Linqi Lu

Foodie traps within facebook cannabis promotional posts: Deploying multimodal deep learning AIs to monitor audience engagement

Linqi Lu, Xianshi Yu, Zhuoyan Xu, Hyerin Kwon et autres

us, au (code pays fourni par la source)

Leveraging the power of ChatGPT to analyze policy framing: policy agendas and issue positions of U.S. governors during the COVID-19 crisis

Hyerin Kwon, Laila Abbas, Jiwon Kang, Linqi Lu et autres

Abstract Following Entman’s observation that policy frames define social problems, diagnose causes and suggest remedies, we examined the strategies that 12 U.S. governors (from states matched according to population size and density, demographic composition, per capita incomes, geographic proximity, and COVID-19 incidence) …

us (code pays fourni par la source)

Evaluating Large Vision-Language Models for Visual Framing Analysis in News Imagery: A Theory-Driven Benchmark

Linqi Lu, Zihan Wan, Hyerin Kwon, Sang Jung Kim et autres

This study evaluates and compares the effectiveness of multiple large vision-language models (LVLMs) for automated visual framing analysis in the context of news imagery about social movements. Specifically, we evaluate LVLMs (Gemma3-27B, GPT-4.1, InternVL3-14B, InternVL3-38B, and Qwen2.5-VL-72B) against human-annotated ground truth data, …

us (code pays fourni par la source)

Prosocial storytelling: the role of rewards and punishments in shaping inclusive norms through narratives

Linqi Lu, Hyungjin Gill, Karyn Riddle

Building off prior research on entertainment-education and narrative persuasion, the present study compares a narrative story featuring inclusive behaviors toward gay men (that are rewarded) to one featuring homophobic, exclusive behaviors toward gay men (that are punished). Drawing from reinforcement learning models, …

us (code pays fourni par la source)

Cannabis warning labels, sensory marketing, and electronic word-of-mouth: AI-facilitated textual analysis of a randomized experiment among youth and young adults

Linqi Lu, Hyerin Kwon, Wei Wang, Lynne Margalit Cotter et autres

Online marketing of recreational cannabis products, particularly edibles, increasingly employs sensory appeals to attract adolescents and young adults (AYAs). Requiring cannabis warning labels (CWLs) on social media marketing posts is a potentially cost-effective intervention to improve health education and influence online word-of-mouth, …

us (code pays fourni par la source)

Human–Generative AI Interactions and Their Effects on Beliefs About Health Issues: Content Analysis and Experiment (Preprint)

Linqi Lu, Yanshu Sybil Wang, Jiawei Liu, Douglas M. McLeod

UNSTRUCTURED This study examined how interactions with ChatGPT about flu vaccination and climate change influenced users’ beliefs and attitudes.

Pictorial warning labels reduce sharing intentions, blunt self-relevance processes elicited by social media posts promoting cannabis edibles

Matt Minich, Lynne Margalit Cotter, Lauren A. Kriss, Linqi Lu et autres

The implementation of warning labels has been shown to slow the spread of harmful content on social media, but the mechanisms by which these interventions affect individuals' sharing decisions are not yet known. This study sought to establish the efficacy of these …

us (code pays fourni par la source)

Visual Constructs of Conflict and Solidarity: The Role of Visual Framing on Public Perceptions and Engagement Intentions with Social Protests

Linqi Lu, Ran Tao, Hyerin Kwon, Ji-Won Kang et autres

This study investigates the role of visual framing in shaping public perceptions of the Black Lives Matter (BLM) protests through an online experiment, informed by news value and protest paradigm theory. It specifically examines the effects of conflict versus solidarity visual frames …

us (code pays fourni par la source)

Leveraging the Power of ChatGPT: Evaluating Its Effectiveness for Content Analysis and Framing Research in Mass Communication

Hyerin Kwon, Linqi Lu, Ji-Won Kang

This study explores the application of ChatGPT (GPT) to content analysis within the context of framing research, specifically examining its effectiveness in identifying public health, economic stability, and civic vitality frames in COVID-19 press releases. Our methodology is grounded in the Semantic …

Detecting Visual Triggers in Cannabis Imagery: A CLIP-Based Multi-Labeling Framework with Local-Global Aggregation

Linqi Lu, Xianshi Yu, Arpitha Reddy

This study investigates the interplay of visual and textual features in online discussions about cannabis edibles and their impact on user engagement. Leveraging the CLIP model, we analyzed 42,743 images from Facebook (March 1 to August 31, 2021), with a focus on …

The Effects of Numerical Evidence and Message Framing in Communicating Vaccine Efficacy

Linqi Lu, Jiawei Liu, Sang Jung Kim, Ran Tao et autres

To examine the effects of numerical evidence and message framing in communicating vaccine efficacy information about infectious diseases, an online experiment presented to U.S. adults different versions of a vaccination promotional message that vary by numerical vaccine efficacy evidence: (low efficacy rate: …

us (code pays fourni par la source)

mHealth Engagement for Antiretroviral Medication Adherence Among People With HIV and Substance Use Disorders: Observational Study

Ranran Z. Mi, Ellie Fan Yang, Alexander M. Tahk, Adati Tarfa et autres

BACKGROUND: Despite the increasing popularity of mobile health (mHealth) technologies, little is known about which types of mHealth system engagement might affect the maintenance of antiretroviral therapy among people with HIV and substance use disorders. OBJECTIVE: This study aimed to use longitudinal …

us (code pays fourni par la source)