Nicola Dell

Yours is better!: participant response bias in HCI

Although HCI researchers and practitioners frequently work with groups of people that differ significantly from themselves, little attention has been paid to the effects these differences have on the evaluation of HCI systems. Via 450 interviews in Bangalore, India, we measure participant response bias due to interviewer demand characteristics and the role of social and demographic factors in influencing that bias. We find that respondents are about 2.5x more likely to prefer a technological artifact they believe to be developed by the interviewer, even when the alternative is identical. When the interviewer is a foreign researcher requiring a translator, the bias towards the interviewers artifact increases to 5x. In fact, the interviewers artifact is preferred even when it is degraded to be obviously inferior to the alternative. We conclude that participant response bias should receive more attention within the CHI community, especially when designing for underprivileged populations.

Open data kit 2.0: expanding and refining information services for developing regions

Open Data Kit (ODK) is an open-source, modular toolkit that enables organizations to build application-specific information services for use in resource-constrained environments. ODK is one of the leading data collection solutions available and has been deployed by a wide variety of organizations in dozens of countries around the world. This paper discusses how recent feedback from users and developers led us to redesign the ODK system architecture. Specifically, the design principles for ODK 2.0 focus on: 1) favoring runtime languages over compile time languages to make customizations easier for individuals with limited programming experience; 2) implementing basic data structures as single rows within a table of data; 3) storing that data in a database that is accessible across applications and client devices; and 4) increasing the diversity of input types by enabling new data input methods from sensors. We discuss how these principles have led to the refinement of the existing ODK tools, and the creation of several new tools that aim to improve the toolkit, expand its range of applications, and make it more customizable by users.

Digitizing paper forms with mobile imaging technologies

In low-resource settings in developing countries, most records are still captured and maintained using paper forms. Despite a recent proliferation of digital data collection systems, paper forms remain a trusted, low-cost and ubiquitous medium that will continue to be utilized in these communities for years to come. However, it can be challenging to aggregate, share, and analyze the data collected using paper forms. This paper presents mScan, a mobile smartphone application that uses computer vision to capture data from paper forms that use a multiple choice or bubble format. The initial mScan implementation targets the task of digitizing paper forms used to record vaccine statistics in rural health centers in Mozambique. We have evaluated the accuracy and performance of mScan under a variety of different environmental conditions, and our results show that mScan is a robust tool that is capable of accurately capturing and digitizing data from paper forms.

Towards a point-of-care diagnostic system: automated analysis of immunoassay test data on a cell phone

Many of the diagnostic tests administered in well-funded clinical laboratories are inappropriate for point-of-care testing in low-resource environments. As a result, inexpensive, portable immunoassay tests have been developed to facilitate the rapid diagnosis of many diseases common to developing countries. However, manually analyzing the test results at the point of care may be complex and error-prone for untrained users reading test results by eye, and providing methods for automatically processing these tests could significantly increase their utility. In this paper, we present a mobile application that automatically quantifies immunoassay test data on a smart phone. The speed and accuracy demonstrated by the application suggest that cell-phone based analysis could aid disease diagnosis at the point of care.

Social Media Platforms for Low-Income Blind People in India

We present the first analysis of the use and non-use of social media platforms by low-income blind users in rural and peri-urban India. Using a mixed-methods approach of semi-structured interviews and observations, we examine the benefits received by low-income blind people from Facebook, Twitter and WhatsApp and investigate constraints that impede their social media participation. We also present a detailed analysis of how low-income blind people used a voice-based social media platform deployed in India that received significant traction from low-income people in rural and peri-urban areas. In eleven-weeks of deployment, fifty-three blind participants in our sample collectively placed 4784 voice calls, contributed 1312 voice messages, cast 33,909 votes and listened to the messages 46,090 times. Using a mixed-methods analysis of call logs, qualitative interviews, and phone surveys, we evaluate the strengths and weaknesses of the platform and benefits it offered to low-income blind people.

