Understanding Cancer Survivorship Care Needs Using Amazon Reviews: Content Analysis, Algorithm Development, and Validation Study
Bibliographic record
Abstract
Background: Complementary therapies are being increasingly used by cancer survivors. As a channel for customers to share their feelings, outcomes, and perceived knowledge about the products purchased from e-commerce platforms, Amazon consumer reviews are a valuable real-world data source for understanding cancer survivorship care needs. Objective: In this study, we aimed to highlight the potential of using Amazon consumer reviews as a novel source for identifying cancer survivorship care needs, particularly related to symptom self-management. Specifically, we present a publicly available, manually annotated corpus derived from Amazon reviews of health-related products and develop baseline natural language processing models using deep learning and large language model (LLM) to demonstrate the usability of this dataset. Methods: We preprocessed the Amazon review dataset to identify sentences with cancer mentions through a rule-based method and conducted content analysis including text feature analysis, sentiment analysis, topic modeling, cancer type, and symptom association analysis. We then designed an annotation guideline, targeting survivorship-relevant constructs. A total of 159 reviews were annotated, and baseline models were developed based on deep learning and large language model (LLM) for named entity recognition and text classification tasks. Results: A total of 4703 sentences containing positive cancer mentions were identified, drawn from 3349 reviews associated with 2589 distinct products. The identified topics through topic modeling revealed meaningful insights into cancer symptom management and survivorship experiences. Examples included discussions of green tea use during chemotherapy, cancer prevention strategies, and product recommendations for breast cancer. Top 15 symptoms in reviews were also identified, with pain being the most frequent symptom, followed by inflammation, fatigue, etc. The annotation labels were designed to capture cancer types, indicated symptoms, and symptom management outcomes. The resulting annotation corpus contains 2067 labels from 159 Amazon reviews. It is publicly accessible, together with the annotation guideline through the Open Health Natural Language Processing (OHNLP) GitHub. Our baseline model, Bert-base-cased, achieved the highest weighted average F1-score, that is, 66.92%, for named entity recognition, and LLM gpt4-1106-preview-chat achieved the highest F1-score for text classification tasks, that is, 66.67% for "Harmful outcome," 88.46% for "Favorable outcome" and 73.33% for "Ambiguous outcome." Conclusions: Our results demonstrate the potential of Amazon consumer reviews as a novel data source for identifying persistent symptoms, concerns, and self-management strategies among cancer survivors. This corpus, along with the baseline natural language processing models developed for named entity recognition and text classification, lays the groundwork for future methodological advancements in cancer survivorship research. Importantly, insights from this study could be evaluated against established clinical guidelines for symptom management in cancer survivorship care. By revealing the feasibility of using consumer-generated data for mining survivorship-related experiences, this study offers a promising foundation for future research and argumentation analysis aimed at improving long-term outcomes and support for cancer survivors.
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 | 0.003 | 0.015 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.002 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.001 |
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".