illness (ILI) pose ongoing public health challenges, prompting widespread demand for timely and accessible health information. TikTok, a leading short video platform, has emerged as an overarching channel for disseminating health-related content, particularly in mainland China. While previous studies have examined health communication on social media, few have integrated complementary theoretical frameworks to understand how user perceptions and motivations jointly influence health behaviors. Objective: This study integrates the situational theory of problem solving (STOPS) and the technology acceptance model (TAM) to examine the communicative actions and intentions of Chinese TikTok users to adopt health protective behaviors in response to ILI. Methods: A cross-sectional web-based survey was conducted in China between June and July 2023 using convenience and snowball sampling. A total of 1109 valid responses were analyzed using partial least squares structural equation modeling. Constructs from STOPS (problem recognition, constraint recognition, involvement recognition, situational motivation, and communicative action in problem solving) and TAM (perceived usefulness, perceived ease of use, and attitude) were measured alongside risk perception and intention to engage in protective behaviors. Results: Perceived usefulness (β=.344; P<.001) and ease of use (β=.359; P<.001) positively influenced the attitude toward using TikTok. Risk perception (β=.050, P=.02) had a small but significant impact on attitude. Situational motivation was positively predicted by risk perception (β=.154; P<.001), problem recognition (β=.153; P<.001), and involvement recognition (β=.248; P<.001) but negatively predicted by constraint recognition (β=−.265; P<.001). Both attitude (β=.390; P<.001) and situational motivation (β=.471; P<.001) significantly influenced communicative action, which in turn predicted intention to practice protective behaviors (β=.570; P<.001). Mediation analyses confirmed the partial mediating roles of attitude and situational motivation. Conclusions: TikTok is an effective platform for public health communication in China, particularly for ILI-related content. Integrating the STOPS and TAM provides a robust framework for explaining how user perceptions and motivations translate into digital engagement and health protective intentions. These findings suggest that interventions should not only enhance technological usability and credibility but also tailor content to elevate perceived personal relevance and reduce psychological or contextual constraints. Future public health campaigns can benefit from engaging influencers, using participatory content formats, and targeting specific motivational cues to increase user involvement in health communication and behavioral change. Caution is warranted in generalizing these results because of the culturally specific and demographically skewed nature of the sample.

Many who believed Covid-19 fake news eschewed vaccines, masks, and social distancing; got unnecessarily infected; and died. To detect such fake news, we follow deceptive writing theory and link French hedges and modals to validity. As hedges indicate uncertainty, fake news writers can use it to include falsehoods while shifting responsibility to the audience. Whereas devoir (must) emphasizes certainty and truth, falloir (should, need) implies truth but emphasizes external factors, allowing writers to shirk responsibility. Pouvoir (can) indicates possibility, making it less tied to truth or falsehood. We tested this model with 50,000 French tweets about Covid-19 during March–August 2020 via mixed response analysis. Tweets with hedges or the modal falloir were more likely than others to be false, those with devoir were more likely to be true, and those with pouvoir showed no clear link to truth. Tweets of users with verification, more followers, or fewer status updates were more likely to be true. These results extend deceptive writing theory and inform fake news detection algorithms and media literacy instruction.

BACKGROUND Outbreaks of influenza-like illness (ILI) pose ongoing public health challenges, prompting widespread demand for timely and accessible health information. TikTok, a leading short video platform, has emerged as an overarching channel for disseminating health-related content, particularly in mainland China. While previous studies have examined health communication on social media, few have integrated complementary theoretical frameworks to understand how user perceptions and motivations jointly influence health behaviors. OBJECTIVE This study integrates the situational theory of problem solving (STOPS) and the technology acceptance model (TAM) to examine the communicative actions and intentions of Chinese TikTok users to adopt health protective behaviors in response to ILI. METHODS A cross-sectional web-based survey was conducted in China between June and July 2023 using convenience and snowball sampling. A total of 1109 valid responses were analyzed using partial least squares structural equation modeling. Constructs from STOPS (problem recognition, constraint recognition, involvement recognition, situational motivation, and communicative action in problem solving) and TAM (perceived usefulness, perceived ease of use, and attitude) were measured alongside risk perception and intention to engage in protective behaviors. RESULTS Perceived usefulness (β=.344; P<.001) and ease of use (β=.359; P<.001) positively influenced the attitude toward using TikTok. Risk perception (β=.050, P=.02) had a small but significant impact on attitude. Situational motivation was positively predicted by risk perception (β=.154; P<.001), problem recognition (β=.153; P<.001), and involvement recognition (β=.248; P<.001) but negatively predicted by constraint recognition (β=−.265; P<.001). Both attitude (β=.390; P<.001) and situational motivation (β=.471; P<.001) significantly influenced communicative action, which in turn predicted intention to practice protective behaviors (β=.570; P<.001). Mediation analyses confirmed the partial mediating roles of attitude and situational motivation. CONCLUSIONS TikTok is an effective platform for public health communication in China, particularly for ILI-related content. Integrating the STOPS and TAM provides a robust framework for explaining how user perceptions and motivations translate into digital engagement and health protective intentions. These findings suggest that interventions should not only enhance technological usability and credibility but also tailor content to elevate perceived personal relevance and reduce psychological or contextual constraints. Future public health campaigns can benefit from engaging influencers, using participatory content formats, and targeting specific motivational cues to increase user involvement in health communication and behavioral change. Caution is warranted in generalizing these results because of the culturally specific and demographically skewed nature of the sample.

Government agencies tasked with soliciting comments from the American public in response to changes in rulemaking have long been interested in finding effective techniques to automatically process spam comments, including flagging and filtering duplicate comments. Duplicate submissions are problematic because they obscure genuine public input and may amplify fringe opinions nonrepresentative of the majority of the American public. Given that duplicate comments are generated from templates or predrafted texts, they can easily overwhelm the commenting process, and massive opinion spam campaigns have made manually flagging duplicate comments a costly and time-consuming task for rulemaking agencies. To help agencies in their deduplication efforts, we developed and tested a highly accurate and cost-effective technique based on unsupervised deep machine learning. Our method used the graph augmented deep learning model to embed the comment texts into vectors, and then we applied the clustering method to the embedded vectors to identify similar comments. To test the efficacy of the proposed approach, we applied our technique to the raw data from the Federal Communications Commission’s (FCC) proposed rule change on Net Neutrality in 2017. Our study results demonstrate the superiority of the proposed deep learning technique at identifying duplicate comments, relative to other state-of-the-art deduplication approaches.

Seongbum Seo, Sangbong Yoo, Hyelim Lee, Yun Jang, Ji Hwan Park, Jeong-Nam Kim. Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (System Demonstrations). 2025.

Public relations (PR) aims to establish positive relationships of company-customer and government-citizen. PR researchers and scholars achieve this by analyzing communication behavioral data, which encompasses the public’s experiences in consumption, policy, and governance. However, labeling this data for analysis in PR is costly and complex, primarily due to its multi-label and the need for human judgment based on the Organization-Public Relationship Assessment (OPRA) concepts. Consequently, these problems limit the development of automated labeling models because more training data is needed for fine-tuning. In this paper, we propose a novel tag cloud visualization integrated with dimensionality reduction for conceptualizing communication behavioral data to address limitations in PR. We use attention-based embedding and dimensionality reduction to visualize the public’s experience as a scatter plot according to OPRA concepts. Additionally, we provide PR researchers and scholars with clues for multi-labeling by combining the tag cloud using Bag of Words (BoW) in a scatter plot. We evaluate our proposed interactive visualization through a case study and feedback from two PR researchers.