ECASE awards are the highest honor bestowed by the ARO to outstanding scientists and engineers beginning their independent careers. The awards recognize researchers who pursue innovative research at the frontiers of science and technology and who also engage in scientific leadership, education, or community outreach.<\/p>\n \u201cThis is a big boost that will help my lab continue to pursue blue-sky research,\u201d says Hoque, an assistant professor of computer science<\/a> and the Asaro Biggar Family Fellow in Data Science. He is also interim director of the Goergen Institute for Data Science<\/a>.<\/p>\n \u201cThe Army Research Office encourages young scientists to take on ridiculously difficult problems and allow ample intellectual freedom to pursue them,\u201d Hoque says. \u201cIt is a wonderful opportunity for young scientists like myself to take on high risks early in their career.\u201d<\/p>\n The technology Hoque hopes to develop with this award builds upon his lab\u2019s recent work on understanding deception based on facial and verbal cues<\/a>. His Rochester Human-Computer Interaction<\/a> (ROC-HCI) Lab used data science and created an online crowdsourcing framework called ADDR (Automated Dyadic Data Recorder) to build the largest publicly available deception dataset so far \u2013 and to discover, for example, why some smiles are more deceitful than others.<\/p>\n Applications include:<\/p>\n <\/p>\n With the new award, Hoque and his lab will develop machine-learning algorithms that could make the interrogations and interviews used in these settings more objective.<\/p>\n A typical interrogation is conducted in distinct phases, starting with general questions to establish rapport.<\/p>\n \u201cHow someone answers in the rapport-building phase could influence how the interviewer looks at that person when the important, relevant questions are asked in the subsequent phases, biasing the interviewer\u2019s ability to tell if someone is lying or telling the truth,\u201d Hoque says.<\/p>\n \u201cSo, imagine as I\u2019m interviewing you, I have a computer that is helping me out, that can treat each phase as unique and objective,\u201d Hoque says. \u201cWe can build algorithms to help quantify some of the nuances that an interviewer might miss\u2013subtle inconsistencies among facial cues, what is said, how it is said.\u201d<\/p>\n At the end of each phase, the algorithm, trained with reinforcement learning, would recommend whether it has \u201cseen\u201d enough to recommend going to the\u00a0 next phase, or whether additional questions should be asked.<\/p>\n The interviewer would still be in charge and still make the decisions, Hoque emphasizes, but \u201cthe algorithm is providing independent, quantifiable metrics, so that the interrogators can further quantify their decisions. It adds objectivity and transparency to the interrogation process.\u201d<\/p>\n Greater objectivity could benefit both the interviewer and the person being interviewed, especially in security and law enforcement settings, he says.<\/p>\n![\"Ehsan](\"https:\/\/www.rochester.edu\/newscenter\/wp-content\/uploads\/2016\/08\/2016-06-30_M_Ehsan_Hoque_029-crop-630x378.jpg\")
\n
Making interrogations more objective<\/strong><\/h3>\n