Population-specific Detection of Couples' Interpersonal Conflict using Multi-task Learning

Gujral, Aditya; Chaspari, Theodora; Timmons, Adela C.; Kim, Yehsong; Barrett, Sarah; Margolin, Gayla

doi:10.1145/3242969.3243007

Cited by 6 publications

(4 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We proposed sub-population specific machine learning models for detecting couples' interpersonal conflict in real life. In accordance with previous work [29,38,62], our results indicate that different features are predictive of conflict for different sub-populations. Despite their limited age range, the recruited participants in this study depicted significant variability in terms of their socio-demographic (e.g., race, ethnicity, employment status) and relationship-based characteristics (e.g., current length, cohabituation status, satisfaction, attachment).…”

Section: Discussionsupporting

confidence: 93%

“…Information from the entire population is represented in the first layers of these models, while sub-population specific knowledge is integrated in the later levels. To implement this model, a hierarchical MTL framework implemented with FNNs has been proposed for the detection of stress, mood, and happiness in real-life scenarios, as well as for the detection of interpersonal conflict between couples [29,31,62]. Jaques Adaptive models leverage transfer learning techniques and are achieved via fine-tuning of general models.…”

Section: Prior Workmentioning

confidence: 99%

“…In contrast to the aforementioned studies, where interpersonal conflict is well-defined, conflict between romantic partners can be a complex and sometimes subtle event, affected by a variety of interpersonal and psychological factors. In our previous work, we have attempted to use general machine learning models and hierarchical approaches to detect couples' interpersonal conflict [29,63].…”

Section: Prior Workmentioning

confidence: 99%

See 2 more Smart Citations

Sub-Population Specific Models of Couples’ Conflict

Gupta

Gujral

Chaspari

et al. 2020

ACM Trans. Internet Technol.

Self Cite

View full text Add to dashboard Cite

Interpersonal conflict between couples is a significant source of stress with long-lasting effects on partners’ physical and psychological health. Motivated by findings in psychological science, we study how couples with distinct relationship functioning characteristics experience conflict in real life. We propose sub-population specific machine learning models using hierarchical and adaptive learning frameworks to automatically detect interpersonal conflict through the ambulatory monitoring of couples’ physiological signals, audio samples, and linguistic indices. Results indicate that the proposed models outperform a general model learned for the entire population and separate models independently trained on each sub-population, providing a foundation toward personalized health applications.

show abstract

Section: Discussionsupporting

confidence: 93%

Section: Prior Workmentioning

confidence: 99%

Section: Prior Workmentioning

confidence: 99%

See 1 more Smart Citation

Sub-Population Specific Models of Couples’ Conflict

Gupta

Gujral

Chaspari

et al. 2020

ACM Trans. Internet Technol.

Self Cite

View full text Add to dashboard Cite

show abstract

“…Such approaches usually involve the learning of separate models for each participant (33), which entails the risk of over-fitting or inadequate training due to the lack of enough data from a given subject. Group-specific models cluster participants according to clinically and theoretically relevant characteristics and are usually implemented through hierarchical and adaptive learning methods (34)(35)(36). Such methods use a portion of data from a target entity to fine-tune the decisions of a machine learning model adaptively (37,38).…”

Section: Introductionmentioning

confidence: 99%

Modeling inter-individual differences in ambulatory-based multimodal signals via metric learning: a case study of personalized well-being estimation of healthcare workers

Paromita

Mundnich

Nadarajan

et al. 2023

Front. Digit. Health

View full text Add to dashboard Cite

IntroductionIntelligent ambulatory tracking can assist in the automatic detection of psychological and emotional states relevant to the mental health changes of professionals with high-stakes job responsibilities, such as healthcare workers. However, well-known differences in the variability of ambulatory data across individuals challenge many existing automated approaches seeking to learn a generalizable means of well-being estimation. This paper proposes a novel metric learning technique that improves the accuracy and generalizability of automated well-being estimation by reducing inter-individual variability while preserving the variability pertaining to the behavioral construct.MethodsThe metric learning technique implemented in this paper entails learning a transformed multimodal feature space from pairwise similarity information between (dis)similar samples per participant via a Siamese neural network. Improved accuracy via personalization is further achieved by considering the trait characteristics of each individual as additional input to the metric learning models, as well as individual trait base cluster criteria to group participants followed by training a metric learning model for each group.ResultsThe outcomes of the proposed models demonstrate significant improvement over the other inter-individual variability reduction and deep neural baseline methods for stress, anxiety, positive affect, and negative affect.DiscussionThis study lays the foundation for accurate estimation of psychological and emotional states in realistic and ambulatory environments leading to early diagnosis of mental health changes and enabling just-in-time adaptive interventions.

show abstract