I have been working for more than a decade on new ways to solve humanities problems
of practical interest using computers. Most of my work has focused on determining
the authorship of a document via stylometry (the study and measurement of writing
style). Using this technology, I have been able to identify J.K. Rowling's use of
a pen name to write The Cuckoo's Calling, to testify about judicial misconduct in
Chevron Corp. via Donziger, and to help a refugee remain in the United States in Federal
Immigration Court. Some of the software I have helped to create is available for use
under an open-source license from www.jgaap.com.
The key insight that guides my research is that there are lots of ways to say or write the same message, and people are free to choose from among many different ways to express the same ideas. Frequently-made choices become habits, and habits can be picked up by looking at other things a person has said or written, so a piece of writing that shows the same habitual choices is likely to be a piece of writing by the same person.
I received my Ph.D. in computer science from the University of Colorado at Boulder (USA) in 1995, then worked for three years as a postdoctoral researcher in the department of experimental psychology at Oxford University (UK). Since 1998, I have been working at Duquesne University (Pittsburgh, PA, USA) in the mathematics and computer science department, where I currently hold the position of Professor of Computer Science.
- B.S. (Electrical Engineering and Mathematics) The Johns Hopkins University (1987)
- M.S. (Computer Science) The University of Colorado at Boulder (1991)
- M.S. (Cognitive Science) The University of Colorado at Boulder (1993)
- Ph.D. (Computer Science) The University of Colorado at Boulder (1995)
Graduate Courses Taught:
CPMA 515 (Advanced Discrete Mathematics)
CPMA 531 (Programming Language: Java)
CPMA 532 (Data Structures)
CPMA 535 (Computer Systems)
CPMA 535 (Software Engineering)
CPMA 564 (Cryptology)
CPMA 580 (Artificial Intelligence/Cognitive Science)
CPMA 585 (Computer Security)
GRBUS 462 (Topics in Digital Forensics)
Undergraduate Courses Taught:
COSC 100 (Elements of Computer Science)
COSC 101 (Introduction to Visual Basic)
COSC 150 (Computer Programming: C++)
COSC 220 (Computer Organization and Assembly Language)
COSC 210 (Data Structures)
COSC 325W (Operating Systems and Computer Architecture)
COSC 410 (Artificial Intelligence)
COSC 425 (Computer Graphics)
COSC 435 (Theory of Programming Languages)
COSC 450 (Computer Networks)
COSC 460 (Computer Security)
COSC 494 (SPTPC: Neural Networks)
COSC 495 (SPTPC: Authorship Attribution)
Founder and Director of Research, J Computing, Inc. (2010 - Present). A Pennsylvania-based
startup specializing in forensic
Adjunct Scientist, Human Language Technology Center of Excellence, the Johns Hopkins University (2008 - Present).
Visiting Scientist, CERT/CC, Carnegie Mellon University (1999 - 2001).
Staff Scientist, PGP, Inc. (1995 - 2001).
Software Engineer, Brain and Cognitive Sciences Dept., MIT (1990 - 1990).
Technical Consultant, AT&T Bell Laboratories (1987 - 1990).
CIRCA Scholar, Canadian Institute for Research Computing in the Arts, University of
Alberta (2011 - Present).
Contributing Editor, PCSense Magazine (1995 - 1997).
NSF Fellow, Electrotechnical Laboratory (1991 - 1991).
2018: Juola, P. & Riddell, A., SaTC: CORE Small: Collaborative: Defending Against Authorship Attribution Attacks, Principal Investigator, GOV-National Science Foundation (NSF).
2014: Juola, P. Direct Assessment of Authorial Likelihood Using Bayes' Theorem and Monte Carlo Simulation, Principal Investigator, Innovation Works.
2012: Stowell, D. & Juola, P., Is That You, Mr. Lincoln?: Applying Authorship Attribution to the Early Political Writings of Abraham Lincoln ($50,000.00), GOV-National Endowment for the Humanities.
2010: Juola, P., SDCI Data: Improvement: Java Graphical Authorship Attribution Program (JGAAP) ($1,622,036.00), GOV-National Science Foundation (NSF).
2009: Juola, P., Conjecture Generation ($3,500.00), Wimmer Family Foundation.
2008: Juola, P. & Argamon, S., CRI: CRD: Collaborative Research: Community Resources for Authorship Attribution Research ($58,202.00), GOV-National Science Foundation (NSF).
2007: Juola, P., SDCI Data New: A Modular Software Framework for Evaluation, Testing, and Cross-Fertilization of Authorship Attribution Techniques ($212,000.00), GOV-National Science Foundation (NSF).
2007: Juola, P., A Machine-Aided Back-of-the-Book Indexing System ($131,465.00), GOV-National Endowment for the Humanities.
2006: Juola, P., Wimmer Textbook Writing Proposal: Six Septembers ($3,500.00), Wimmer Family Foundation.
2003: Simon, D. & Juola, P., Acquisition of a Beowulf Cluster for Research and Education in the Computational Sciences, GOV-National Science Foundation (NSF).
2003: Juola, P., A Model of Aphasia using Dictionary-Derived Natural Language Semantics, Oxford University Press. Supported by provision of research corpora from the Digital Reference library.
2002: Juola, P., Wimmer Textbook Writing Proposal: A Virtual Assembly, Wimmer Family
Funded for one course released time.
2002: Juola, P. & Levine, S., Interdisciplinary Teaching Development, MATH 320: Topics in Mathematics ($5,000.00), Wimmer Family Foundation.
