3. AI & Automation

会議の名前
UIST 2024
Towards Automated Accessibility Report Generation for Mobile Apps
要旨

ACM DL: https://dl.acm.org/doi/full/10.1145/3674967 Many apps have basic accessibility issues, like missing labels or low contrast. To supplement manual testing, automated tools can help developers and QA testers find basic accessibility issues, but they can be laborious to use or require writing dedicated tests. To motivate our work, we interviewed eight accessibility QA professionals at a large technology company. From these interviews, we synthesized three design goals for accessibility report generation systems. Motivated by these goals, we developed a system to generate whole app accessibility reports by combining varied data collection methods (e.g., app crawling, manual recording) with an existing accessibility scanner. Many such scanners are based on single-screen scanning, and a key problem in whole app accessibility reporting is to effectively de-duplicate and summarize issues collected across an app. To this end, we developed a screen grouping model with 96.9% accuracy (88.8% F1-score) and UI element matching heuristics with 97% accuracy (98.2% F1-score). We combine these technologies in a system to report and summarize unique issues across an app, and enable a unique pixel-based ignore feature to help engineers and testers better manage reported issues across their app’s lifetime. We conducted a user study where 19 accessibility engineers and testers used multiple tools to create lists of prioritized issues in the context of an accessibility audit. Our system helped them create lists they were more satisfied with while addressing key limitations of current accessibility scanning tools.

著者
Amanda Swearngin
Apple, Seattle, Washington, United States
Jason Wu
Apple, Seattle, Washington, United States
Xiaoyi Zhang
Apple Inc, Seattle, Washington, United States
Esteban Gomez
Apple Inc, San Francisco, California, United States
Jen Coughenour
Apple Inc, Portland, Oregon, United States
Rachel Stukenborg
Apple Inc, Cupertino, California, United States
Bhavya Garg
Apple Inc, Cupertino, California, United States
Greg Hughes
Apple Inc, Cupertino, California, United States
Adriana Hilliard
Apple Inc, Cupertino, California, United States
Jeffrey P. Bigham
Apple, Pittsburgh, Pennsylvania, United States
Jeffrey Nichols
Apple Inc, San Diego, California, United States
Memolet: Reifying the Reuse of User-AI Conversational Memories
要旨

As users engage more frequently with AI conversational agents, conversations may exceed their memory capacity, leading to failures in correctly leveraging certain memories for tailored responses. However, in finding past memories that can be reused or referenced, users need to retrieve relevant information in various conversations and articulate to the AI their intention to reuse these memories. To support this process, we introduce Memolet, an interactive object that reifies memory reuse. Users can directly manipulate Memolet to specify which memories to reuse and how to use them. We developed a system demonstrating Memolet's interaction across various memory reuse stages, including memory extraction, organization, prompt articulation, and generation refinement. We examine the system's usefulness with an N=12 within-subject study and provide design implications for future systems that support user-AI conversational memory reusing.

著者
Ryan Yen
University of Waterloo, Waterloo, Ontario, Canada
Jian Zhao
University of Waterloo, Waterloo, Ontario, Canada
論文URL

https://doi.org/10.1145/3654777.3676388

動画
VIME: Visual Interactive Model Explorer for Identifying Capabilities and Limitations of Machine Learning Models for Sequential Decision-Making
要旨

Ensuring that Machine Learning (ML) models make correct and meaningful inferences is necessary for the broader adoption of such models into high-stakes decision-making scenarios. Thus, ML model engineers increasingly use eXplainable AI (XAI) tools to investigate the capabilities and limitations of their ML models before deployment. However, explaining sequential ML models, which make a series of decisions at each timestep, remains challenging. We present Visual Interactive Model Explorer (VIME), an XAI toolbox that enables ML model engineers to explain decisions of sequential models in different ``what-if'' scenarios. Our evaluation with 14 ML experts, who investigated two existing sequential ML models using VIME and a baseline XAI toolbox to explore ``what-if'' scenarios, showed that VIME made it easier to identify and explain instances when the models made wrong decisions compared to the baseline. Our work informs the design of future interactive XAI mechanisms for evaluating sequential ML-based decision support systems.

著者
Anindya Das Antar
University of Michigan, Ann Arbor, Michigan, United States
Somayeh Molaei
University of Michigan, Ann Arbor, Michigan, United States
Yan-Ying Chen
Toyota Research Institute, Los Altos, California, United States
Matthew L. Lee
Toyota Research Institute, Los Altos, California, United States
Nikola Banovic
University of Michigan, Ann Arbor, Michigan, United States
論文URL

https://doi.org/10.1145/3654777.3676323

動画
SERENUS: Alleviating Low-Battery Anxiety Through Real-time, Accurate, and User-Friendly Energy Consumption Prediction of Mobile Applications
要旨

Low-battery anxiety has emerged as a result of growing dependence on mobile devices, where the anxiety arises when the battery level runs low. While battery life can be extended through power-efficient hardware and software optimization techniques, low-battery anxiety will remain a phenomenon as long as mobile devices rely on batteries. In this paper, we investigate how an accurate real-time energy consumption prediction at the application-level can improve the user experience in low-battery situations. We present Serenus, a mobile system framework specifically tailored to predict the energy consumption of each mobile application and present the prediction in a user-friendly manner. We conducted user studies using Serenus to verify that highly accurate energy consumption predictions can effectively alleviate low-battery anxiety by assisting users in planning their application usage based on the remaining battery life. We summarize requirements to mitigate users’ anxiety, guiding the design of future mobile system frameworks.

著者
Sera Lee
KAIST, Daejeon, Korea, Republic of
Dae R. Jeong
KAIST, Daejeon, Korea, Republic of
Junyoung Choi
KAIST, Daejeon, Korea, Republic of
Jaeheon Kwak
KAIST, Daejeon, Korea, Republic of
Seoyun Son
KAIST, Daejeon, Korea, Republic of
Jean Y. Song
DGIST, Daegu, Korea, Republic of
Insik Shin
KAIST, Daejeon, Korea, Republic of
論文URL

https://doi.org/10.1145/3654777.3676437

動画