Perception and sentiment analysis of palliative care in Chinese social media: Qualitative studies based on machine learning

IF 4.9 2区医学 Q1 PUBLIC, ENVIRONMENTAL & OCCUPATIONAL HEALTH

Social Science & Medicine Pub Date : 2025-05-10 DOI:10.1016/j.socscimed.2025.118178

Qi Zhou , Yuling Lei , Luwen Tian , Shanshan Ai , Yuting Yang , Yueli Zhu

{"title":"Perception and sentiment analysis of palliative care in Chinese social media: Qualitative studies based on machine learning","authors":"Qi Zhou , Yuling Lei , Luwen Tian , Shanshan Ai , Yuting Yang , Yueli Zhu","doi":"10.1016/j.socscimed.2025.118178","DOIUrl":null,"url":null,"abstract":"<div><h3>Background</h3><div>Traditional Chinese culture makes death a sensitive and taboo topic, leading patients and family members to refuse to choose palliative care.</div></div><div><h3>Aim</h3><div>To explore the current situation of the public's perception and sentiment towards palliative care and reduce the barriers health-related persons face in providing professional services.</div></div><div><h3>Method</h3><div>The research steps include text acquisition, text cleaning, data standardization, K-Means clustering algorithm, and sentiment analysis algorithm.</div></div><div><h3>Results</h3><div>This study had 9017 comments. The comments increased yearly from 2014 to 2023. K-Means clustering results showed patients' physical condition, disease knowledge, and nursing service. Boson NLP results showed 3264 negative comments, 3451 positive comments, and 2302 neutral objective comments. The dictionary method showed positive and negative emotions such as anger, disgust, fear, sad, surprise, good, and happy. Negative emotions were mainly in Physical and mental condition. Positive emotions were mainly in nursing service and unrelated to disease knowledge.</div></div><div><h3>Conclusion</h3><div>Healthcare professionals should pay attention to the adverse effects of public misperceptions and negative emotions. They provide appropriate measures to enhance positive emotions and perceptions and encourage patients to accept palliative care.</div></div>","PeriodicalId":49122,"journal":{"name":"Social Science & Medicine","volume":"379 ","pages":"Article 118178"},"PeriodicalIF":4.9000,"publicationDate":"2025-05-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Social Science & Medicine","FirstCategoryId":"3","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0277953625005088","RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"PUBLIC, ENVIRONMENTAL & OCCUPATIONAL HEALTH","Score":null,"Total":0}

引用次数: 0

Abstract

Background

Traditional Chinese culture makes death a sensitive and taboo topic, leading patients and family members to refuse to choose palliative care.

Aim

To explore the current situation of the public's perception and sentiment towards palliative care and reduce the barriers health-related persons face in providing professional services.

Method

The research steps include text acquisition, text cleaning, data standardization, K-Means clustering algorithm, and sentiment analysis algorithm.

Results

This study had 9017 comments. The comments increased yearly from 2014 to 2023. K-Means clustering results showed patients' physical condition, disease knowledge, and nursing service. Boson NLP results showed 3264 negative comments, 3451 positive comments, and 2302 neutral objective comments. The dictionary method showed positive and negative emotions such as anger, disgust, fear, sad, surprise, good, and happy. Negative emotions were mainly in Physical and mental condition. Positive emotions were mainly in nursing service and unrelated to disease knowledge.

Conclusion

Healthcare professionals should pay attention to the adverse effects of public misperceptions and negative emotions. They provide appropriate measures to enhance positive emotions and perceptions and encourage patients to accept palliative care.

查看原文本刊更多论文

中国社交媒体对姑息治疗的感知与情绪分析：基于机器学习的定性研究

中国传统文化使死亡成为一个敏感和禁忌的话题，导致患者和家属拒绝选择姑息治疗。目的探讨公众对姑息治疗的认知和情绪现状，减少健康相关人士在提供专业服务时面临的障碍。方法研究步骤包括文本采集、文本清洗、数据标准化、K-Means聚类算法和情感分析算法。结果本研究共发表评论9017条。从2014年到2023年，评论每年都在增加。K-Means聚类结果显示患者的身体状况、疾病知识和护理服务。Boson NLP结果显示3264条负面评论，3451条正面评论，2302条中立客观评论。字典法显示了积极和消极的情绪，如愤怒、厌恶、恐惧、悲伤、惊讶、美好和快乐。负性情绪主要表现在身体和精神两方面。积极情绪主要存在于护理服务中，与疾病知识无关。结论卫生保健工作者应重视公众误解和负面情绪的不良影响。他们提供适当的措施来增强积极的情绪和感知，并鼓励患者接受姑息治疗。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Social Science & Medicine PUBLIC, ENVIRONMENTAL & OCCUPATIONAL HEALTH-

CiteScore

9.10

自引率

5.60%

发文量

762

审稿时长

38 days

期刊介绍： Social Science & Medicine provides an international and interdisciplinary forum for the dissemination of social science research on health. We publish original research articles (both empirical and theoretical), reviews, position papers and commentaries on health issues, to inform current research, policy and practice in all areas of common interest to social scientists, health practitioners, and policy makers. The journal publishes material relevant to any aspect of health from a wide range of social science disciplines (anthropology, economics, epidemiology, geography, policy, psychology, and sociology), and material relevant to the social sciences from any of the professions concerned with physical and mental health, health care, clinical practice, and health policy and organization. We encourage material which is of general interest to an international readership.