Human-Computer Interaction Student Research Colloquium Series at Northwestern University
Work in progress. We plan to use this repository/webpage to provide information about the event and presentation schedule for Winter and Spring 2018. Check back soon!
NU HCI is a group of graduate students, faculty, and post-doctoral researchers from a variety of disciplines. Group members research a wide array of topics in HCI, including Artificial Intelligence, User-Centered Design, Social Computing, and Learning and Collaboration Technology, and employ both qualitative and quantitative methods in their work. A graduate-student-run group, NU HCI organizes both social and academic events to foster cross-department community building and provides a venue for in-progress research feedback.
The Northwestern University HCI Student Research Colloquium series provides opportunities for PhD students to obtain in-progress feedback from a supportive, academically diverse audience. As a new initiative, we hope that this colloquium series can spark new conversations and introduce the community to the breadth of HCI research at Northwestern.
Sessions occur during specific weeks of the academic year during the Thursday 4pm timeslot. Each student presenter will share a ten-minute presentation followed by twenty minutes of interactive Q&A. A reception follows to allow for conversations to continue as desired.
We plan to keep the colloquium sign-up form open and accept new submissions on an ongoing basis. This is not a weekly commitment so the timing and format is flexible. Sessions may occur whenever students are interested and willing to present. Former presenters are welcome to present projects again after making more progress and/or present a different project.
Cindy Xiong: The Curse of Knowledge in Visual Data Communication
The curse of knowledge is an inability to separate one's own knowledge or expertise from that of an audience. We test the idea that this curse can substantially impair visual communication of data, and has the potential to fixate an analyst on a given pattern in data. Because a viewer can extract many potential relationships and patterns from any set of visualized data values, a viewer may see one pattern in the data as more visually salient than others. We demonstrate this phenomenon in the laboratory, showing that when people are given background information, they see the pattern in the data corresponding to the background information as more visually salient.
Leesha Maliakal: Continual Support Systems to Orchestrate Research Communities
As research groups expand in size, it becomes increasingly difficult for community members to identify the expertise within the community and the resources available to help with research challenges. Mentors spend additional time providing ad-hoc support, but this strategy quickly becomes intractable without orchestration supports. I design, implement, and evaluate orchestration technologies capable of detecting diverse student needs, identifying available actions and help resources to meet those needs, and connecting resources and needs in ways that are cognizant of the collective needs and resources across a community.
Mark Díaz: Addressing Age-Related Bias in Sentiment Analysis
Computational approaches to text analysis are useful in understanding aspects of online interaction, such as opinions and subjectivity in text. Yet, recent studies have identified various forms of bias in language-based models, raising concerns about the risk of propagating social biases against certain groups based on sociodemographic factors (e.g., gender, race, geography). In this study, we contribute a systematic examination of the application of language models to study discourse on aging. We analyze the treatment of age-related terms across 15 sentiment analysis models and 10 widely-used GloVe word embeddings and attempt to alleviate bias through a method of processing model training data. Our results demonstrate that significant age bias is encoded in the outputs of many sentiment analysis algorithms and word embeddings. We discuss the models' characteristics in relation to output bias and how these models might be best incorporated into research.
Scott Cambo: Introducing Human-Centered Machine Learning
By definition, Machine Learning provides software with a way to learn something that it was not explicitly programmed for. In practice, Machine Learning is often used to allow people to learn something they might not have been able to do otherwise (e.g. infer relationships from large scale high-dimensional data at potentially high speed) and allow computers to learn something that humans learn naturally (e.g.: speaking, hearing, seeing). These two broad application areas of Machine Learning not only have a large impact on human behavior, their success often depends on a nuanced understanding of human behavior and how people interact with technology (i.e.: sociotechnical behavior). Students of the Human-Centered Machine Learning course will help form a new way of understanding and practicing the application of machine learning through a series of readings, discussions, and a final project.
Emily Wang: Creating Accessibility in STEM Professional Practices
Face-to-face collaboration is inherently multimodal: teams can edit on a shared screen (visual), talk to each other while editing (auditory), and gesture to express and clarify (visual/kinesthetic). Hearing collaborators often rely on the ability to see and hear at the same time, such as when a person talks about a portion of text while looking at the display. However, this interaction norm breaks down when teammates have different sensory capacity. For example, how do Deaf professionals collaborate with their hearing teammates on complex visual tasks? Deaf-hearing teams more heavily rely on visual communication strategies such as lipreading, sign language, gesturing, and text, which results in a physical separation between the workspace visuals and where one must look for language. In this talk, I will describe plans and initial work to design, implement, and evaluate a system that supports co-located pair programming between Deaf and hearing collaborators.
Eleanor Burgess: Mental Health Care Practices & Technology Opportunities within Care Management
Mental health care in the United States is often a needed but difficult to access resource. This presentation will explore the facilitation efforts for mental health care provision through a sociotechnical lens focused on the emerging role of care management. Care manager (CM) work includes coordination with and between insurance provider restrictions, healthcare system mandates, and community resources to promote the mental and physical health of their patients. I will address questions including: How do CMs seek to improve the health of patients in their care? What resources and technologies do they use to help patients to learn and practice healthy behaviors? How do CMs see the relationship between physical and mental health? The aims of this study were to understand CM work practices, with a focus on mental health care, and to uncover opportunities for mental healthcare technologies from an investigation of an ambulatory care management practice. This work presents an opportunity space for the development of technology-enabled mental health services within the norms and practices of care management services.