%0期刊文章%@ 2369- 2960% I JMIR Publica卡塔尔世界杯8强波胆分析tions %V 4% N 1% P e5% T通过推文内容分析监测大一新生的大学经历:观察性研究%A Liu,Sam %A Zhu,Miaoqi %A Young,Sean D %+运动科学学院，体育与健康教育，维多利亚大学，PO Box 1700 STN CSC，维多利亚，BC，，加拿大，1 250 721 8392,samliu@uvic.ca %K社交网络%K大数据%K人口监测%K教育%K学生%K社交媒体%K推特%D 2018 %7 11.01.2018 %9原创论文%J JMIR公共卫生监测%G英语%X背景:大一经历可以极大地影响学生的成功。监测新生经历的传统方法，比如进行调查，既耗费资源又耗时。社交媒体，如推特，使用户能够分享他们的日常经验。因此，使用Twitter来监控学生的毕业后经历是可能的。目的:我们的目标是:(1)描述大学生在整个学期中在Twitter上发布的与学术研究、个人健康和社会生活有关的内容的比例;(2)检查内容的比例是否因人口统计而异，以及在非考试期间与考试期间。方法:在2015年10月5日至12月11日期间，我们收集了170名就读于美国加州洛杉矶大学的18至20岁新生的推文。我们使用关键字搜索将这些推文分类为与学术、个人健康和社会生活相关的主题。Mann-Whitney U和Kruskal-Wallis H测试研究了发布的内容是否因性别、种族和专业而不同。 The Friedman test determined whether the total number of tweets and percentage of tweets related to academic studies, personal health, and social life differed between nonexam (weeks 1-8) and final exam (weeks 9 and 10) periods. Results: Participants posted 24,421 tweets during the fall semester. Academic-related tweets (n=3433, 14.06%) were the most prevalent during the entire semester, compared with tweets related to personal health (n=2483, 10.17%) and social life (n=1646, 6.74%). The proportion of academic-related tweets increased during final-exam compared with nonexam periods (mean rank 68.9, mean 18%, standard error (SE) 0.1% vs mean rank 80.7, mean 21%, SE 0.2%; Z=–2.1, P=.04). Meanwhile, the proportion of tweets related to social life decreased during final exams compared with nonexam periods (mean rank 70.2, mean 5.4%, SE 0.01% vs mean rank 81.8, mean 7.4%, SE 0.01%; Z=–4.8, P<.001). Women tweeted more often than men during both nonexam (mean rank 95.8 vs 76.8; U=2876, P=.02) and final-exam periods (mean rank 96.2 vs 76.2; U=2832, P=.01). The percentages of academic-related tweets were similar between ethnic groups during nonexam periods (P>.05). However, during the final-exam periods, the percentage of academic tweets was significantly lower among African Americans than whites (χ24=15.1, P=.004). The percentages of tweets related to academic studies, personal health, and social life were not significantly different between areas of study during nonexam and exam periods (P>.05). Conclusions: The results suggest that the number of tweets related to academic studies and social life fluctuates to reflect real-time events. Student’s ethnicity influenced the proportion of academic-related tweets posted. The findings from this study provide valuable information on the types of information that could be extracted from social media data. This information can be valuable for school administrators and researchers to improve students’ university experience. %M 29326096 %R 10.2196/publichealth.7444 %U http://publichealth.www.mybigtv.com/2018/1/e5/ %U https://doi.org/10.2196/publichealth.7444 %U http://www.ncbi.nlm.nih.gov/pubmed/29326096