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.
https://dl.acm.org/doi/10.1145/3706598.3713367
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.
https://dl.acm.org/doi/10.1145/3706598.3713275
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.
https://dl.acm.org/doi/10.1145/3706598.3713309
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.
https://dl.acm.org/doi/10.1145/3706598.3713132
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.
https://dl.acm.org/doi/10.1145/3706598.3713715
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.
https://dl.acm.org/doi/10.1145/3706598.3713913