PhD Candidate, Georgia Tech
Email
Abstract
Computational Approaches to Understanding Stylistic Variation in Online Writing
Language use in online interactions varies from community to community, from individual to individual, and even for individuals in different contexts. While prior work has identified these differences, far less is understood about why these differences have arisen in online writing. My research focuses on this ‘why’ question. The reasons for linguistic diversity in online writing could be multifold. As more and more interpersonal social interactions are conducted through mediated channels, there is an increasing need to express multiple social meanings in varied social situations through linguistic means. In the absence of non-verbal cues, the technology-mediated channels provide several affordances to conduct interpersonal interactions. How do factors such as the need to convey varied social meanings in online interpersonal interactions and the affordances in technology- mediated channels shape online writing? I investigate this interplay through a series of large-scale computational studies of linguistic style variation in online writing. This work will advance our understanding of how individuals utilize the affordances in online social platforms and shift style to achieve varied social goals. Understanding the social dimensions of linguistic style variation in online writing has important consequences for the design of language technology and social computing systems, and beyond.
Bio
Umashanthi Pavalanathan is a PhD Candidate at the College of Computing at Georgia Institute of Technology. She is a member of the Computational Linguistics Laboratory, working with Dr. Jacob Eisenstein. She works in the emerging discipline of Computational Sociolinguistics and her thesis work focuses on computational approaches to understanding stylistic variation in online writing. In addition, her research spans Natural Language Processing, Computational Social Science, and Social Computing. She is also interested in applying computation for broader social good and she was a Data Science for Social Good Fellow in summer 2014.
Umashanthi did internships at Facebook’s Core Data Science Team, Microsoft Research and the Pacific Northwest National Lab. Before grad school she was a junior visiting research scholar at the Data to Insight Center at Indiana University, Bloomington. She earned her bachelor’s degree in Engineering specializing in Computer Science and Engineering at University of Moratuwa, Sri Lanka.