© Proudly created with Wix.com

Thank you to our Sponsors

Research has been supported by the Defense Advanced Research Projects Agency, the Center for Business and Social Analytics at MSU, the National Science Foundation, and the William T. Grant Foundation under award numbers (NSF REAL– 1420532, WT Grant - 182764)

Contact Us

Tel: 517-353-3618

Email: torphyka@msu.edu

Michigan State University

College of Education

East Lansing, MI

Search
  • Teachers in Social Media

University of Chicago: Computational Social Science Workshop

Updated: Sep 5, 2019

Dr. Kaitlin Torphy, Dr. Ken Frank, and Hamid Karimi visited the University of Chicago to speak about an emergent phenomenon, social media in education. Dr. Frank presented on the importance of curation within social media and what we can learn from teachers’ digital traces. Check out Hamid Karimi's Talk here!


Hamid Karimi discusses how to leverage information within Pinterest data in machine learning approaches.

The Fifth Estate

Dr. Torphy discussed the notion of a Fifth Estate within the digital age, redefining network influence. As power and influence are negotiated across executive, judicial, and legislative enterprises, media—the Fourth Estate, and networks of influence amongst individuals within the Fifth Estate, present a new form of educational professionalism. Here, educators, researchers, and the community may engage directly in virtual space.


Computational Social Science Applications

Dr. Torphy also presented applications of research regarding teachers’ engagement within Pinterest, a prevalent social media platform amongst teachers nationwide. Using both quantitative descriptive and causal estimation approaches, she examined entrepreneurial behaviors within education—the teacherpreneur— and their response to the Common Core State Standards, a federal education reform.


Neural Networks and Machine Learning within Pinterest

Finally, Hamid Karimi will present early efforts to extend characterization of instructional quality at scale using computer science approaches in machine learning.



For more details and uploaded content see the workshop Github space here.


13 views