Large language models (LLMs) chatbots like ChatGPT are increasingly used for mental health support. They offer accessible, therapeutic support but also raise concerns about misinformation, over-reliance, and risks in high-stakes contexts of mental health. We crowdsource large-scale users' posts from six major social media platforms to examine how people discuss their interactions with LLM chatbots across different mental health conditions. Through an LLM-assisted pipeline grounded in Value-Sensitive Design (VSD), we mapped the relationships across user-reported sentiments, mental health conditions, perspectives, and values. Our results reveal that the use of LLM chatbots is condition-specific. Users with neurodivergent conditions (e.g., ADHD, ASD) report strong positive sentiments and instrumental or appraisal support, whereas higher-risk disorders (e.g., schizophrenia, bipolar disorder) show more negative sentiments. We further uncover how user perspectives co-occur with underlying values, such as identity, autonomy, and privacy. Finally, we discuss shifting from "one-size-fits-all" chatbot design toward condition-specific, value-sensitive LLM design.

Peer Reviewed

Abstract Teaching has often been characterized as a “labor of love.” Despite their passion, teachers often find themselves underpaid and unrecognized, leading them to engage in taxing emotional labor. Emotional labor in traditional educational settings is not new. However, teaching as online gig work has become increasingly data-driven and transnational. With the burgeoning popularity of online educational industries in China, U.S. teachers are entering the transitional gig economy to teach students, parents, and educational standards in cross-cultural contexts. Based on 24 semi-structured interviews with U.S. teachers who worked on Chinese gig-education platforms, this paper documents their challenges and how such platforms reconfigure their emotional labor, enabling them to reaffirm their identities as teachers and caregivers and rekindle the passion that gave their lives purpose and meaning. However, these platforms, underpinned by Chinese cultural values and data-driven technologies (e.g., datafication, algorithms, and surveillance) — which we dub transnational emotional computing — demand emergent forms of emotional labor with which participants must contend. This work contributes to a human-centered conceptualization of identity alignment and carries theoretical and design implications for the future of transnational gig platforms, especially for cross-cultural digital knowledge labor.

Content creators with marginalized identities are disproportionately affected by shadowbanning on social media platforms, which impacts their economic prospects online. Through a diary study and interviews with eight marginalized content creators who are women, pole dancers, plus size, and/or LGBTQIA+, this paper examines how content creators with marginalized identities experience shadowbanning. We highlight the labor and economic inequalities of shadowbanning, and the resulting invisible online labor that marginalized creators often must perform. We identify three types of invisible labor that marginalized content creators engage in to mitigate shadowbanning and sustain their online presence: mental and emotional labor, misdirected labor, and community labor. We conclude that even though marginalized content creators engaged in cross-platform collaborative labor and personal mental/emotional labor to mitigate the impacts of shadowbanning, it was insufficient to prevent uncertainty and economic precarity created by algorithmic opacity and ambiguity.

Generative AI has exhibited considerable potential to transform various industries and public life. The role of news media coverage of generative AI is pivotal in shaping public perceptions and judgments about this significant technological innovation. This paper provides in-depth analysis and rich insights into the temporal and spatial distribution of topics, sentiment, and substantive themes within global news coverage focusing on the latest emerging technology—generative AI. We collected a comprehensive dataset of English news articles (January 2018 to November 2023, N = 24,827) through ProQuest databases. For topic modeling, we employed the BERTopic technique and combined it with qualitative coding to identify semantic themes. Subsequently, sentiment analysis was conducted using the RoBERTa-base model. Analysis of temporal patterns in the data reveals notable variability in coverage across key topics—business, corporate technological development, regulation and security, and education—with spikes in articles coinciding with major AI developments and policy discussions. Sentiment analysis shows a predominantly neutral to positive media stance, with the business-related articles exhibiting more positive sentiment, while regulation and security articles receive a reserved, neutral to negative sentiment. Our study offers a valuable framework to investigate global news discourse and evaluate news attitudes and themes related to emerging technologies.

