While natural language processing affords researchers an opportunity to automatically scan millions of social media posts, there is growing concern that automated computational tools lack the ability to understand context and nuance in human communication and language. Columbia University’s Desmond Upton Patton introduces a critical systematic approach for extracting culture, context and nuance in social media data. The Contextual Analysis of Social Media (CASM) approach considers and critiques the gap between inadequacies in natural language processing tools and differences in geographic, cultural, and age-related variance of social media use and communication. CASM utilizes a team-based approach to analysis of social media data, explicitly informed by community expertise. The team uses CASM to analyze Twitter posts from gang-involved youth in Chicago. They designed a set of experiments to evaluate the performance of a support vector machine using CASM hand-labeled posts against a distant model. They found that the CASM-informed hand-labeled data outperforms the baseline distant labels, indicating that the CASM labels capture additional dimensions of information that content-only methods lack. They then question whether this is helpful or harmful for gun violence prevention.
About Elizabeth Borneman
Elizabeth is a designer, writer, and researcher interested in how art, computation, and communication can combine to strengthen community structures, and enhance learning across learner backgrounds. A Florida native, Elizabeth earned her Bachelor of Science in Neurobiology from Georgetown University. There she led a research team in the Culture and Emotions Lab investigating the campus climate for patterns in students’ belonging and social engagement across university locations and situational contexts. She also spent a semester in Cape Town, South Africa as a field researcher studying plant systems and animals’ optimal foraging, ideal free distribution, and territorial defense behaviors.
She most recently worked as a designer and programmer artist in Xaq Pitkow’s Computational Neuroscience lab, where she designed and prototyped interactive graphics and games for teaching and communicating concepts in computational neuroscience and in color vision grounded in visual perception. She’s excited about the power of info-visualization. At MIT, Elizabeth works in the Teaching Systems Lab designing multi-media practice spaces and curriculum for equitable teaching in Computer Science and STEM. Outside of study, Elizabeth likes to go dancing, spend time on the water, and explore outdoors.