基于用户信息行为的微信健康信息关注度研究
|
摘要
【目的/意义】旨在自动分析用户对微信健康信息的关注度。【方法/过程】构建了微信健康信息关注度分析模型,以丁香医生、丁香家庭健康和脉脉养生公众号推送的健康信息作为数据来源,识别微信健康信息的类别和主题分布,基于对用户信息行为的分析来评估用户对健康信息的关注度。【结果/结论】微信公众平台推送的健康信息主要有12类;通过分析用户对微信健康信息关注度发现,健康风险、饮食、药物、身体活动和癌症主题受关注程度较高;用户对各主题健康信息的关注程度与微信公众平台的信息供应分布并不一致。本研究提出的用户关注度自动分析模型具备可以移植性,是对传统关注度研究方法的有效补充。
【Purpose/significance】This paper aims to analyze users' attention to WeChat health information automatically.【Method/process】In this paper, the automated analysis model of collective attention to health information on WeChat was developed. We collected the health information pushed by the public accounts of"dingxiangyisheng","baojiandaifu"and"mmaijiu"as experimental data. The topic distribution of WeChat health information was mined and identified, and the collective attention to health information was evaluated through the analysis of users' information behaviors.【Result/conclusion】WeChat public platform mainly pushes 12 types of health information. By analyzing users' attention to WeChat health information, it is found that health risks, diet, drugs, physical activities, cancer are highly concerned. Users' attention to health information on each subject is not consistent with the release distribution of WeChat public platform. The automated analysis model of collective attention proposed in this study is portable and it is an effective supplement to the traditional research methods of user concern.
【Purpose/significance】This paper aims to analyze users' attention to WeChat health information automatically.【Method/process】In this paper, the automated analysis model of collective attention to health information on WeChat was developed. We collected the health information pushed by the public accounts of"dingxiangyisheng","baojiandaifu"and"mmaijiu"as experimental data. The topic distribution of WeChat health information was mined and identified, and the collective attention to health information was evaluated through the analysis of users' information behaviors.【Result/conclusion】WeChat public platform mainly pushes 12 types of health information. By analyzing users' attention to WeChat health information, it is found that health risks, diet, drugs, physical activities, cancer are highly concerned. Users' attention to health information on each subject is not consistent with the release distribution of WeChat public platform. The automated analysis model of collective attention proposed in this study is portable and it is an effective supplement to the traditional research methods of user concern.
引文
【1】中国信息通信研究院. 2017年微信经济社会影响力研究[EB/OL].http://www.199it.com/archives/720219.html,2018-05-04.
2 束芳彬.微信的传播机制研究[D].武汉:华中师范大学,2015.
3 石文惠,王静雷,李园等.利用微信开展健康传播的探索[J].中国健康教育,2018,(3):326-333.
4 吕亚兰,黄成,周虎.微信平台用户健康信息行为及其影响因素研究[J].医学信息学杂志,2018, 39(3):77-80.
5 金碧漪,许鑫.网络健康社区中的主题特征研究[J].图书情报工作,2015,(12):100-105.
6 侯筱蓉,付扬,陈娟.基于微信平台的健康信息用户感知和效用研究[J].现代情报,2016, 36(10):89-93.
7 张克永,李贺.健康微信公众平台信息质量评价指标体系研究[J].情报科学,2017,(11):143-148.
8 金燕,张启源.基于扎根理论的健康类微信公众号关注度影响因素研究[J].图书馆理论与实践,2018,(4):54-58.
9 戴龙,田丁,骆瑾瑜,等.厦门市居民健康信息关注程度与获取途径分析[J].中国健康教育, 2013,29(4):348-351.
10 单婵娟,龙俊睿,邬碧波,等.上海市社区人群对慢性肾脏病的关注度及其影响因素[J].第二军医大学学报, 2018,(1):37-43.
11 Wu F, Huberman B A. Novelty and Collective Attention[J]. Proc Natl Acad Sci USA, 2007, 104(45):17599-17601.
12 阳德青,肖仰华,汪卫.基于统计模型的社会网络群体关注度的分析与预测[J].计算机研究与发展, 2010, 47(z1):378-384.
13 Frese M. Creating Collective Attention in the Public Domain:Human Interest Narratives and the Rescue of Floyd Collins[J]. Social Forces, 2002, 81(1):57-85.
14 Moussaid M, Helbing D, Theraulaz G. An individualbased model of collective attention[J]. arXiv preprint,2017,arXiv:0909.2757, 2009.
15 董富强.网络用户行为分析研究及其应用[D].西安:西安电子科技大学, 2005.
