13th Annual Conference of the International Speech Communication Association

Portland, OR, USA
September 9-13, 2012

Based on Isolated Saliency or Causal Integration? Toward a Better Understanding of Human Annotation Process using Multiple Instance Learning and Sequential Probability Ratio Test

Chi-Chun Lee, Athanasios Katsamanis, Panayiotis G. Georgiou, Shrikanth S. Narayanan

Signal Analysis and Interpretation Laboratory (SAIL), Los Angeles, CA, USA

Human perception is capable of integrating local events to generate an overall impression at the global level; this is evident in daily life and is utilized repeatedly in behavioral science studies to bring objective measures into studies of human behavior. In this work, we explore two hypotheses considering whether it is the isolated-saliency or the causal-integration of information that can trigger the global perceptual behavioral ratings as trained annotators engage in tasks of observational coding. We carry out analyses using Multiple Instance Learning and Sequential Probability Ratio Test in a corpus of real and spontaneous distressed couples' interaction with global session-level abstract behavioral coding done by trained human annotators. We present various analyses based on different behavioral detection schemes demonstrating the potential of utilizing these algorithms in bringing insights into the human annotation process. We further show that while annotating behaviors with more positive impression, annotators gather information throughout the session compared to behaviors with more negative impression, where a single salient instance is enough to trigger the final global decision.

Index Terms: multiple instance learning, sequential probability ratio test, behavior annotation, perception, observational coding

Full Paper

Bibliographic reference.  Lee, Chi-Chun / Katsamanis, Athanasios / Georgiou, Panayiotis G. / Narayanan, Shrikanth S. (2012): "Based on isolated saliency or causal integration? toward a better understanding of human annotation process using multiple instance learning and sequential probability ratio test", In INTERSPEECH-2012, 619-622.