Identifying Language Features Associated With Needs of Ovarian Cancer Patients and Caregivers Using Social Media
Bibliographic record
Abstract
BACKGROUND: Online health communities (OHCs) can be a source for clinicians to learn the needs of cancer patients and caregivers. Ovarian cancer (OvCa) patients and caregivers deal with a wide range of unmet needs, many of which are expressed in OHCs. An automated need classification model could help clinicians more easily understand and prioritize information available in the OHCs. OBJECTIVE: The aim of this study was to use initial OHC postings to develop an automated model for the classification of OvCa patient and caregiver needs. METHODS: We collected data from the OvCa OHC and analyzed the initial postings of patients and caregivers (n = 853). Two annotators coded each posting with 12 types of needs. Then, we applied the machine learning approach with bag-of-words features to build a model to classify needs. F1 score, an indicator of model accuracy, was used to evaluate the model. RESULTS: The most reported needs were information, social, psychological/emotional, and physical. Thirty-nine percent of postings described information and social needs in the same posting. Our model reported a high level of accuracy for classifying those top needs. Psychological terms were important for classifying psychological/emotional and social needs. Medical terms were important for physical and information needs. CONCLUSIONS: We demonstrate the potential of using OHCs to supplement traditional needs assessment. Further research would incorporate additional information (eg, trajectory, stage) for more sophisticated models. IMPLICATIONS FOR PRACTICE: This study shows the potential of automated classification to leverage OHCs for needs assessment. Our approach can be applied to different types of cancer and enhanced by using domain-specific information.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 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 teacher head, 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".