Latest CS research – from microgenetic learning to space exploration

Latest CS research - from microgenetic learning to space exploration

A few of the school's many research projects are highlighted below.

Microgenetic Learning Analytics - Professor Emeritus Rick Adrion is collaborating with Education Associate Professor Florence Sullivan on a National Science Foundation (NSF) project to develop and pilot a new research method that combines microgenetic analysis techniques derived from developmental psychology with learning analytic techniques from the field of computer science. They will use the new method, termed "Microgenetic Learning Analytics," to engage in research on the development of computational thinking among underrepresented students, particularly girls, as they interact in a robotics learning environment, with the goal of increasing the diversity of individuals who enter the field of computing.

Effectiveness of Video Ads - Associate Professor Ramesh Sitaraman and research partner S. Shunmuga Krishnan of Akamai recently completed perhaps the largest-ever scientific study of the effectiveness of video ads, a fundamental question for business. Sitaraman, who led the study, says a simple, well-accepted measure of ad effectiveness is whether viewers watch the video ads to completion or not. "Our goal was to scientifically understand what factors influence people to complete watching video ads and what contributes to them abandoning the ad before it completes." Sitaraman presented their findings at the ACM Internet Measurement Conference in Barcelona on Oct. 24. See the study results at www.umass.edu/newsoffice/article/umass-amherst-researcher-quantifies.

Meditation Use in Treating Addiction - CS alum Yariv Levy (Ph.D. '13), Professor Emeritus Andrew Barto, and Neuroscience Researcher Jerrold Meyer use a computational model of addiction, a literature review, and an in silico experiment to suggest that rehabilitation strategies coupling meditation-like practices with drug and behavior therapies are more helpful than drug-plus-talk therapy alone when helping people overcome addiction. Levy, who conducted this investigation while a doctoral student, says the goal is to translate what has been learned from animal and human studies to better understand addiction and explore new approaches to treatment. Levy reported results of his survey in a special section on addictive disorders in the current issue of the journal Frontiers in Psychiatry. Another member of the team is Tel Aviv University Neuroeconomist Dino Levy.  See www.umass.edu/newsoffice/article/addiction-meditation-helpful-when-coupled.

Understanding the Composition of Mars - Professor Sridhar Mahadevan and Mt. Holyoke Professor Darby Dyar are collaborating on an NSF project combining machine learning (ML) and astronomy to understand the composition of substances on Mars from laser spectrometry data collected by the Curiosity rover on Mars. They examine the spectra of Martian rocks that Curiosity zaps with a laser, and use high-dimensional ML techniques to study their elemental composition. The researchers hope such analyses will one day shed light on the eternal question of whether there ever was life on other planets.

In a separate project, Mahadevan is working with a multi-institutional team of researchers on a National Aeronautics and Space Administration (NASA) Solar System Exploration Research Virtual Institute (SSERVI) project led by Stony Brook University to analyze samples from the Moon, Near Earth Asteroids, and Martian moons Phobos and Deimos. The research goal is to facilitate possible human exploration and colonization of these planetary bodies.