Michelle Levine

Learn More
In order to effectively access the rapidly increasing range of media content available in the home, new kinds of more natural interfaces are needed. In this paper, we explore the application of multimodal interface technologies to searching and browsing a database of movies. The resulting system allows users to access movies using speech, pen, remote(More)
Detecting deception from different dimensions of human behavior has been a major goal of research in psychology and computational linguistics for some years and is currently of considerable interest to military and law enforcement agencies. However, relatively little work has been done to develop automatic methods to detect deception from spoken language or(More)
— We are building a new corpus of deceptive and non-deceptive speech, using American English and Mandarin Chinese adult native speakers, to investigate individual and cultural differences in acoustic, prosodic, and lexical cues to deception. Here, we report on the role of personality factors using the NEO-FFI (Neuroticism-Extraversion-Openness Five Factor(More)
When automatically detecting deception, it is important to model individual differences across speakers. We explore the automatic identification of individual traits such as gender , native language, and personality, using acoustic-prosodic and lexical features from an initial non-deceptive dialogue. We also explore predicting success at deception and at(More)
Automatic personality recognition is useful for many computational applications, including recommendation systems, dating websites, and adaptive dialogue systems. There have been numerous successful approaches to classify the " Big Five " personality traits from a speaker's utterance, but these have largely relied on judgments of personality obtained from(More)
Medical expenditure data analysis has recently become an important problem in bio-statistics. These data typically have a number of features making their analysis rather difficult. Commonly, they are heavily right-skewed, contain a large percentage of zeros and often exhibit large numbers of missing observations due to death and/or the lack of follow-up.(More)
  • 1