Population-specific detection of couples' interpersonal conflict using multi-task learning Conference

Gujral, A, Kim, Y, Chaspari, T et al. (2018). Population-specific detection of couples' interpersonal conflict using multi-task learning . 229-233. 10.1145/3242969.3243007

cited authors

  • Gujral, A; Kim, Y; Chaspari, T; Barrett, S; Timmons, AC; Margolin, G

authors

abstract

  • The inherent diversity of human behavior limits the capabilities of general large-scale machine learning systems, that require ample data to provide robust descriptors of the outcomes of interest. Population-specific models comprise a promising line of work for representing human behavior, since they make decisions for clusters of people with common characteristics, reducing the amount of data needed for training. We propose a multi-task learning (MTL) framework for developing population-specific models of interpersonal conflict between couples using ambulatory sensor and mobile data from real-life interactions. The criteria for population clustering include global indices related to couples' relationship quality and attachment style, person-specific factors of partners' positivity, negativity, and stress levels, as well as fluctuating factors of daily emotional arousal obtained from acoustic and physiological indices. Population-specific information is incorporated through a MTL feed-forward neural network (FF-NN), whose first layers capture the common information across all data samples, while its last layers are specific to the unique characteristics of each population. Our results indicate that the proposed MTL FF-NN trained solely on the sensor-based modalities provides unweighted and weighted F1-scores of 0.51 and 0.75, respectively, outperforming a single general FF-NN trained on the entire dataset and separate FF-NNs trained on each population cluster individually, highlighting the importance of taking into account the inherent diversity of different populations for the development of human-centered machine learning models.

publication date

  • October 2, 2018

Digital Object Identifier (DOI)

International Standard Book Number (ISBN) 13

start page

  • 229

end page

  • 233