Analysis of Patient Cues in Asynchronous Health Interactions: Pilot Study Combining Empathy Appraisal and Systemic Functional Linguistics
Bibliographic record
Abstract
BACKGROUND: Lifestyle-related diseases are among the leading causes of death and disability. Their rapid increase worldwide has called for low-cost, scalable solutions to promote health behavior changes. Digital health coaching has proved to be effective in delivering affordable, scalable programs to support lifestyle change. This approach increasingly relies on asynchronous text-based interventions to motivate and support behavior change. Although we know that empathy is a core element for a successful coach-user relationship and positive patient outcomes, we lack research on how this is realized in text-based interactions. Systemic functional linguistics (SFL) is a linguistic theory that may support the identification of empathy opportunities (EOs) in text-based interactions, as well as the reasoning behind patients' linguistic choices in their formulation. OBJECTIVE: This study aims to determine whether empathy and SFL approaches correspond and complement each other satisfactorily to study text-based communication in a health coaching context. We sought to explore whether combining empathic assessment with SFL categories can provide a means to understand client-coach interactions in asynchronous text-based coaching interactions. METHODS: We retrieved 148 text messages sent by 29 women who participated in a randomized trial of telecoaching for the prevention of gestational diabetes mellitus (GDM) and postnatal weight loss. We conducted a pilot study to identify users' explicit and implicit EOs and further investigated these statements using the SFL approach, focusing on the analysis of transitivity and thematic analysis. RESULTS: We identified 164 EOs present in 42.37% (3478/8209) of the word count in the corpus. These were mainly negative (n=90, 54.88%) and implicit (n=55, 60.00%). We distinguished opening, content and closing messages structures. Most of the wording was found in the content (n=7077, 86.21%) with a declarative structure (n=7084, 86.30%). Processes represented 22.4% (n=1839) of the corpus, with half being material (n=876, 10.67%) and mostly related to food and diet (n=196, 54.92%), physical activity (n=96, 26.89%), and lifestyle goals (n=40, 11.20%). CONCLUSIONS: Our findings show that empathy and SFL approaches are compatible. The results from our transitivity analysis reveal novel insights into the meanings of the users' EOs, such as their seek for help or praise, often missed by health care professionals (HCPs), and on the coach-user relationship. The absence of explicit EOs and direct questions could be attributed to low trust on or information about the coach's abilities. In the future, we will conduct further research to explore additional linguistic features and code coach messages. TRIAL REGISTRATION: Australian New Zealand Clinical Trials Registry (ANZCTR) ACTRN12620001240932; https://www.anzctr.org.au/Trial/Registration/TrialReview.aspx?id=380020.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.006 | 0.030 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.002 | 0.001 |
| Scholarly communication | 0.002 | 0.001 |
| Open science | 0.001 | 0.002 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.004 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".