Storytelling and Sense-Making

会議の名前
CHI 2025
Supporting Mobile Reading While Walking with Automatic and Customized Font Size Adaptations
要旨

The pervasive use of mobile devices for information consumption makes reading on-the-go an unavoidable daily occurrence, whereby walking creates a natural situational impairment for reading. In this work, we quantify the impact of walking on reading performance and compare automatic system adaptations with user customizations for mitigating these impacts. We collected user interactions and mobile sensor data of reading while walking in a controlled lab study with 45 participants. We found that automatic font size adjustment by viewing distance mitigated the performance degradation from walking, yielding faster reading speed and increased comfort. Furthermore, exposure to the automatic adaptation functionality influences user customization behavior and preferences for reading while walking. We discuss implications and provide design suggestions for personalizing interfaces when reading on-the-go, including blending system recommendation with user customization, offering multiple points of customization through appropriately-timed prompts, and refining recommendations based on observed preferences.

著者
Junhan Kong
University of Washington, Seattle, Washington, United States
Jacob O.. Wobbrock
University of Washington, Seattle, Washington, United States
Tianyuan Cai
Adobe Research, San Francisco, California, United States
Zoya Bylinskii
Adobe Research, Cambridge, Massachusetts, United States
DOI

10.1145/3706598.3713367

論文URL

https://dl.acm.org/doi/10.1145/3706598.3713367

動画
Characterizing LLM-Empowered Personalized Story Reading and Interaction for Children: Insights From Multi-Stakeholders' Perspective
要旨

Personalized interaction is highly valued by parents in their story-reading activities with children. While AI-empowered story-reading tools have been increasingly used, their abilities to support personalized interaction with children are still limited. Recent advances in large language models (LLMs) show promise in facilitating personalized interactions, but little is known about how to effectively and appropriately use LLMs to enhance children's personalized story-reading experiences. This work explores this question through a design-based study. Drawing on a formative study, we designed and developed StoryMate, an LLM-empowered personalized interactive story-reading tool for children, following an empirical study with children, parents, and education experts. Our participants valued the personalized features in StoryMate, and also highlighted the need to support personalized content, guiding mechanisms, reading context variations, and interactive interfaces. Based on these findings, we propose a series of design recommendations for better using LLMs to empower children's personalized story reading and interaction.

著者
Jiaju Chen
East China Normal University, Shanghai, China
Minglong Tang
East China Normal University, Shanghai, China
Yuxuan Lu
Northeastern University, Boston, Massachusetts, United States
Bingsheng Yao
Northeastern University, Boston, Massachusetts, United States
Elissa Fan
Lexington High School, Lexington, Massachusetts, United States
Xiaojuan Ma
Hong Kong University of Science and Technology, Hong Kong, Hong Kong
Ying Xu
University of Michigan, Ann Arbor, Michigan, United States
Dakuo Wang
Northeastern University, Boston, Massachusetts, United States
Yuling Sun
East China Normal University, Shanghai, China
Liang He
East China Normal University, Shanghai, China
DOI

10.1145/3706598.3713275

論文URL

https://dl.acm.org/doi/10.1145/3706598.3713275

動画
Influencer: Empowering Everyday Users in Creating Promotional Posts via AI-infused Exploration and Customization
要旨

Creating promotional posts on social platforms enables everyday users to disseminate their creative outcomes, engage in community exchanges, or generate additional income from micro-businesses. However, crafting eye-catching posts with appealing images and effective captions can be challenging and time-consuming for everyday users since they are mostly design novices. We propose Influencer, an interactive tool that helps novice creators quickly generate ideas and create high-quality promotional post designs through AI. Influencer offers a multi-dimensional recommendation system for ideation through example-based image and caption suggestions. Further, Influencer implements a holistic promotional post-design system supporting context-aware exploration considering brand messages and user-specified design constraints, flexible fusion of content, and a mind-map-like layout for idea tracking. Our user study, comparing the system with industry-standard tools, along with two real-life case studies, indicates that Influencer is effective in assisting design novices to generate ideas as well as creative and diverse promotional posts with user-friendly interaction.

