JMIR Publications

ABSTRACT

Background:

Text mining methods, such as topic modeling, can offer valuable information on how and to whom internet-delivered cognitive behavioral therapies (iCBT) work. Although iCBT treatments provide convenient data for topic modeling, it has rarely been used in this context.

Objective:

To apply topic modeling to written assignment texts from iCBT for generalized anxiety disorder and explore the resulting topics’ associations with treatment response. As predetermining the number of topics presents a considerable challenge in topic modeling, we also aimed to explore a novel method for topic number selection.

Methods:

We defined two latent Dirichlet allocation (LDA) topic models using both a novel data-driven and a more commonly used interpretability-based topic number selection approach. We used multi-level models to associate the topics with continuous-valued treatment response, defined as the rate of per-session change in GAD-7 sum scores throughout the treatment.

Results:

Our analyses included 1686 patients. We observed two topics that were associated with better than average treatment response: “Well-being of family, pets and loved ones” from the data-driven LDA model (B = ˗0.10 sd/session/∆topic; 95% CI ˗016 – ˗0.03) and “Children, family issues” from the interpretability-based model (B = ˗0.18 sd/session/∆θ; 95% CI ˗0.31 – ˗0.05). Two topics were associated with worse treatment response: “Monitoring of thoughts and worries” from the data-driven model (B = 0.06 sd/session/∆θ; 95% CI 0.01 – 0.11) and “Internet therapy” from the interpretability-based model (B = 0.27 sd/session/∆θ; 95% CI 0.07 – 0.46).

Conclusions:

The two LDA models were different in terms of their interpretability and broadness of topics, but both contained topics that were associated with treatment response in a meaningful manner. Our work demonstrates that topic modeling suits well for iCBT research and has potential to expose clinically relevant information from vast text data.