Migrants experience unique needs and use social media, in part, to address them. While prior work has primarily focused on migrant populations who are vulnerable socio-economically and legally, less is known about how highly educated migrant populations use social media. Additionally, a growing body of work focuses on algorithmic perceptions and resistance, primarily from laypersons' perspectives rather than people with high degrees of algorithmic literacy. To address these gaps, we draw from interviews with 20 Chinese-born migrant technology professionals. We found that social media played an integral role in helping participants meet their unique needs but that participants perceived social media algorithms to negatively shape the content they consumed, which ultimately influenced their mobility-related aspirations and goals. We discuss how findings challenge the promise of algorithmic literacy and contribute to a human-centered conceptualization of algorithmic mobility as socially and algorithmically produced motion that concerns the movement of physical bodies and interactions as well as associated digital movement. Specifically, we introduce a fourth dimension of algorithmic mobility: algorithmically curated content on social media and elsewhere based on facets of users' identities directly influences users' mobility-related aspirations and goals, such as how, when, and where they go. Finally, we call for transnational policy interventions related to algorithms and highlight design considerations around content moderation, algorithmic user-control, and contestability.

Major life events can cause great upheaval in one's life. Many people perceive their identities to change due to major life events. During identity shifts, impression management and self-presentation, online communities, and social media affordances can allow individuals to better facilitate their experiences. To examine how people perceive their identity to change during major events and how they use social media in the process, we interviewed 28 participants who recently experienced major life events. We found that many people perceived their identity to change through various avenues that they felt were important to their identity: mental processes, identity roles, and identity fulfillment. However, some people perceive their identity to be maintained rather than changed. During identity changes or maintenance, participants utilized impression management and self-presentation to curate their online presence. Participants also used online communities to build relationships with similar others or virtual friends and enable more connections via what we call the domino effect. Social media sites also provided the affordances of editability, visibility control, and spreadability, which can help ease life transition and identity change processes.

In August 2020, the U.S. President issued an executive order to ban the Chinese-based social platform WeChat, alleging that WeChat posed a national security risk. WeChat is a vital application for Chinese diasporic communities in the United States. The ban's status was uncertain for several months before it was temporarily halted and later revoked in 2021. Through interviews with 15 WeChat users and online participant observation, this study examines the anticipated impacts of the potential WeChat ban and participants' reactions. We find that participants described negative consequences of the potential ban, including adverse network and economic effects and disruption of community-building efforts. We also find that many participants considered WeChat to be critical infrastructure in the United States, as it has become an indispensable part of their daily lives. To frame participants' experiences, we introduce the concept of infrastructural migration-the process of users relocating to another digital media service that embodies the properties and functions of infrastructure or moving to an assemblage of different applications that meet their infrastructural needs separately. We then discuss implications for designing for infrastructural migration and future considerations for HCI research with diasporic communities.

Some life transitions can be difficult to discuss on social media, especially with networks of known ties, due to challenges such as stigmatization. Separate online networks can provide alternative spaces to discuss life transitions. To understand why and how people turn to separate networks, we interviewed 28 participants who had recently experienced life transitions. While prior research tends to focus on one life transition in isolation, this work examines social media sharing behaviors across a wide variety of life transitions. We describe how people often turn to separate networks during life transitions due to challenges faced in networks of known ties, yet encounter new challenges such as difficulty locating these networks. We describe support from waiting contributors and virtual friends. Finally, we provide insight into how online separate networks can be better designed through enhancing search functionality, promoting contribution, and providing context-sensitive templates for sharing in online spaces.

People often strive to present themselves authentically on social media, but this may not be possible for everyone. To understand how people view online authenticity, how it relates to social media sharing behaviors, and whether it is achievable, we interviewed 28 social media users who had recently experienced major life transitions. We found that to many participants, online authenticity required presenting a consistent, positive, and "true" self across online and offline contexts. Though most stated that they considered online authenticity achievable, their social media self-disclosure behaviors around life transitions revealed what we call the online authenticity paradox: people strive to achieve online authenticity, yet because doing so requires sharing negative experiences on social media, online authenticity is often unreachable, or is possible only at great personal cost - especially for those with marginalized identities and difficult life experiences.