著者
Xuye Liu
University of Waterloo, Waterloo, Ontario, Canada
Annie Sun
University of Waterloo, Waterloo, Ontario, Canada
Pengcheng An
Southern University of Science and Technology, Shenzhen, China
Tengfei Ma
Stony Brook University, Stony Brook, New York, United States
Jian Zhao
University of Waterloo, Waterloo, Ontario, Canada
DOI

10.1145/3706598.3713309

論文URL

https://dl.acm.org/doi/10.1145/3706598.3713309

動画
Strollytelling: Coupling Animation with Physical Locomotion to Explore Immersive Data Stories
要旨

With a growing interest in immersive data storytelling, there is an opportunity to explore story presentation and navigation techniques in virtual reality (VR) that can engage audiences as much as data story techniques have on conventional displays. We propose and explore “strolly”telling, a novel data storytelling technique that maps the story progression with the user/audience’s physical locomotion. Inspired by the conventional web-based technique for scrolling-based stories (i.e. scrollytelling), our technique tightly couples the user’s position in physical space to the animation frame of the data story. This technique leverages the natural tendency of humans to "walk and talk" while telling a story and requires users to engage with the content actively. This work defines strollytelling, design considerations, and a preliminary process for designing a strollytelling experience. A user study comparing strollytelling with virtual locomotion found that strollytelling was preferred by most participants and had higher self-reported immersion. We conclude with opportunities for strollytelling within the immersive data storytelling landscape.

受賞
Honorable Mention
著者
RADHIKA PANKAJ JAIN
University of South Australia, Adelaide, Australia
Adam Drogemuller
University of South Australia, Mawson Lakes, South Australia, Australia
Kadek Ananta Satriadi
Monash University, Melbourne, Australia
Ross Smith
University of South Australia, Mawson Lakes, SA, Australia
Andrew Cunningham
University of South Australia, Adelaide, Australia
DOI

10.1145/3706598.3713132

論文URL

https://dl.acm.org/doi/10.1145/3706598.3713132

動画
Finding Needles in Document Haystacks: Augmenting Serendipitous Claim Retrieval Workflows
要旨

Preliminary exploration of vast text corpora for generating and validating hypotheses, typical in academic inquiry, requires flexible navigation and rapid validation of claims. Navigating the corpus by titles, summaries, and abstracts might neglect information, whereas identifying the relevant context-specific claims through in-depth reading is unfeasible with rapidly increasing publication numbers. Our paper identifies three typical user pathways for hypothesis exploration and operationalizes sentence-based retrieval combined with effective contextualization and provenance tracking in a unified workflow. We contribute an interface that augments the previously laborious tasks of claim identification and consistency checking using NLP techniques while balancing user control and serendipity. Use cases, expert interviews, and a user study with 10 participants demonstrate how the proposed workflow enables users to traverse literature corpora in novel and efficient ways. For the evaluation, we instantiate the tool within two independent domains, providing novel insights into the analysis of political discourse and medical research.

著者
Moritz Dück
ETH Zurich, Zuerich, Switzerland
Steffen Holter
ETH Zurich, Zurich, Switzerland
Robin Shing Moon. Chan
ETH Zürich, Zürich, Switzerland
Rita Sevastjanova
ETH Zurich, Zurich, Switzerland
Mennatallah El-Assady
ETH Zürich, Zürich, Switzerland
DOI

10.1145/3706598.3713715

論文URL

https://dl.acm.org/doi/10.1145/3706598.3713715

動画
Jupybara: Operationalizing a Design Space for Actionable Data Analysis and Storytelling with LLMs
要旨

Mining and conveying actionable insights from complex data is a key challenge of exploratory data analysis (EDA) and storytelling. To address this challenge, we present a design space for actionable EDA and storytelling. Synthesizing theory and expert interviews, we highlight how semantic precision, rhetorical persuasion, and pragmatic relevance underpin effective EDA and storytelling. We also show how this design space subsumes common challenges in actionable EDA and storytelling, such as identifying appropriate analytical strategies and leveraging relevant domain knowledge. Building on the potential of LLMs to generate coherent narratives with commonsense reasoning, we contribute Jupybara, an AI-enabled assistant for actionable EDA and storytelling implemented as a Jupyter Notebook extension. Jupybara employs two strategies—design-space-aware prompting and multi-agent architectures—to operationalize our design space. An expert evaluation confirms Jupybara’s usability, steerability, explainability, and reparability, as well as the effectiveness of our strategies in operationalizing the design space framework with LLMs.

著者
Huichen Will. Wang
University of Washington, Seattle, Washington, United States
Larry Birnbaum
Northwestern University, Evanston, Illinois, United States
Vidya Setlur
Tableau Research, Palo Alto, California, United States
DOI

10.1145/3706598.3713913

論文URL

https://dl.acm.org/doi/10.1145/3706598.3713913

動画