SenseMate: An AI-based Platform to Support Qualitative Coding
Many community organizations want to engage in conversations with
their constituents but lack the support they need to analyze feedback
through qualitative data analysis (QDA), or sensemaking. As a result,
it’s important to provide accessible entry points into the analysis
process for people with no prior experience. For my master's thesis,
I’m designing SenseMate, an AI-based platform to support
non-researchers in qualitative coding. After developing a codebook,
or a list of themes, from a subset of the data, qualitative coding
involves applying the codebook to all the data. SenseMate aims to
transparently recommend themes for pieces of text to increase the
efficiency and reliability of qualitative coding.
This is an ongoing project!
Future CMS Schools
I collaborated with an amazing team of people from CCC and
Charlotte-Mecklenburg Schools (CMS)
to create a new form of community engagement around two magnet schools opening in the fall of
2023. Through facilitated small-group conversations and various online platforms that we designed,
we were able to more deeply engage CMS’ parents, students, and other community members in dialogue
around their hopes and concerns for the new schools.
A paper on this work was recently submitted to CHI 2023 as a case study.
Personal Reminiscence Detection
For my Natural Language Processing (NLP) final project, I worked with three classmates to detect personal
reminiscence from face-to-face, small-group conversation transcripts. Our NLP task was to classify whether a
conversation excerpt contains an instance of personal reminiscence or not. We constructed an
annotated dataset for personal reminiscence detection and implemented a variety of models for classification.