Shuo Niu

Yao Lyu, He Zhang, Shuo Niu et al.

Content creators increasingly utilize generative artificial intelligence (Gen-AI) on platforms such as YouTube, TikTok, Instagram, and various blogging sites to produce imaginative images, AI-generated videos, and articles using Large Language Models (LLMs). Despite its growing popularity, there remains an underexplored area concerning the specific domains where AI-generated content is being applied, and the methodologies content creators employ with Gen-AI tools during the creation process. This study initially explores this emerging area through a qualitative analysis of 68 YouTube videos demonstrating Gen-AI usage. Our research focuses on identifying the content domains, the variety of tools used, the activities performed, and the nature of the final products generated by Gen-AI in the context of user-generated content.

Jiaying Lizzy Liu, Yunlong Wang, Yao Lyu et al.

Despite the growing interest in leveraging Large Language Models (LLMs) for content analysis, current studies have primarily focused on text-based content. In the present work, we explored the potential of LLMs in assisting video content analysis by conducting a case study that followed a new workflow of LLM-assisted multimodal content analysis. The workflow encompasses codebook design, prompt engineering, LLM processing, and human evaluation. We strategically crafted annotation prompts to get LLM Annotations in structured form and explanation prompts to generate LLM Explanations for a better understanding of LLM reasoning and transparency. To test LLM's video annotation capabilities, we analyzed 203 keyframes extracted from 25 YouTube short videos about depression. We compared the LLM Annotations with those of two human coders and found that LLM has higher accuracy in object and activity Annotations than emotion and genre Annotations. Moreover, we identified the potential and limitations of LLM's capabilities in annotating videos. Based on the findings, we explore opportunities and challenges for future research and improvements to the workflow. We also discuss ethical concerns surrounding future studies based on LLM-assisted video analysis.

Shuo Niu, Hugh S. Manon, Ava Bartolome et al.

ASMR (Autonomous Sensory Meridian Response) has grown to immense popularity on YouTube and drawn HCI designers' attention to its effects and applications in design. YouTube ASMR creators incorporate visual elements, sounds, motifs of touching and tasting, and other scenarios in multisensory video interactions to deliver enjoyable and relaxing experiences to their viewers. ASMRtists engage viewers by social, physical, and task attractions. Research has identified the benefits of ASMR in mental wellbeing. However, ASMR remains an understudied phenomenon in the HCI community, constraining designers' ability to incorporate ASMR in video-based designs. This work annotates and analyzes the interaction modalities and parasocial attractions of 2663 videos to identify unique experiences. YouTube comment sections are also analyzed to compare viewers' responses to different ASMR interactions. We find that ASMR videos are experiences of multimodal social connection, relaxing physical intimacy, and sensory-rich activity observation. Design implications are discussed to foster future ASMR-augmented video interactions.

Shuo Niu, D. Scott McCrickard, Steve Harrison

Themed collocated events, such as conferences, workshops, and seminars, invite people with related life experiences to connect with each other. In this era when people record lives through the Internet, individual experiences exist in different forms of digital contents. People share digital life records during collocated events, such as sharing blogs they wrote, Twitter posts they forwarded, and books they have read. However, connecting experiences during collocated events are challenging. Not only one is blind to the large contents of others, identifying related experiential items depends on how well experiences are retrieved. The collection of personal contents from all participants forms a valuable group repository, from which connections between experiences can be mined. Visualizing same or related experiences inspire conversations and support social exchange. Common topics in group content also help participants generate new perspectives about the collocated group. Advances in machine learning and data visualization provide automated approaches to process large data and enable interactions with data repositories. This position paper promotes the idea of event mining: how to utilize state-of-the-art data processing and visualization techniques to design event mining systems for connecting experiences during collocated activities. We discuss empirical and constructive problems in this design space, and our preliminary study of deploying a tabletop-based system, BlogCloud, which supports experience re-visitation and exchange with machine-learning and data visualization.

Lindah Kotut, Michael Horning, Derek Haqq et al.

This paper compares the needs of groups and communities in outdoor settings, seeking to identify subtle but important differences in the ways that their needs can be supported. We first examine the questions of who uses technology in outdoor settings, what their technological uses and needs are, and what conflicts exist between different trail users regarding technology use and experience. We then consider selected categories of people to understand their distinct needs when acting as groups and as communities. We conclude that it is important to explore the tensions between groups and communities to identify design opportunities.