基于百度贴吧的HIV高危人群特征分析

doi:10.11959/j.issn.2096-0271.2019008

大数据 ›› 2019, Vol. 5 ›› Issue (1): 98-108.doi: 10.11959/j.issn.2096-0271.2019008

基于百度贴吧的HIV高危人群特征分析

肖时耀¹,吕慰²,陈洒然¹,秦烁¹,黄格¹,蔡梦思¹,谭跃进¹,谭旭³,吕欣¹()

¹ 国防科技大学系统工程学院，湖南长沙 410073
² 湖南益阳康雅医院肿瘤科，湖南益阳 413002
³ 深圳信息职业技术学院软件工程学院，广东深圳 518172

出版日期:2019-01-01 发布日期:2019-02-01
作者简介:肖时耀（1996- ），男，国防科技大学系统工程学院硕士生，主要研究领域为大数据分析。|吕慰（1985- ），男，湖南益阳康雅医院肿瘤科主治医师，主要研究领域为放射医学。|陈洒然（1989- ），男，国防科技大学系统工程学院博士生，主要研究领域为复杂网络理论、统计抽样、数据挖掘。|秦烁（1995- ），女，国防科技大学系统工程学院硕士生，主要研究领域为复杂网络传播动力学。|黄格（1991- ），女，国防科技大学系统工程学院博士生，主要研究领域为大数据、复杂网络。|蔡梦思（1992- ），女，国防科技大学系统工程学院博士生，主要研究领域为社交网络、大数据。|谭跃进（1958- ），男，国防科技大学系统工程学院教授，主要研究领域为复杂网络。|谭旭（1981- ），男，深圳信息职业技术学院软件工程学院教授，主要研究领域为智能决策、机器学习、舆情分析。|吕欣（1984- ），男，国防科技大学系统工程学院副教授，主要研究领域为大数据、复杂网络理论、应急管理。
基金资助:
国家自然科学基金资助项目(No.91846301);国家自然科学基金资助项目(No.71771213);国家自然科学基金资助项目(No.71790615);国家自然科学基金资助项目(No.71690233);中国教育部文学和社会科学基金资助项目(No.17YJCZH157);深圳市“鹏城学者计划”基金资助项目

Analysis of HIV high-risk population characteristics with Baidu Tieba data

Shiyao XIAO¹,Wei LYU²,Saran CHEN¹,Shuo QIN¹,Ge HUANG¹,Mengsi CAI¹,Yuejin TAN¹,Xu TAN³,Xin LU¹()

¹ School of Systems Engineering, National University of Defense Technology, Changsha 410073, China
² Department of Oncology, Kangya Hospital, Yiyang 413002, China
³ School of Software Engineering, Shenzhen Institute of Information Technology, Shenzhen 518172, China

Online:2019-01-01 Published:2019-02-01
Supported by:
The National Natural Science Foundation of China(No.91846301);The National Natural Science Foundation of China(No.71771213);The National Natural Science Foundation of China(No.71790615);The National Natural Science Foundation of China(No.71690233);The MOE(Ministry of Education in China)Liberal Arts and Social Sciences Foundation(No.17YJCZH157);The Pengcheng Scholar Funded Scheme

摘要/Abstract

摘要：

对百度贴吧“恐艾吧”中在线高危人群的帖子内容、线上活动时间规律进行了分析，利用LDA话题模型，对比分析了有无HIV感染者参与的主贴讨论的话题之间的差异，使用基于关键词的机器学习方法区分了在“恐艾吧”中发布话题的用户的性取向，计算不同性取向人群中HIV的流行率。研究结果说明，使用在线数据挖掘的技术和方法比传统方法更加高效，可以作为高危人群研究的重要补充。此外，基于机器学习对人群性取向进行智能判别，对于公共卫生管理部门监测疫情在不同人群中的发展状况有重要意义。

关键词: 在线高危人群, 男同性恋, HIV, LDA话题模型, 百度贴吧, 机器学习

Abstract:

The textual content and temporal pattern of online activities for users gathered in the “Fear of HIV Bar” of Baidu Tieba were analyzed. LDA topic model was used to analyze the main differences between topics discussed among HIV-infected people and non-HIV-infected people. A machine learning method based on key words was used to distinguish the sexual orientation of users who start a discussion in “Fear of HIV Bar”, and calculate the epidemic rate of HIV among groups with different sexual orientations. The techniques used in this paper can be supplemented as an important tool for high-risk populations research. In addition, this paper can be applied to assess the epidemic of HIV in populations with different sexual orientations by using machine learning technique to intelligently classify the sexual orientation of a user, which is of great significance for the public health agencies.

Key words: online high-risk populations, MSM, HIV, LDA topic model, Baidu Tieba, machine learning

中图分类号:

TP391.1

肖时耀, 吕慰, 陈洒然, 秦烁, 黄格, 蔡梦思, 谭跃进, 谭旭, 吕欣. 基于百度贴吧的HIV高危人群特征分析[J]. 大数据, 2019, 5(1): 98-108.

Shiyao XIAO, Wei LYU, Saran CHEN, Shuo QIN, Ge HUANG, Mengsi CAI, Yuejin TAN, Xu TAN, Xin LU. Analysis of HIV high-risk population characteristics with Baidu Tieba data[J]. Big Data Research, 2019, 5(1): 98-108.