16 Guan W,GaoH,Yang M, et al. Analyzing user behavior of the micro-blogging website Sina Weibo during hot social events[J]. Physica A:Statistical Mechanics and its Applications, 2014, 395(2):340-351.
17 解军,邢进生.基于KNN算法的新浪微博用户行为分析及预测[J].山西师范大学学报(自然科学版), 2016,(2):38-45.
18 Ghavami S M, Asadpour M, Hatami J, et al. Facebook user's like behavior can reveal personality[C]//2015 7th Conference on Information and Knowledge Technology(IKT).IEEE, 2015:1-3.
19 齐超,陈鸿昶,于岩.基于行为分析的微博信息传播效果[J].计算机应用,2014, 34(8):2404-2408.
20 胡昌平.现代信息管理机制研究[M].武汉:武汉大学出版社,2004:124-132.
21 Ratkiewicz J, Flammini A, Menczer F. Traffic in social media I:paths through information networks[C]//2010 IEEE Second International Conference on Social Computing.IEEE, 2010:452-458.
22 Gan C. Understanding WeChat users’liking behavior:An empirical study in China[J]. Computers in human behavior,2017,68(1):30-39.
23 李重阳,翟姗姗,郑路.网络健康社区信息需求特征测度——基于时间和主题视角的实证分析[J].数字图书馆论坛, 2016,(9):34-42.
24 世界卫生组织.健康主题[EB/OL].https://www.who.int/topics/zh/,2018-12-04.
25 清博指数.微信传播指数WCI[EB/OL].http://www.gsdata.cn/site/usage/,2018-09-01.
26 郭志懋,周傲英.数据质量和数据清洗研究综述[J].软件学报, 2002, 13(11):2076-2082.
27 张卫丰,张迎周,周国强.中文分词技术综述[C]//全国web信息系统及其应用学术会议、全国语义web与本体论学术研讨会暨全国电子政务技术与应用学术研讨会.2008:9-11.
28 Python Software Foundation. Jieba 0.39[EB/OL].https://pypi.org/project/jieba/,2018-12-04.
29 搜狗.细胞词库[EB/OL].https://pinyin.sogou.com/dict/,2018-12-05.
30 Wu H C, Luk R W P, Wong K F, et al. Interpreting TFIDF term weights as making relevance decisions[J]. Acm Transactions on Information Systems, 2008, 26(3):55-59.
31 Pena J M, Lozano J A, Larranaga P. An empirical comparison of four initialization methods for the k-means algorithm[J]. Pattern recognition letters, 1999, 20(10):1027-1040.
32 Ketchen D J, Shook C L. The Application of Cluster Analysis in Strategic Management Research:An Analysis and Critique[J]. Strategic Management Journal, 1996, 17(6):441-458.
33 熊富林,邓怡豪,唐晓晟. Word2vec的核心架构及其应用[J].南京师范大学学报(工程技术版), 2015,(1):43-48.
34 Mac Kay D. An example inference task:clustering[M]. Information Theory, Inference and Learning Algorithms.Cambridge:Cambridge University Press, 2003:284-292.
35 Cha M, Kwak H, Rodriguez P, et al. I tube, you tube, everybody tubes:analyzing the world’s largest user generated content video system[C]//Proceedings of the 7th ACM SIGCOMM conference on Internet measurement. ACM,2007:1-14.
36 Marazzi A, Ruffieux C. The truncated mean of an asymmetric distribution[J]. Computational Statistics&Data Analysis, 1999, 32(1):79-100.
2 束芳彬.微信的传播机制研究[D].武汉:华中师范大学,2015.
3 石文惠,王静雷,李园等.利用微信开展健康传播的探索[J].中国健康教育,2018,(3):326-333.
4 吕亚兰,黄成,周虎.微信平台用户健康信息行为及其影响因素研究[J].医学信息学杂志,2018, 39(3):77-80.
5 金碧漪,许鑫.网络健康社区中的主题特征研究[J].图书情报工作,2015,(12):100-105.
6 侯筱蓉,付扬,陈娟.基于微信平台的健康信息用户感知和效用研究[J].现代情报,2016, 36(10):89-93.
7 张克永,李贺.健康微信公众平台信息质量评价指标体系研究[J].情报科学,2017,(11):143-148.
8 金燕,张启源.基于扎根理论的健康类微信公众号关注度影响因素研究[J].图书馆理论与实践,2018,(4):54-58.
9 戴龙,田丁,骆瑾瑜,等.厦门市居民健康信息关注程度与获取途径分析[J].中国健康教育, 2013,29(4):348-351.
