JMIR Publications

ABSTRACT

Background:

Alzheimer’s disease or related dementias (ADRD) is a severe neurological disorder that impairs the thinking and memory skills of older adults. A majority of persons living with dementia (PLWDs) receive care at home from their family members or other unpaid informal caregivers, which places significant mental, physical, and financial challenges on these caregivers. To reduce this burden, many informal ADRD caregivers seek social support in online environments. Despite a growing body of research examining online caregiving discussions, few investigations distinguish caregivers according to their type of relationship with PLWDs. Various studies have suggested that caregivers in different relationships experience distinct caregiving challenges and support needs.

Objective:

We examined and compared the online behaviors of adult children and spousal caregivers, the two largest groups of informal ADRD caregivers, in an open online community.

Methods:

We collected posts from ALZConnected, an online community that is managed by the Alzheimer’s Association and open to any person affected by ADRD. To gain insights into online behaviors, we first applied structured topic modeling (STM) to identify topics and topic prevalence between adult children and spousal caregivers. Next, we applied Valence Aware Dictionary for sEntiment Reasoning and Linguistic Inquiry and Word Count to evaluate sentiment changes of the online posts over time for both types of caregivers. We further built machine learning models to distinguish posts of each caregiver type and evaluated them on precision, recall, F1 and Area Under Precision-Recall Curve (AUPRC). Finally, we applied the best predicting model to compare the temporal trend of relationship predicting capacities in posts between the two types of caregivers.

Results:

Our analysis showed that the number of posts from both types of caregivers followed a long-tailed distribution, indicating that the majority of online caregivers in this community were infrequent users. In comparison to adult children caregivers, spousal caregivers tended to be more active in the community, publishing more posts and engaging in discussions on a wider range of caregiving topics. Spousal caregivers also exhibited slower growth in positive emotional communication over time. The best machine learning model for predicting adult children, spousal, or other caregivers achieved an AUPRC of 81.3%. The subsequential trend analysis showed that it became more difficult to predict adult children caregiver posts than spousal caregiver posts over time. This suggests that adult children and spousal caregivers might gradually shift their discussions from questions that are more directly related to their own experiences and needs to questions that are more general and applicable to other types of caregivers.

Conclusions:

Our findings suggest that it is important for researchers and community organizers to consider the heterogeneity of caregiving experiences and subsequent online behaviors among different types of caregivers when tailoring online peer support to meet the specific needs of each caregiver group.