Rada Mihalcea

Rada Mihalcea is a professor of computer science and engineering at the University of Michigan. Her research focuses on natural language processing, multimodal processing, and computational social science.

Rada Mihalcea
Born
Cluj-Napoca, Romania
EducationTechnical University of Cluj-Napoca (1992), Southern Methodist University (1999,2001), Oxford University (2010)
OccupationProfessor at University of Michigan
Known for
  • Natural Language Processing
  • Computational Social Science
  • Multimodal Interaction

Career

Mihalcea has a Ph.D. in Computer Science and Engineering from Southern Methodist University (2001) and a Ph.D. in Linguistics, Oxford University (2010). In 2017 she was named Director of the Artificial Intelligence Laboratory at University of Michigan, Computer Science and Engineering. In 2018, Mihalcea was elected as new VP for the Association for Computational Linguistics (ACL). She is a professor of Computer Science and Engineering at the University of Michigan, where she also leads the Language and Information Technologies (LIT) Lab[1].

Mihalcea has published over 220 articles since 1998 on topics ranging from semantic analysis of text to lie detection.[2] President Barack Obama granted her the Presidential Early Career Award for Scientists and Engineers in 2008.[3]

Mihalcea is an outspoken promoter of diversity in computer science. She also supports an expansion of the traditional analysis of educational success, which tends to focus on academic behaviour, to include student life, personality and background outside of the classroom.[4] Mihalcea leads Girls Encoded, a program designed to develop the pipeline of women in computer science as well as to retain the women who have entered into the program.[5][6][7]

Awards

Research

Mihalcea is known for her research in natural language processing, multimodal processing, computational social sciences. In a collaboration she leads at the University of Michigan, Mihalcea has created software that can detect human lying.[12] In a study of video clips of high profile court cases, a computer was more accurate at detecting deception than human judges.[13][14][15]

Mihalcea's lie-detection software uses machine learning techniques to analyze video clips of actual trials.[16] In her 2015 study, the team used clips from The Innocence Project, a national organization that works to reexamine cases where individuals were tried without the benefit of DNA testing with the aim of exonerating wrongfully convicted individuals.[17] After identifying common human gestures, they transcribed the audio from the video clips of trials and analyzed how often subjects labeled deceptive used various words and phrases. The system was 75% accurate in identifying which subjects were deceptive among 120 videos.[17][18] That puts Mihalcea’s algorithm on par with the most commonly accepted form of lie detection, polygraph tests, which are roughly 85 percent accurate when testing guilty people and 56 percent accurate when testing the innocent.[19] She notes there are still improvements to be made — in particular to account for cultural and demographic differences.[17] A possibly unique advantage of Mihalcea's study was the real world, high stakes nature of the footage analyzed in the study. In laboratory experiments, it is difficult to create a setting that motivates people to truly lie.[20]

In 2018, Mihalcea and her collaborators worked on an algorithm-based system that identifies linguistic cues in fake news stories. It successfully found fakes up to 76% of the time, compared to a human success rate of 70%.[21]

Publications

Books

Journals and conferences
gollark: You can group the channels somehow.
gollark: Oh dear.
gollark: I think there used to be.
gollark: Interesting that there's absolutely no overlap between top star receivers and top star givers there.
gollark: I forgot where it is, enjoy searching chat history.

References
  1. "Language Information and Technologies". lit.eecs.umich.edu. Retrieved 2019-03-07.
  2. "Rada Mihalcea". Semantic Scholar. Retrieved 2017-08-30.
  3. "President Honors Outstanding Early-Career Scientists". National Science Foundation. Retrieved 2017-08-30.
  4. "U Michigan MIDAS Program Backs Student Success Research". Campus Technology. Retrieved 2016-06-23.
  5. "Girls Encoded". girlsencoded.eecs.umich.edu. Retrieved 2019-03-07.
  6. "Making a difference for women in academia". University of Michigan EECS. Retrieved 2019-03-07.
  7. "A champion for women in computer science". University of Michigan EECS. Retrieved 2019-03-07.
  8. 2019 ACM Fellows Recognized for Far-Reaching Accomplishments that Define the Digital Age, Association for Computing Machinery, retrieved 2019-12-11
  9. "Sarah Goddard Power Award". The University Record. Retrieved 2019-03-07.
  10. "Carol Hollenshead Award | Center for the Education of Women | University of Michigan". www.cew.umich.edu. Retrieved 2019-03-07.
  11. "President Honors Outstanding Early-Career Scientists | NSF - National Science Foundation". www.nsf.gov. Retrieved 2019-03-07.
  12. "Researchers Develop New Lie-Detecting Software". Topnews.in. Retrieved 2015-12-16.
  13. "Can you spot a liar? Fail safe ways to determine if someone is telling the truth". New Zealand Herald. Retrieved 2017-01-30.
  14. "New Developed Software can detect lie with %75 success – Baltimore News". Albany Daily Star. Retrieved 2016-08-17.
  15. "To spot a liar, look at their hands". Quartz. Retrieved 2015-12-12.
  16. "Courtroom fibs used to develop lie-detecting software". Gizmag. 2015-12-12. Retrieved 2015-12-12.
  17. "University professors create new software to detect lies". Michigan Daily. Retrieved 2015-12-11.
  18. "Liar, Liar Pants On Fire: 6 Signs Computers Use To Spot Liars With 75% Accuracy". Medical Daily. 2015-12-15. Retrieved 2015-12-16.
  19. "5 Ways to Tell If Someone is Lying to You". Yahoo! Health. Retrieved 2015-12-15.
  20. "New software analysis words, gestures to detect lies". Jagran Post. Retrieved 2015-12-11.
  21. "Fake news detector algorithm works better than a human". University of Michigan News. 2018-08-21. Retrieved 2019-03-26.


This article is issued from Wikipedia. The text is licensed under Creative Commons - Attribution - Sharealike. Additional terms may apply for the media files.