10 单婵娟,龙俊睿,邬碧波,等.上海市社区人群对慢性肾脏病的关注度及其影响因素[J].第二军医大学学报, 2018,(1):37-43.
11 Wu F, Huberman B A. Novelty and Collective Attention[J]. Proc Natl Acad Sci USA, 2007, 104(45):17599-17601.
12 阳德青,肖仰华,汪卫.基于统计模型的社会网络群体关注度的分析与预测[J].计算机研究与发展, 2010, 47(z1):378-384.
13 Frese M. Creating Collective Attention in the Public Domain:Human Interest Narratives and the Rescue of Floyd Collins[J]. Social Forces, 2002, 81(1):57-85.
14 Moussaid M, Helbing D, Theraulaz G. An individualbased model of collective attention[J]. arXiv preprint,2017,arXiv:0909.2757, 2009.
15 董富强.网络用户行为分析研究及其应用[D].西安:西安电子科技大学, 2005.
16 Guan W,GaoH,Yang M, et al. Analyzing user behavior of the micro-blogging website Sina Weibo during hot social events[J]. Physica A:Statistical Mechanics and its Applications, 2014, 395(2):340-351.
17 解军,邢进生.基于KNN算法的新浪微博用户行为分析及预测[J].山西师范大学学报(自然科学版), 2016,(2):38-45.
18 Ghavami S M, Asadpour M, Hatami J, et al. Facebook user's like behavior can reveal personality[C]//2015 7th Conference on Information and Knowledge Technology(IKT).IEEE, 2015:1-3.
19 齐超,陈鸿昶,于岩.基于行为分析的微博信息传播效果[J].计算机应用,2014, 34(8):2404-2408.
20 胡昌平.现代信息管理机制研究[M].武汉:武汉大学出版社,2004:124-132.
21 Ratkiewicz J, Flammini A, Menczer F. Traffic in social media I:paths through information networks[C]//2010 IEEE Second International Conference on Social Computing.IEEE, 2010:452-458.
22 Gan C. Understanding WeChat users’liking behavior:An empirical study in China[J]. Computers in human behavior,2017,68(1):30-39.
23 李重阳,翟姗姗,郑路.网络健康社区信息需求特征测度——基于时间和主题视角的实证分析[J].数字图书馆论坛, 2016,(9):34-42.
24 世界卫生组织.健康主题[EB/OL].https://www.who.int/topics/zh/,2018-12-04.
25 清博指数.微信传播指数WCI[EB/OL].http://www.gsdata.cn/site/usage/,2018-09-01.
26 郭志懋,周傲英.数据质量和数据清洗研究综述[J].软件学报, 2002, 13(11):2076-2082.
27 张卫丰,张迎周,周国强.中文分词技术综述[C]//全国web信息系统及其应用学术会议、全国语义web与本体论学术研讨会暨全国电子政务技术与应用学术研讨会.2008:9-11.
28 Python Software Foundation. Jieba 0.39[EB/OL].https://pypi.org/project/jieba/,2018-12-04.
29 搜狗.细胞词库[EB/OL].https://pinyin.sogou.com/dict/,2018-12-05.
30 Wu H C, Luk R W P, Wong K F, et al. Interpreting TFIDF term weights as making relevance decisions[J]. Acm Transactions on Information Systems, 2008, 26(3):55-59.
31 Pena J M, Lozano J A, Larranaga P. An empirical comparison of four initialization methods for the k-means algorithm[J]. Pattern recognition letters, 1999, 20(10):1027-1040.
32 Ketchen D J, Shook C L. The Application of Cluster Analysis in Strategic Management Research:An Analysis and Critique[J]. Strategic Management Journal, 1996, 17(6):441-458.
33 熊富林,邓怡豪,唐晓晟. Word2vec的核心架构及其应用[J].南京师范大学学报(工程技术版), 2015,(1):43-48.
34 Mac Kay D. An example inference task:clustering[M]. Information Theory, Inference and Learning Algorithms.Cambridge:Cambridge University Press, 2003:284-292.
35 Cha M, Kwak H, Rodriguez P, et al. I tube, you tube, everybody tubes:analyzing the world’s largest user generated content video system[C]//Proceedings of the 7th ACM SIGCOMM conference on Internet measurement. ACM,2007:1-14.
36 Marazzi A, Ruffieux C. The truncated mean of an asymmetric distribution[J]. Computational Statistics&Data Analysis, 1999, 32(1):79-100.
© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号 地址：北京市海淀区学院路29号 邮编：100083 电话：办公室：(+86 10)66554848；文献借阅、咨询服务、科技查新：66554700 |