An official website of the United States government
The factors influencing people’s food decisions, such as one’s mood and eating environment, are important information to foster self-reflection and to develop personalized healthy diet. But, it is difficult to consistently collect them due to the heavy data capture burden. In this work, we examine how speech input supports capturing everyday food practice through a week-long data collection study (N = 11). We deployed FoodScrap, a speech-based food journaling app that allows people to capture food components, preparation methods, and food decisions. Using speech input, participants detailed their meal ingredients and elaborated their food decisions by describing the eating moments, explaining their eating strategy, and assessing their food practice. Participants recognized that speech input facilitated self-reflection, but expressed concerns around re-recording, mental load, social constraints, and privacy. We discuss how speech input can support low-burden and reflective food journaling and opportunities for effectively processing and presenting large amounts of speech data.
more »
« less
Understanding People's Perceptions of Approaches to Semi-Automated Dietary Monitoring
The respective benefits and drawbacks of manual food journaling and automated dietary monitoring (ADM) suggest the value of semi-automated journaling systems combining the approaches. However, the current understanding of how people anticipate strategies for implementing semi-automated food journaling systems is limited. We therefore conduct a speculative survey study with 600 responses, examining how people anticipate approaches to automatic capture and prompting for details. Participants feel the location and detection capability of ADM sensors influences anticipated physical, social, and privacy burdens. People more positively anticipate prompts which contain information relevant to their journaling goals, help them recall what they ate, and are quick to respond to. Our work suggests a tradeoff between ADM systems' detection performance and anticipated acceptability, with sensors on facial areas having higher performance but lower acceptability than sensors in other areas and more usable prompting methods like those containing specific foods being more challenging to produce than manual reminders. We suggest opportunities to improve higher-acceptability, lower-accuracy ADM sensors, select approaches based on individual and practitioner journaling needs, and better describe capabilities to potential users.
more »
« less
- Award ID(s):
- 1850389
- PAR ID:
- 10607235
- Publisher / Repository:
- Association for Computing Machinery (ACM)
- Date Published:
- Journal Name:
- Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies
- Volume:
- 6
- Issue:
- 3
- ISSN:
- 2474-9567
- Format(s):
- Medium: X Size: p. 1-27
- Size(s):
- p. 1-27
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
This paper introduces reAnalyst, a framework designed to facilitate the study of reverse engineering (RE) practices through the semi-automated annotation of RE activities across various RE tools. By integrating tool-agnostic data collection of screenshots, keystrokes, active processes, and other types of data during RE experiments with semi-automated data analysis and generation of annotations, reAnalyst aims to overcome the limitations of traditional RE studies that rely heavily on manual data collection and subjective analysis. The framework enables more efficient data analysis, which will in turn allow researchers to explore the effectiveness of protection techniques and strategies used by reverse engineers more comprehensively and efficiently. Experimental evaluations validate the framework’s capability to identify RE activities from a diverse range of screenshots with varied complexities. Observations on past experiments with our framework as well as a survey among reverse engineers provide further evidence of the acceptability and practicality of our approach.more » « less
-
Studies of personal informatics systems primarily examine people's use or non-use, but people often leverage other technology towards their long-term behavior change processes such as social platforms. We explore how tracking technologies and social platforms together help people build healthy eating behaviors by interviewing 18 people who use Chinese food journaling apps. We contribute a Model of Socially Sustained Self-Tracking in personal informatics, building on the past model of Personal Informatics and the learning components of Social Cognitive Theory. The model illustrates how people get advice from social platforms on when and how to track, transfer data to and apply knowledge from social platforms, evolve to use social platforms after tracking, and occasionally resume using tracking tools. Observational learning and enactive learning are central to these processes, with social technologies helping people to gain deeper and more reliable domain knowledge. We discuss how lapsing and abandoning of tracking can be viewed as evolving to social platforms, offering recommendations for how technology can better facilitate this evolution.more » « less
-
Food insecurity is a problem that should not be overlooked in America. In 2022, about 1.3 billion people were food insecure, an increase of 10% from the previous year. Food deserts, an area with low income and low access to nutritious foods, can be characterized by 5A’s: availability, accessibility, accommodation, affordability, and acceptability. As more investments go into building infrastructure for population growth, the local food industry must expand for both current and new residents. One strategy to combat food deserts is to use the Internet and e-commerce like online food services can contribute to solving food insecurity. From Generation X to Millennials to Generation Z, the adoption of the Internet is rapid. However, these services have additional costs for the consumer. The goal of this research was to examine the current e-commerce solutions to food deserts in a local area and review the literature on how e-commerce can alleviate food deserts. Data were collected from published government and company sites. Results reveal Internet accessibility continues to be an issue for reliable e-commerce use. E-commerce can alleviate food deserts by reducing the cost for both consumers and businesses, accommodating various groups of people, and focusing on rural areas.more » « less
-
Abstract Deep generative models have shown significant promise in improving performance in design space exploration. But there is limited understanding of their interpretability, a necessity when model explanations are desired and problems are ill-defined. Interpretability involves learning design features behind design performance, called designer learning. This study explores human–machine collaboration’s effects on designer learning and design performance. We conduct an experiment (N = 42) designing mechanical metamaterials using a conditional variational autoencoder. The independent variables are: (i) the level of automation of design synthesis, e.g., manual (where the user manually manipulates design variables), manual feature-based (where the user manipulates the weights of the features learned by the encoder), and semi-automated feature-based (where the agent generates a local design based on a start design and user-selected step size); and (ii) feature semanticity, e.g., meaningful versus abstract features. We assess feature-specific learning using item response theory and design performance using utopia distance and hypervolume improvement. The results suggest that design performance depends on the subjects’ feature-specific knowledge, emphasizing the precursory role of learning. The semi-automated synthesis locally improves the utopia distance. Still, it does not result in higher global hypervolume improvement compared to manual design synthesis and reduced designer learning compared to manual feature-based synthesis. The subjects learn semantic features better than abstract features only when design performance is sensitive to them. Potential cognitive constructs influencing learning in human–machine collaborative settings are discussed, such as cognitive load and recognition heuristics.more » « less