Yum-Me: A Personalized Nutrient-Based Meal Recommender System

Nutrient-based meal recommendations have the potential to help individuals prevent or manage conditions such as diabetes and obesity. However, learning people’s food preferences and making recommendations that simultaneously appeal to their palate and satisfy nutritional expectations are challenging. Existing approaches either only learn high-level preferences or require a prolonged learning period. We propose Yum-me, a personalized nutrient-based meal recommender system designed to meet individuals’ nutritional expectations, dietary restrictions, and fine-grained food preferences. Yum-me enables a simple and accurate food preference profiling procedure via a visual quiz-based user interface and projects the learned profile into the domain of nutritionally appropriate food options to find ones that will appeal to the user. We present the design and implementation of Yum-me and further describe and evaluate two innovative contributions. The first contriution is an open source state-of-the-art food image analysis model, named FoodDist. We demonstrate FoodDist’s superior performance through careful benchmarking and discuss its applicability across a wide array of dietary applications. The second contribution is a novel online learning framework that learns food preference from itemwise and pairwise image comparisons. We evaluate the framework in a field study of 227 anonymous users and demonstrate that it outperforms other baselines by a significant margin. We further conducted an end-to-end validation of the feasibility and effectiveness of Yum-me through a 60-person user study, in which Yum-me improves the recommendation acceptance rate by 42.63%.

Integrating ODK Scan into the community health worker supply chain in Mozambique

We describe our experiences integrating ODK Scan into the community health worker (CHW) supply chain in Mozambique. ODK Scan is a mobile application that uses computer vision techniques to digitize data from paper forms. The application automatically classifies machine-readable data types, like bubbles and checkboxes, and assists users with the manual entry of handwritten text and numbers. We designed an intervention that uses paper forms in conjunction with ODK Scan to monitor CHW usage of essential health commodities, finding that the application is capable of providing supervisors and stakeholders with important information regarding health commodity availability in the field. Specifically, we (1) detail our experiences integrating ODK Scan into the health worker supply chain in Mozambique, with particular emphasis on the critical (and often under-reported) role of practitioners; (2) evaluate the impact of the technology at multiple levels of the information hierarchy, providing quantitative and qualitative data that exposes the benefits, challenges and limitations of the technology; and (3) share lessons learned and provide actionable guidance to researchers and practitioners interested in ODK Scan or other systems that bridge the gap between paper-based and digital data collection.

Paper-Digital Workflows in Global Development Organizations

Global development organizations rely on the essential affordances provided by both paper and digital materials to navigate hurdles posed by poor infrastructure, low connectivity, linguistic differences, and other socioeconomic constraints that render communication and collaboration challenging. This paper examines the collaborative practices around paper-digital workflows within global development organizations operating in low-resource environments. We use a mixed methods approach to gather data from 23 organizations in 16 countries. Our findings show the tensions that arise between the ubiquitousness of paper and the desirability of digitized data, and highlight the challenges associated with transitioning information several times between paper and digital materials. We also reveal design opportunities for new tools to bridge the gap between paper-based and digital information in low-resource settings. Finally, we contribute a nuanced understanding of the cross-cultural and infrastructural challenges that influence the paper-digital lifecycle. Our findings will be useful for researchers and practitioners interested in understanding or participating in the workflows that drive global development.

Mobile tools for point-of-care diagnostics in the developing world

Remote health monitoring and disease detection in the developing world are hampered by a lack of accurate, convenient and affordable diagnostic tests. Many of the tests routinely administered in well-equipped clinical laboratories are inappropriate for the settings encountered at the point of care, where low-income patients may be best served. To address this problem, medical researchers have developed innovative rapid diagnostic tests (RDTs) that are capable of detecting diseases at the point of care within a single patient visit to a clinic. However, for these new diagnostic technologies to be effective, tools must be developed to support the health workers who will be responsible for administering the tests and interpreting their results. This paper describes the design and initial implementation of ODK Diagnostics, a smartphone application that supports health workers in three ways: (1) by facilitating the creation of digital job aids that provide in-context assistance to users administering RDTs, (2) by automatically interpreting the test results and delivering the diagnosis, and (3) by automating the data collected regarding the type and outcome of the test. Our technical evaluation suggests that the system is capable of accurately reading RDT results and is ready to be field tested with health workers to ensure that it is usable and appropriate for point-of-care settings in developing countries.

Supporting Community Health Workers in India through Voice- and Web-Based Feedback

Our research aims to support community health workers (CHWs) in low-resource settings by providing them with personalized information regarding their work. This information is delivered through a combination of voice- and web-based feedback that is derived from data already collected by CHWs. We describe the in situ participatory design approach used to create usable and appropriate feedback for low-literate CHWs and present usage data from a 12-month study with 71 CHWs in India. We show how the system supported and motivated CHWs, and how they used both the web- and voice-based systems, and each of the visualizations, for different reasons. We also show that the comparative feedback provided by the system introduced elements of competition that discouraged some CHWs while motivating others. Taken together, our findings suggest that providing personalized voice- and web-based feedback could be an effective way to support and motivate CHWs in low-resource settings.