印尼消费者健康问题的语义分类
Raniah Nur Hanami1, Rahmad Mahendra1, Alfan Farizki Wicaksono2
1Faculty of Computer Science, Universitas Indonesia, Kampus UI, Depok, 16424, West Java, Indonesia.
这项研究开发了印尼健康问题的语义类型分类器,创建了一个新的数据集,并使用LIME进行偏差分析. 模型显示了处理偏差数据的潜力,其中Perceptron和XGBoost表现最好.
科学领域:
- 自然语言处理自然语言处理.
- 机器学习 机器学习
- 消费者健康信息学
背景情况:
- 在线健康论坛促进了公共医疗专业人员的互动,但由于医疗保健专业人员的有限性,他们面临着及时答案的挑战.
- 自动问题答案 (QA) 系统可以提高响应时间,需要语义问题类型分类来理解用户的意图.
研究的目的:
- 提出一种新的两步方法,用于印尼消费者健康问题的语义类型分类.
- 通过创建一个新的注释库来解决印尼卫生领域数据的稀缺问题.
- 为提问语义类型构建和评估数据驱动的预测模型,包括可解释性和偏差分析.
主要方法:
- 开发了一套由964个注释的印尼消费者健康问题组成的新集体.
- 利用数据驱动的预测模型进行语义类型分类.
- 采用LIME (局部可解释模型-不可知解释) 框架来进行模型可解释性和偏差分析.
主要成果:
- 标注显示了专家标注者之间适度的共识.
- XGBoost,Naïve Bayes和MLP模型显示,倾向于将"癌症"和"抑郁症"问题归类为诊断.
- 感知器和XGBoost获得了最高的加权平均F1分数;在与边界SMOTE进行数据平衡后,天真贝叶斯表现最好.
结论:
- 构建了一个印尼消费者健康查询语义的语料库,构成了预测模型的基础.
- 研究了疾病偏差词的影响,在排除这些词时没有发现显著的性能差异,这表明模型可以减轻偏差.
- 该研究强调了机器学习模型在理解和分类消费者健康问题方面的潜力,即使数据有限或可能有偏见.
更多相关视频
06:39Electroencephalographic, Heart Rate, and Galvanic Skin Response Assessment for an Advertising Perception Study: Application to Antismoking Public Service Announcements
Published on: August 28, 2017
13:44Project-Based Learning Guidelines for Health Sciences Students: An Analysis with Data Mining and Qualitative Techniques
Published on: December 9, 2022
相关概念视频
Classification of Illness
An illness is a response to a disease in which the person's level of functioning is changed compared with a previous level. The general classification of illness includes acute and chronic.
Acute illness is severe...
Concepts of Health and Illness
Assessment of the Gastrointestinal System II: Health Perception Pattern
Health Perception Patterns
Health perception patterns offer valuable insights into a patient's lifestyle habits and how they may impact their GI health. These patterns include:
Health Literacy
Cardiovascular Drugs: Classification based on Therapeutic Indications
Levels of Health Promotion and Illness Prevention
In primary prevention, actions taken before disease onset prevent the disease from...
