Using hidden Markov model to uncover processing states from eye movements in information search tasks |
| |
| Institution: | 1. Indian Institute of Technology Gandhinagar, Gujarat, 382355, India;2. Indian Institute of Technology Madras, Tamil Nadu, 600036, India;1. Helsinki Institute of Life Science, Neuroscience Center, University of Helsinki, Finland;2. Cognitive Brain Research Unit (CBRU), University of Helsinki, Finland;3. Department of Marketing, Aalto University School of Business, Finland;4. Turku Institute for Advanced Studies and Department of Psychology, University of Turku, Finland;1. Department of Civil, Environmental and Architectural Engineering, University of Colorado Boulder, 1111 Engineering Drive, Boulder, CO 80309-0428, USA;2. Department of Civil Engineering, Taibah University, Madinah 42353, Saudi Arabia;3. Department of Construction Management, Colorado State University, Fort Collins, CO 80525, USA;1. Eccles Institute of Neuroscience, John Curtin School of Medical Research, Australian National University, Acton, ACT, Australia;2. Department of Neuroscience, King Fahad Specialist Hospital, Dammam, Saudi Arabia;3. Department of Neurology, The Canberra Hospital, Canberra, ACT, Australia;4. Australian National University Medical School, Acton, ACT, Australia;1. Department of Medical Psychology, School of Medical Humanities, Capital Medical University, Beijing, China;2. Peking University Sixth Hospital, Beijing, China;3. Adai Technology (Beijing) Ltd., Co, Beijing, China |
| |
| Abstract: | We study how processing states alternate during information search tasks. Inference is carried out with a discriminative hidden Markov model (dHMM) learned from eye movement data, measured in an experiment consisting of three task types: (i) simple word search, (ii) finding a sentence that answers a question and (iii) choosing a subjectively most interesting title from a list of ten titles. The results show that eye movements contain necessary information for determining the task type. After training, the dHMM predicted the task for test data with 60.2% accuracy (pure chance 33.3%). Word search and subjective interest conditions were easier to predict than the question–answer condition. The dHMM that best fitted our data segmented each task type into three hidden states. The three processing states were identified by comparing the parameters of the dHMM states to literature on eye movement research. A scanning type of eye behavior was observed in the beginning of the tasks. Next, participants tended to shift to states reflecting reading type of eye movements, and finally they ended the tasks in states which we termed as the decision states. |
| |
| Keywords: | |
| 本文献已被 ScienceDirect 等数据库收录！ |
|
