Analysis of Twitter to Identify Topics Related to Eating Disorder Symptoms
Analysis of Twitter to Identify Topics Related to Eating Disorder Symptoms
复制标题
分析 Twitter 以确定与饮食失调症状相关的主题
DOI：
10.1109/ichi.2019.8904863
复制
发表时间：
2019
期刊：
影响因子：
--
通讯作者：
Zhang, Rui
中科院分区：
文献类型：
--
作者：
Zhou, Sicheng;Zhao, Yunpeng;Rizvi, Rubina;Bian, Jiang;Haynos, Ann F.;Zhang, Rui
进食障碍（ED）是一种严重的精神疾病，与身体和精神问题以及过早死亡有关。检查社交媒体上关于艾德症状的传播可能会为如何预防和治疗这些疾病提供见解。本研究旨在探讨Twitter上与ED相关的话题。我们对18，288条ED相关推文应用了CorEx主题模型，并确定了20个主题，这些主题进一步分为8类。排在前两位的主题类别是身体形象和艾德后果。我们手动评估了推文与其指定主题的相关性，平均准确率为77.86%。我们的发现与另一项使用内容分析的研究一致，我们从这些推文中确定了其他主题，如艾德后果、色情以及治疗和教育。
Eating disorders (EDs) are serious mental illnesses associated with physical and psychiatric problems, and premature death. Examining social media communication about ED symptoms may provide insight into how to prevent and treat these disorders. This study is to explore topics on Twitter related to EDs. We applied the Correlation Explanation (CorEx) topic model on 18,288 ED-related tweets and identified 20 topics, which were further grouped into 8 categories. The top two topic categories are body image and ED consequences. We manually evaluated the relevance of tweets to their assigned topics and average accuracy is 77.86%. Our findings are consistent with another study using content analysis, and we identified additional topics, such as ED consequences, pornography, and treatment and education from these tweets.