%0期刊文章%@ 2561- 7605% I JMIR出版物%V 5%卡塔尔世界杯8强波胆分析 N 3% P 39547% T自动识别Twitter用户的干预措施，以支持痴呆症家庭护理人员:注释数据集和基准分类模型%A Klein,Ari Z %A Magge,Arjun %A O'Connor,Karen %A Gonzalez-Hernandez,Graciela +生物统计、流行病学和信息学系，宾夕法尼亚大学佩雷尔曼医学院，Blockley Hall, 4楼，423,Guardian博士，费城，宾夕法尼亚州，19104，美国，1 310 423 3521，ariklein@pennmedicine.upenn.edu %K自然语言处理%K社交媒体%K数据挖掘%K痴呆症%K阿尔茨海默病%K护理人员%D 2022 %7 16.9.2022 %9短论文%J JMIR老龄化%G英语%X背景:美国有超过600万人患有阿尔茨海默病和相关痴呆症，接受超过1100万家庭或其他非正式护理人员的帮助。制定了一系列传统干预措施，以支持家庭照顾者;然而，其中大多数尚未在实践中得到实施，而且在很大程度上仍然无法实现。虽然最近的研究表明，痴呆症患者的家庭照顾者使用Twitter讨论他们的经历，但还没有开发出能够使用Twitter进行干预的方法。目的:本研究的目的是开发一个注释数据集和基准分类模型，用于自动识别家庭成员患有痴呆症的Twitter用户队列。方法:在2021年5月4日至5月20日期间，我们收集了8846名用户发布的10733条推文，这些推文提到了一个与痴呆症相关的关键词，一个可能表明诊断的语言标记，以及一个选定的家庭关系。三名注释人员为每个用户随机注释一条推文，以区分那些表明家庭成员患有痴呆症的人。注释者间的一致性为0.82 (Fleiss kappa)。 We used the annotated tweets to train and evaluate support vector machine and deep neural network classifiers. To assess the scalability of our approach, we then deployed automatic classification on unlabeled tweets that were continuously collected between May 4, 2021, and March 9, 2022. Results: A deep neural network classifier based on a BERT (bidirectional encoder representations from transformers) model pretrained on tweets achieved the highest F1-score of 0.962 (precision=0.946 and recall=0.979) for the class of tweets indicating that the user has a family member with dementia. The classifier detected 128,838 tweets that indicate having a family member with dementia, posted by 74,290 users between May 4, 2021, and March 9, 2022—that is, approximately 7500 users per month. Conclusions: Our annotated data set can be used to automatically identify Twitter users who have a family member with dementia, enabling the use of Twitter on a large scale to not only explore family caregivers’ experiences but also directly target interventions at these users. %M 36112408 %R 10.2196/39547 %U https://aging.www.mybigtv.com/2022/3/e39547 %U https://doi.org/10.2196/39547 %U http://www.ncbi.nlm.nih.gov/pubmed/36112408