SoylentNews is people
SoylentNews
An Anonymous Coward informs us that the 17th ACM International Conference on Multimodal Interaction will be taking place in Seattle on 13 November. The goal of the Conference is:
... to provide the participants with a forum to foster the dissemination of ideas on computational and behavioral methodologies for deception detection.
The AC points out that, in a call for papers, it specifically says:
The 2015 ACM Workshop on Multimodal Deception Detection [...] will focus on multimodal and interdisciplinary approaches to deception detection, as well as approaches that utilize a single modality with clear potential for integration with additional modalities. Deception detection has received an increasing amount of attention due to the significant growth of digital media, as well as increased ethical and security concerns. Earlier approaches to deception detection were mainly focused on law enforcement applications and relied on polygraph tests, which had proven to falsely accuse the innocent and free the guilty in multiple cases. More recent work on deception has expanded to other applications, such as deception detection in social media, interviews, or deception in day-by-day interactions. Moreover, recent research on deception detection has brought together scientists from fields as diverse as computational linguistics, speech processing, computer vision, psychology, and physiology, which makes this problem particularly appealing for multimodal processing.
In the opinion of the AC, Multimodal Interaction researchers will be trying, in effect, to build a better lie detector at the ACM Workshop, held as part of the International Conference on Multimodal Interaction. Researchers are aiming for quantitative methods of deception detection by using modalities such as "text, speech, thermal, and visual," with application areas to include "healthcare, law enforcement, and others."
For those of you who remember '1984', senior research director O'Brien, affiliated with the Ministry of Love, passionately described in detail his future vision for the ideal lie detector, which includes a dial with a lever on top and figures running round the face, "able to inflict pain at any moment and to whatever degree I choose," according to O'Brien.
What are your views?
(Score: 3, Insightful) by Anonymous Coward on Friday July 24 2015, @01:28PM
The issue with a goal to detect lies is that memories are fallible - they don't record reality. People can be telling the truth and also not be given any account of reality.
This is especially true in stressful encounters, where every participant in an event can be completely *truthful*, give completely accurate descriptions of what they *remember*, and video evidence would tell any entirely different story. Were they all lying? I don't think so. Testimonial evidence has and always will be a very poor substitute for physical evidence, and a lie detector isn't going to change a damn thing.
(Score: 2) by Thexalon on Friday July 24 2015, @06:31PM
This is more for dealing with complete fabrications which also appear to be common. For example, in the high-profile cases involving police misconduct, the reports filed by the officers (shortly after the fact, before the case became noteworthy) did not even come close to matching video evidence.
I agree human memory sucks, but to say that humans never lie is also completely inaccurate.
The only thing that stops a bad guy with a compiler is a good guy with a compiler.