1999: Juola, P., Measuring Linguistic Complexity ($2,500.00), NEH Internal Grant.
Juola, Patrick. "The Rowling case: A proposed standard analytic protocol for authorship questions." Digital Scholarship in the Humanities 30, no. suppl_1 (2015): i100-i113.
Fridman, Lex, Ariel Stolerman, Sayandeep Acharya, Patrick Brennan, Patrick Juola, Rachel Greenstadt, and Moshe Kam. "Multi-modal decision fusion for continuous authentication." Computers & Electrical Engineering 41 (2015): 142-156.
Stamatatos, Efstathios, Walter Daelemans, Ben Verhoeven, Martin Potthast, Benno Stein, Patrick Juola, Miguel A. Sanchez-Perez, and Alberto Barrón-Cedeño. "Overview of the author identification task at PAN 2014." In CLEF 2014 Evaluation Labs and Workshop Working Notes Papers, Sheffield, UK, 2014, pp. 1-21. 2014.
Juola, Patrick. "How a computer program helped reveal JK Rowling as author of A Cuckoo’s Calling." Scientific American 20 (2013).
Fridman, Alex, Ariel Stolerman, Sayandeep Acharya, Patrick Brennan, Patrick Juola, Rachel Greenstadt, and Moshe Kam. "Decision fusion for multimodal active authentication." IT Professional 15, no. 4 (2013): 29-33.
Noecker Jr, John, Michael Ryan, and Patrick Juola. "Psychological profiling through textual analysis." Literary and Linguistic Computing 28, no. 3 (2013): 382-387.
Juola, Patrick. "Using the Google N-Gram corpus to measure cultural complexity." Literary and linguistic computing 28,no. 4 (2013): 668-675.
Juola, Patrick, and Efstathios Stamatatos. "Overview of the Author Identification Task at PAN 2013." CLEF (Working Notes) 1179 (2013).
Juola, Patrick. "Stylometry and immigration: A case study." JL & Pol'y 21 (2012): 287.
Juola, Patrick. "Detecting stylistic deception." In Proceedings of the Workshop on Computational Approaches to Deception Detection, pp. 91-96. Association for Computational Linguistics, 2012.
Juola, Patrick. "Large-scale experiments in authorship attribution." English Studies 93, no. 3 (2012): 275-283.
Juola, Patrick. "An Overview of the Traditional Authorship Attribution Subtask." In CLEF (Online Working Notes/Labs/Workshop). 2012.
Argamon, Shlomo, and Patrick Juola. "Overview of the international authorship identification competition at PAN-2011." In CLEF (NotebookPapers/Labs/Workshop). 2011.
Juola, Patrick, and Darren Vescovi. "Empirical evaluation of authorship obfuscation using JGAAP." In Proceedings of the 3rd ACM workshop on Artificial Intelligence and Security, pp. 14-18. ACM, 2010.
Juola, Patrick. "Killer applications in digital humanities." Literary and Linguistic Computing 23,no. 1 (2008): 73-83.
Juola, Patrick. "Authorship attribution." Foundations and Trends® in Information Retrieval 1, no. 3 (2008): 233-334
Juola, Patrick. "Assessing linguistic complexity." Language complexity: Typology, contact, change (2008):89-108.
Juola, Patrick. "Authorship attribution for electronic documents." In IFIP International Conference on Digital Forensics, pp. 119-130. Springer, Boston, MA, 2006.
Juola, Patrick, John Sofko, and Patrick Brennan. "A prototype for authorship attribution studies." Literary and Linguistic Computing 21, no. 2 (2006): 169-178.
Juola, Patrick, and R. Harald Baayen. "A controlled-corpus experiment in authorship identification by cross-entropy." Literary andLinguistic Computing 20, no. Suppl (2005): 59-67.
Juola, Patrick. "Ad-hoc authorship attribution competition." In Proceedings of the Joint Conference of the Association for Computers and the Humanities and the Association for Literary and Linguistic Computing, pp. 175-176. 2004.
Juola, Patrick. "The time course of language change." Computers and the Humanities 37, no. 1 (2003): 77-96.
Juola, Patrick. "Document categorization and evaluation via cross-entrophy." U.S. Patent 6,397,205, issued May 28, 2002.
Plunkett, Kim, and Patrick Juola. "A connectionist model of English past tense and plural morphology." Cognitive Science 23, no. 4 (1999): 463-490.
Juola, Patrick. "Cross-entropy and linguistic typology." In Proceedings of the joint conferences on new methods in language processing and computational natural language learning, pp. 141-149. Association for Computational Linguistics, 1998.
Juola, Patrick. "Measuring linguistic complexity: The morphological tier." Journal of Quantitative Linguistics 5, no. 3 (1998): 206-213.
Juola, Patrick. "What can we do with small corpora? Document categorization via cross-entropy." In Proceedings of an Interdisciplinary Workshop on Similarity and Categorization, Department of Artificial Intelligence, University of Edinburgh, Edinburgh, UK. 1997.
Juola, Patrick. "Whole-word phonetic distances and the PGPfone alphabet." In Proceeding of Fourth International Conference on SpokenLanguage Processing. ICSLP'96, vol. 1, pp. 98-101. IEEE, 1996.
Kumar, Vijay, Anton Dahbura, Fred Fischer, and Patrick Juola. "An approach for the yield enhancement of programmable gate arrays." In 1989 IEEE International Conference on Computer-Aided Design. Digest of Technical Papers, pp. 226-229. IEEE, 1989.