In this work, we present a database of multimodal communication features extracted from debate sp... more In this work, we present a database of multimodal communication features extracted from debate speeches in the 2019 North American Universities Debate Championships (NAUDC). Feature sets were extracted from the visual (facial expression, gaze, and head pose), audio (PRAAT), and textual (word sentiment and linguistic category) modalities of raw video recordings of competitive collegiate debaters (N=717 6-minute recordings from 140 unique debaters). Each speech has an associated competition debate score (range: 67-96) from expert judges as well as competitor demographic and per-round reflection surveys. We observe the fully multimodal model performs best in comparison to models trained on various compositions of modalities. We also find that the weights of some features (such as the expression of joy and the use of the word "we") change in direction between the aforementioned models. We use these results to highlight the value of a multimodal dataset for studying competitive...
We present ongoing work on a project for automatic recognition of spon- taneous facial actions. S... more We present ongoing work on a project for automatic recognition of spon- taneous facial actions. Spontaneous facial expressions differ substan- tially from posed expressions, similar to how continuous, spontaneous speech differs from isolated words produced on command. Previous methods for automatic facial expression recognition assumed images were collected in controlled environments in which the subjects delib- erately faced the camera.
Previous research has suggested an important role for the emotion of hatred in intergroup aggress... more Previous research has suggested an important role for the emotion of hatred in intergroup aggression. Recent theoretical and empirical work has strongly suggested that the combination of anger, contempt, and disgust (ANCODI) comprise the basic elements of hatred, and are the key emotions associated with intergroup aggression. No study, however, has provided evidence that these emotions cause hostile cognitions about specific groups. We report two studies that provide initial evidence. In both, participants were members of ideologically motivated groups and were primed with ANCODI. In Study 1 participants primed with ANCODI produced more aggressive cognitions relative to their opponent outgroup than a neutral outgroup; this effect did not occur for participants primed with fear-sadness. In Study 2 participants primed with ANCODI engaged in more competitive decision making against their opponent outgroups than a neutral outgroup; this effect did not occur for participants primed with ...
Journal of Applied Research in Memory and Cognition, 2012
ABSTRACT Highlights ► We argue that dismissing emotional clues to deception is premature. ► We sh... more ABSTRACT Highlights ► We argue that dismissing emotional clues to deception is premature. ► We show the existing research data shows strong emotion link in high motivation deception studies. ► We argue efforts to enhance cognitive clues to deception are important but have not yielded results stronger than emotion. ► We agree that the interaction between liar and lie catcher is an important avenue to pursue. ► We argue that the paradigms used to study deception have not been relevant to real world forensic settings.
In this work, we present a database of multimodal communication features extracted from debate sp... more In this work, we present a database of multimodal communication features extracted from debate speeches in the 2019 North American Universities Debate Championships (NAUDC). Feature sets were extracted from the visual (facial expression, gaze, and head pose), audio (PRAAT), and textual (word sentiment and linguistic category) modalities of raw video recordings of competitive collegiate debaters (N=717 6-minute recordings from 140 unique debaters). Each speech has an associated competition debate score (range: 67-96) from expert judges as well as competitor demographic and per-round reflection surveys. We observe the fully multimodal model performs best in comparison to models trained on various compositions of modalities. We also find that the weights of some features (such as the expression of joy and the use of the word "we") change in direction between the aforementioned models. We use these results to highlight the value of a multimodal dataset for studying competitive...
We present ongoing work on a project for automatic recognition of spon- taneous facial actions. S... more We present ongoing work on a project for automatic recognition of spon- taneous facial actions. Spontaneous facial expressions differ substan- tially from posed expressions, similar to how continuous, spontaneous speech differs from isolated words produced on command. Previous methods for automatic facial expression recognition assumed images were collected in controlled environments in which the subjects delib- erately faced the camera.
Previous research has suggested an important role for the emotion of hatred in intergroup aggress... more Previous research has suggested an important role for the emotion of hatred in intergroup aggression. Recent theoretical and empirical work has strongly suggested that the combination of anger, contempt, and disgust (ANCODI) comprise the basic elements of hatred, and are the key emotions associated with intergroup aggression. No study, however, has provided evidence that these emotions cause hostile cognitions about specific groups. We report two studies that provide initial evidence. In both, participants were members of ideologically motivated groups and were primed with ANCODI. In Study 1 participants primed with ANCODI produced more aggressive cognitions relative to their opponent outgroup than a neutral outgroup; this effect did not occur for participants primed with fear-sadness. In Study 2 participants primed with ANCODI engaged in more competitive decision making against their opponent outgroups than a neutral outgroup; this effect did not occur for participants primed with ...
Journal of Applied Research in Memory and Cognition, 2012
ABSTRACT Highlights ► We argue that dismissing emotional clues to deception is premature. ► We sh... more ABSTRACT Highlights ► We argue that dismissing emotional clues to deception is premature. ► We show the existing research data shows strong emotion link in high motivation deception studies. ► We argue efforts to enhance cognitive clues to deception are important but have not yielded results stronger than emotion. ► We agree that the interaction between liar and lie catcher is an important avenue to pursue. ► We argue that the paradigms used to study deception have not been relevant to real world forensic settings.
Uploads