Lujie Karen Chen

Attachment is the emotional bonding between a child and a caregiver. Whether or not there is a secure attachment in early childhood has a profound life-long impact on the child. In recent years, attachment-based interventions have been developed and implemented, especially with families from low socioeconomic backgrounds. One important aspect of the program is to assess the quality of parent-child interactions through audio/video recorded at home while parent-child dyads were engaged in semi-structured interaction tasks, such as “three-bag-assessment.” The current practice relies on human coders to rate the videos, which is a time-consuming process. Using a dataset of 220 video recordings of parent-child dyads collected at home as part of an attachment-based intervention program, we prototype a machine learning approach based on human body keypoints extracted from the posture analysis tool OpenPose and voice activity features derived from audio recordings. The results show that there are potential values in using machine learning to improve the coding efficiency of parent-child interactions. When further developed and improved, this kind of model may contribute to a new vision of AI-assisted parenting coaching support to make evidence-based interventions accessible and affordable at a large scale to children and families.

Background Nursing assistants working in long‐term care (LTC) often report that their job is stressful. To reduce their work stress, a better understanding of their stress profile is needed. Objective We aimed to pilot test methods to identify and understand stressors that LTC nursing assistants experience. Methods We asked each participant to provide wearable sensor/watch data, ecological momentary assessment (EMA) surveys and end of day review data over two eight‐hour working shifts. Results Eight nursing assistants participated. All participants worked in a common continuing care retirement community in Maryland, United States of America. Our stress assessment method revealed 83 stressful events that were classified under 10 categories. Most of the reported events were rated as having a mild to low‐moderate intensity. The three most common causes of stress were work demands and pressure (28.35%), heavy workload and staffing (19.69%), and safety issues and COVID‐19 concerns (17.32%). We also explored the difference between stress events and intensity among different shifts. Disrespect from residents (22.73%) was the most commonly reported stressor during day shifts. Feeling rushed was the most commonly reported stressor during the evening (22.47%) and the night (38.46%) shifts. Conclusions We found stress was commonly reported. Stress intensity conflicted with prior literature, and we explored possible explanations. Implications for practice We discuss potential implications for these findings, modification of our methods to increase feasibility, the utility of these data collection methods for future work and suggest next steps.