Rada Mihalcea

Rada Mihalcea
Born Cluj-Napoca, Romania
Education Southern Methodist University (1999,2001)
Occupation Professor at University of Michigan
Known for

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.

Career

Mihalcea has published 220 articles since 1998 on topics ranging from semantic analysis of text to lie detection.[1] President Barack Obama granted her the Presidential Early Career Award for Scientists and Engineers in 2008.[2]

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 behavior, to include student life, personality and background outside of the classroom.[3]

Research

In a collaboration she leads at the University of Michigan, Mihalcea has created software that can detect human lying.[4] In a study of video clips of high profile court cases, a computer was more accurate at detecting deception than human judges.[5][6][7]

Mihalcea's lie-detection software uses machine learning techniques to analyze video clips of actual trials.[8] 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.[9] 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.[9][10] 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.[11]

Beyond the courtroom, Mihalcea says, the software could be adapted for job interviews. But she notes there are still improvements to be made — in particular to account for cultural and demographic differences.[9] 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.[12]

References

  1. ↑ "Rada Mihalcea". Semantic Scholar. Retrieved 2017-08-30.
  2. ↑ "President Honors Outstanding Early-Career Scientists". National Science Foundation. Retrieved 2017-08-30.
  3. ↑ "U Michigan MIDAS Program Backs Student Success Research". Campus Technology. Retrieved 2016-06-23.
  4. ↑ "Researchers Develop New Lie-Detecting Software". Topnews.in. Retrieved 2015-12-16.
  5. ↑ "Can you spot a liar? Fail safe ways to determine if someone is telling the truth". New Zealand Herald. Retrieved 2017-01-30.
  6. ↑ "New Developed Software can detect lie with %75 success – Baltimore News". Albany Daily Star. Retrieved 2016-08-17.
  7. ↑ "To spot a liar, look at their hands". Quartz. Retrieved 2015-12-12.
  8. ↑ "Courtroom fibs used to develop lie-detecting software". Gizmag. Retrieved 2015-12-12.
  9. 1 2 3 "University professors create new software to detect lies". Michigan Daily. Retrieved 2015-12-11.
  10. ↑ "Liar, Liar Pants On Fire: 6 Signs Computers Use To Spot Liars With 75% Accuracy". Medical Daily. Retrieved 2015-12-16.
  11. ↑ "5 Ways to Tell If Someone is Lying to You". Yahoo! Health. Retrieved 2015-12-15.
  12. ↑ "New software analysis words, gestures to detect lies". Jagran Post. Retrieved 2015-12-11.
This article is issued from Wikipedia. The text is licensed under Creative Commons - Attribution - Sharealike. Additional terms may apply for the media files.