Broadly, I study stories and phenomenon that emerge from sociotechnical systems. More specifically, I am interested in leveraging textual and network data to understand how social networks facilitate the emergence of discourse and sentiment. Quantifying the dynamics of networks and language is crucial to understanding social movements, collective well being, storytelling, disaster relief, and a variety of other unique and interesting domains. As a result, my research largely falls at the intersection of network science, natural language processing, and computational social science.

I work as a member of the Computational Story Lab under the guidance of Prof. Peter Dodds and Prof. Chris Danforth. For more details view my CV.


  1. Hashtag topic network
    "Anchored Correlation Explanation: Topic Modeling with Minimal Domain Knowledge"
    Ryan J. Gallagher, Kyle Reing, David Kale, Greg Ver Steeg. arXiv preprint arXiv:1611.10277, 2016. In Review.
    [arXiv] [pdf] [Topic model code]
  1. Hashtag topic network
    "Divergent discourse between protests and counter-protests: #BlackLivesMatter and #AllLivesMatter."
    Ryan J. Gallagher, Andrew J. Reagan, Christopher M. Danforth, Peter Sheridan Dodds. arXiv preprint arXiv:1606.06820, 2016. In Review.
    [arXiv] [pdf]