Papers by Samantha Robertson
Proceedings of the Workshop on Human-In-the-Loop Data Analytics
What kinds of tools could support direct engagement between users and researchers, and among user... more What kinds of tools could support direct engagement between users and researchers, and among users? Findings possibly reach users (e.g. through the press) Researchers publish findings Apps share data with researchers Users track data Figure 1: It is increasingly common for researchers to use data from personal health tracking apps in menstrual health research, but this work rarely engages directly with the users who contributed the data. Our work explores how adding research participants into the data analysis loop could help users understand more about their health, and improve the quality of research conducted with this data.
2022 ACM Conference on Fairness, Accountability, and Transparency
Machine translation (MT) is now widely and freely available, and has the potential to greatly imp... more Machine translation (MT) is now widely and freely available, and has the potential to greatly improve cross-lingual communication. In order to use MT reliably and safely, end users must be able to assess the quality of system outputs and determine how much they can rely on them to guide their decisions and actions. However, it can be difficult for users to detect and recover from mistranslations due to limited language skills. In this work we collected 19 MTmediated role-play conversations in housing and employment scenarios, and conducted in-depth interviews to understand how users identify and recover from translation errors. Participants communicated using four language pairs: English, and one of Spanish, Farsi, Igbo, or Tagalog. We conducted qualitative analysis to understand user challenges in light of limited system transparency, strategies for recovery, and the kinds of translation errors that proved more or less difficult for users to overcome. We found that users broadly lacked relevant and helpful information to guide their assessments of translation quality. Instances where a user erroneously thought they had understood a translation correctly were rare but held the potential for serious consequences in the real world. Finally, inaccurate and disfluent translations had social consequences for participants, because it was difficult to discern when a disfluent message was reflective of the other person's intentions, or an artifact of imperfect MT. We draw on theories of grounding and repair in communication to contextualize these findings, and propose design implications for explainable AI (XAI) researchers, MT researchers, as well as collaboration among them to support transparency and explainability in MT. These directions include handling typos and non-standard grammar common in interpersonal communication, making MT in interfaces more visible to help users evaluate errors, supporting collaborative repair of conversation breakdowns, and communicating model strengths and weaknesses to users.
2022 ACM Conference on Fairness, Accountability, and Transparency
Language barriers between patients and clinicians contribute to disparities in quality of care. M... more Language barriers between patients and clinicians contribute to disparities in quality of care. Machine Translation (MT) tools are widely used in healthcare settings, but even small mistranslations can have life-threatening consequences. We study how MT is currently used in medical settings through a qualitative interview study with 20 clinicians-physicians, surgeons, nurses, and midwives. We find that clinicians face challenges stemming from lack of time and resources, cultural barriers, and medical literacy rates, as well as accountability in cases of miscommunication. Clinicians have devised strategies to aid communication in the face of language barriers including back translation, non-verbal communication, and testing patient understanding. We propose design implications for machine translation systems including combining neural MT with pre-translated medical phrases, integrating translation support with multimodal communication, and providing interactive support for testing mutual understanding.
ArXiv, 2020
Emerging methods for participatory algorithm design have proposed collecting and aggregating indi... more Emerging methods for participatory algorithm design have proposed collecting and aggregating individual stakeholder preferences to create algorithmic systems that account for those stakeholders' values. Using algorithmic student assignment as a case study, we argue that optimizing for individual preference satisfaction in the distribution of limited resources may actually inhibit progress towards social and distributive justice. Individual preferences can be a useful signal but should be expanded to support more expressive and inclusive forms of democratic participation.
ACM SIGPLAN Notices, 2018
Systems neuroscience studies involving in-vivo models often require realtime data processing. In ... more Systems neuroscience studies involving in-vivo models often require realtime data processing. In these studies, many events must be monitored and processed quickly, including behavior of the subject (e.g., movement of a limb) or features of neural data (e.g., a neuron transmitting an action potential). Unfortunately, most realtime platforms are proprietary, require specific architectures, or are limited to low-level programming languages. Here we present a hardware-independent, open-source realtime computation platform that supports high-level programming. The resulting platform, LiCoRICE, can process on order 10e10 bits/sec of network data at 1 ms ticks with 18.2 µs jitter. It connects to various inputs and outputs (e.g., DIO, Ethernet, database logging, and analog line in/out) and minimizes reliance on custom device drivers by leveraging peripheral support via the Linux kernel. Its modular architecture supports model-based design for rapid prototyping with C and Python/Cython and can perform numerical operations via BLAS/LAPACK-optimized NumPy that is statically compiled via Numba’s pycc. LiCoRICE is not only suitable for systems neuroscience research, but also for applications requiring closed-loop realtime data processing from robotics and control systems to interactive applications and quantitative financial trading.
Proceedings of the 2021 CHI Conference on Human Factors in Computing Systems, 2021
Figure 1: Student assignment algorithms were designed meet school district values based on modeli... more Figure 1: Student assignment algorithms were designed meet school district values based on modeling assumptions (blue/top) that clash with the constraints of the real world (red/bottom). Students are expected to have predefned preferences over all schools, which they report truthfully. The procedure is intended to be easy to explain and optimally satisfes student preferences. In practice however, these assumptions clash with the real world characterized by unequal access to information, resource constraints (e.g. commuting), and distrust.
Uploads
Papers by Samantha Robertson