Jump to content

Philip Schrodt

From Wikipedia, the free encyclopedia

Philip Andrew "Phil" Schrodt (born July 24, 1951) is a political scientist known for his work in automated data and event coding for political news. On August 1, 2013, he announced that he was leaving his job as professor at Pennsylvania State University[1] to become a full-time consultant.[2][3] Schrodt is currently a senior research scientist at the statistical consulting firm Parus Analytical Systems.[4]

Biography

[edit]

Schrodt received an M.A. in mathematics and a Ph.D. in political science from Indiana University in 1976. He worked at Northwestern University for 12 years, then at the University of Kansas for 21 years, and at Pennsylvania State University for 4 years, before leaving academia for a private sector job with Parus Analytical Systems.[2][4]

Academic work

[edit]

Schrodt's work has largely been focused on automated coding of event data for political news. In 1994, he created the Kansas Event Data System (KEDS) that won the “Outstanding Computer Software Award” from the American Political Science Association in 1995.[4][5][6] In 2000, he created the Textual Analysis by Augmented Replacement Instructions (TABARI) software in 2000 that improved on the KEDS.[5] He developed the Conflict and Mediation Event Observations (CAMEO) data coding framework along with Deborah J. Gerner and others. The TABARI software could automatically code event data according to the CAMEO framework.

A modification of TABARI, called JABARI-NLP, was used for the Integrated Conflict Early Warning System (ICEWS) database by Lockheed Martin Advanced Technology Laboratories.[7] TABARI and CAMEO are also used for event coding for the Global Database of Events, Language, and Tone (GDELT Project), that Schrodt co-created with Kalev Leetaru and others.[8]

Logistic regression models created by Schrodt were also successfully incorporated into the predictive algorithms used by Lockheed Martin for ICEWS.[9][10]

Reception

[edit]

Schrodt's academic work as well as his views (including those expressed in his academic work and in his blog posts) are frequently referenced by other blogs about data science and predictive analytics in political science, such as Jay Ulfelder's blog,[11] the Predictive Heuristics blog,[12] and Bad Hessian.[13] He has also been referenced in Foreign Policy articles.[14][15]

References

[edit]
  1. ^ "Philip Schrodt". Department of Political Science, Pennsylvania State University. Archived from the original on 2014-03-31. Retrieved 2014-06-24.
  2. ^ a b Schrodt, Philip A. (August 1, 2013). "Going Feral! Or "So long, and thanks for all the fish…"". Retrieved June 24, 2014.
  3. ^ Voeten, Erik (August 1, 2013). "Philip Schrodt "Goes Feral"". Retrieved June 24, 2014.
  4. ^ a b c "About". A Second Mouse. Retrieved June 24, 2014.
  5. ^ a b Gerner, Deborah J.; Schrodt, Philip A.; Abu-Jabr, Rajaa; Yilmaz, Omur. "Conflict and Mediation Event Observations (CAMEO): A New Event Data Framework for the Analysis of Foreign Policy Interactions" (PDF).
  6. ^ "Information Technology and Politics Section Award Recipients". American Political Science Association. Retrieved June 24, 2014.
  7. ^ Schrodt, Philip (January 20, 2011). "Automated Production of High-Volume, Near-Real-Time Political Event Data" (PDF). Retrieved June 12, 2014.
  8. ^ "About (Creation)". Global Database of Events, Language, and Tone. Retrieved June 24, 2014.
  9. ^ O'Brien, Sean P. (March 9, 2010). "Crisis Early Warning and Decision Support: Contemporary Approaches and Thoughts on Future Research". {{cite journal}}: Cite journal requires |journal= (help)
  10. ^ Meier, Patrick (March 20, 2010). "DARPA's Crisis Early Warning and Decision Support System". Conflict Early Warning and Early Response. Retrieved June 21, 2014.
  11. ^ Ulfelder, Jay. "Phil Schrodt (tag)". Retrieved June 24, 2014.
  12. ^ "Phil Schrodt (Tag)". Predictive Heuristics. Retrieved June 24, 2014.
  13. ^ "Google Search for Schrodt on badhessian.org". Retrieved June 24, 2014.
  14. ^ Ulfelder, Jay (November 8, 2012). "Why the World Can't Have a Nate Silver. The quants are riding high after Team Data crushed Team Gut in the U.S. election forecasts. But predicting the Electoral College vote is child's play next to some of these hard targets". Retrieved June 3, 2014.
  15. ^ Keating, Joshua (April 10, 2013). "What can we learn from the last 200 million things that happened in the world?". Foreign Policy. Archived from the original on June 6, 2014. Retrieved June 24, 2014.
[edit]