I'm a 6th year Ph.D. candidate at Northwestern University in the Technology and Social Behavior (TSB) program advised by Professor Haoqi Zhang and Professor Darren Gergle.
My research develops human-machine systems for situated activity. My dissertation work focuses on supporting complex situated work (e.g., research, design, engineering, etc.) in networked workplaces. The primary challenge I found in this setting is helping workers deeply understand what work situations they are in and develop strategies for progressing with the support of peers and mentors. I consider how computational support can be drawn into our situated ways of working while leaving the agency of how to use the support up to the workers. In particular, I create programming constructs that model the workplace’s situated ways of working, and programming environments through which experts can model how they diagnose a work situation and strategize on how to resolve work situations. My work draws from the fields of Human-Computer Interaction (HCI), Social Computing, the Learning Sciences, Management and Organizational Sciences, and Artificial Intelligence.
Complex work increasingly demands that people adopt sophisticated strategies for how they plan, seek support, and use available resources along their work process. This involves a challenging monitoring and strategizing process that existing tools cannot support since they largely lack an understanding of an organization’s processes, social structures, venues, and tools.
In this project, we introduce workplace programming for situationally-aware systems–an approach for encoding work situations using computational abstractions of an organization’s ways of working, and surfacing support strategies at appropriate times and settings. Using this approach, systems can encode strategies that provide workers with signals about emerging work situations–like not knowing how to scope a deliverable–and suggested strategies they could use–such as reading a resource guide or reaching out to people for help–along their work process.
In studies, we find that Orchestration Scripts effectively encode situated work practices in a general manner that is less brittle to changes in people’s relationships and venues than workflow automation tools while still being tailored to specific people and their circumstances; and how it supports creating opportunities to discuss effective strategies for emerging work situations across venues in the work ecosystem. These findings show how programmable technologies are capable of flexibly providing situated support in today’s socio-technical workplaces, and enable a rich new set of workplace tools to be built using this newly available understanding of how work is conducted in the organization.
Work and learning communities have become increasingly networked to support their members in developing the skills to solve complex, real-world problems. Though disciplinary knowledge remains important to tackle these problems, working effectively in modern-day communities of practice demands the ability for one to learn how to access networked support (e.g., venues, tools, resource guides, or peers) throughout the socio-technical ecosystem. Against this backdrop, we study networked orchestration--how community members access and learn to access networked supports--in the Design, Technology, and Research (DTR) program for undergraduate research training for undergraduate research training.
Through field observations and in-depth interviews, we find that students in the networked research community dynamically engage with their mentors and peers across multiple venues throughout the week in order to identify, clarify, and resolve their needs. Mentors in the community monitor how students are engaging with the supports available in the network, and provide coaching on effective strategies when students are ineffective on their own. We also identify the challenges involved in each of these processes. For students, these include:
(1) not realize the needs they may have; (2) difficulties in identifying potential venues that can provide support; and (3) difficulties in accessing an opportunity even if it is known due to an unfamiliarity with the venue or person. For mentors, these include (1) struggling with students’ access strategies often being invisible to them since they occur in venues the mentor was not present in; and (2) with the difficulty in tracking the many skills that they are working on with each of their students over time.
These insights lead to practical design implications for networked orchestration technologies that require an ecosystem-level view of interactions occurring across the venues and tools in a community in order to support the development of network access skills to work effectively in networked communities. We envision that these networked orchestration technologies will be crucial for fostering the networked ways of working and learning that are becoming prevalent in our workplaces and learning communities.
Participatory sensing systems in which people actively participate in the data collection process must account for both the needs of data contributors and the data collection goals. Existing approaches tend to emphasize one or the other, with opportunistic and directed approaches making opposing tradeoffs between providing convenient opportunities for contributors and collecting high-fidelity data.
Our approach explores a new, hybrid approach, in which collected data--even if low-fidelity initially--can provide useful information to data contributors and inspire further contributions. We realize this approach with 4X, a multi-stage data collection framework that first collects data opportunistically by requesting contributions at specific locations along users’ routes and then uses collected data to direct users to locations of interest to make additional contributions that build data fidelity and coverage.
To study the efficacy of 4X, we developed LES, an iOS application for collecting information about campus locations and events using the 4X framework. Results from two field deployments (N = 95, N = 18) show that the 4X framework created 34% more opportunities for contributing data without increasing disruption, and yielded 49% more data by directing users to locations of interest. These findings demonstrate the value and potential of multi-stage, dynamic data collection processes that draw on multiple sources of motivation for data, and how they can be used to better meet data collection goals as data becomes available while avoiding unnecessary disruption.
Jupyter Notebooks, Pandas, Numpy, Scikit Learn, R