图/表 8

图1

图2

图3

图4

图5

表1

表2

图6

参考文献 24

[1]	方鹏骞，张佳慧，徐娟 . 我国艾滋病高危人群定义与范畴的界定[J]. 中国艾滋病性病， 2006,12(5): 470-471.
	FANG P Q , ZHANG J H . The definition and category of high-risk group of AIDS(infected with AIDS) in China[J]. Chinese Journal of AIDS and STD, 2006,12(5): 470-471.
[2]	MCLAUGHLIN K . HIV infections are spiking among young gay Chinese[J]. Science, 2017,355(6332): 1359.
[3]	XU J J , ZHANG M , BROWN K , et al. Syphilis and HIV seroconversion among a 12-month prospective cohort of men who have sex with men in Shenyang, China[J]. Sexually Transmitted Diseases, 2010,37(7): 432.
[4]	YANG H , HAO C , HUAN X , et al. HIV incidence and associated factors in a cohort of men who have sex with men in Nanjing, China[J]. Sexually Transmitted Diseases, 2010,37(4): 208-213.
[5]	RUAN Y , JIA Y , ZHANG X , et al. Incidence of HIV-1, syphilis, hepatitis B, and hepatitis C virus infections and predictors associated with retention in a 12-month follow-up study among men who have sex with men in Beijing, China[J]. JAIDS Journal of Acquired Immune Deficiency Syndromes, 2009,52(5): 604-610.
[6]	LIAU A , MILLETT G , MARKS G . Metaanalytic examination of online sex-seeking and sexual risk behavior among men who have sex with men[J]. Sexually Transmitted Diseases, 2006,33(9): 576-584.
[7]	SHARP K , EARLE S . Dot.cons: crime, deviance and identity on the internet[M]. Cullompton: Willan Publishing, 2003:36-52.
[8]	YANHAI W , RAN H , RAN G , et al. Discrimination against people with HIV/AIDS in China[J]. The Equal Rights Review, 2009,4: 15-25.
[9]	ZHANG B C , CHU Q S . MSM and HIV/AIDS in China[J]. Cell Research, 2005,15(11): 858.
[10]	ZHANG P , CHI X , WU M , et al. Status and influencing factors of attitude toward LGBT among college students[J]. Chinese Journal of Public Health, 2012,28: 921-923.
[11]	BARAL S , SIFAKIS F , CLEGHORN F , et al. Elevated risk for HIV infection among men who have sex with men in low-and middle-income countries 2000– 2006:a systematic review[J]. PLoS Medicine, 2007,4(12): e339.
[12]	LIU J X , CHOI K . Experiences of social discrimination among men who have sex with men in Shanghai, China[J]. AIDS and Behavior, 2006,10(1): 25-33.
[13]	LIU H , YANG H , LI X , et al. Men who have sex with men and human immunodeficiency virus/sexually transmitted disease control in China[J]. Sexually Transmitted Diseases, 2006,33(2): 68-76.
[14]	FENG Y , WU Z , DETELS R . Evolution of MSM community and experienced stigma among MSM in Chengdu, China[J]. Journal of Acquired Immune Deficiency Syndromes (1999), 2010,53(Suppl1): S98.
[15]	WU Z , XU J , LIU E , et al. HIV and syphilis prevalence a mong men who have sex with men: a cross-sectional survey of 61 cities in China[J]. Clinical Infectious Diseases, 2013,57(2): 298-309.
[16]	BEYRER C , SULLIVAN P S , SANCHEZ J , et al. A call to action for comprehensive HIV services for men who have sex with men[J]. The Lancet, 2012,380(9839): 424-438.
[17]	CHOI S Y P , HOLROYD E . The influence of power, poverty and agency in the negotiation of condom use for female sex workers in mainland China[J]. Culture, Health & Sexuality, 2007,9(5): 489-503.
[18]	BARAL S , BEYRER C , MUESSIG K , et al. Burden of HIV among female sex workers in low-income and middleincome countries: a systematic review and meta-analysis[J]. The Lancet Infectious Diseases, 2012,12(7): 538-549.
[19]	ROCHA L E C , LILJEROS F , HOLME P . Information dynamics shape the sexual networks of Internet-mediated prostitution[J]. Proceedings of the National Academy of Sciences of the United States of America, 2010,107(13): 5706-5711.
[20]	LIM S H , GUADAMUZ T E , WEI C , et al. Factors associated with unprotected receptive anal intercourse with internal ejaculation among men who have sex with men in a large Internet sample from Asia[J]. AIDS and Behavior, 2012,16(7): 1979-1987.
[21]	LIU C , LU X . Analyzing hidden populations online: topic, emotion, and social network of HIV-related users in the largest Chinese online community[J]. BMC Medical Informatics and Decision Making, 2018,18(1): 2.
[22]	刘楚楚，吕欣 . 基于公开数据的特殊人群在线活动特征挖掘[J]. 大数据， 2018,4(5): 15-28.
	LIU C C , LU X . Activity mining of online hidden population based on public data[J]. Big Data Research, 2018,4(5): 15-28.
[23]	EICHSTAEDT J C , SMITH R J , MERCHANT R M , et al. Facebook language predicts depression in medical records[J]. Proceedings of the National Academy of Sciences, 2018,115(44): 11203-11208.
[24]	BLEI D M , NG A Y , JORDAN M I . Latent dirichlet allocation[J]. Journal of Machine Learning Research, 2003,3(1): 993-1022.

实际		预测
实际	未知	异性恋	同性恋
未知	112	7	5
异性恋	22	112	2
同性恋	4	0	16

类别	精确率	召回率	f1-score
异性恋	0.94	0.82	0.88
同性恋	0.7	0.8	0.74
未知	0.81	0.9	0.85
平均	0.87	0.86	0.86

基于百度贴吧的HIV高危人群特征分析

Analysis of HIV high-risk population characteristics with Baidu Tieba data

在线阅读

PDF下载

可视化

摘要/Abstract

引用本文

使用本文

图/表 8

参考文献 24

相关文章 12

Metrics

推荐阅读 0

[1]	张伶俐, 褚琦凯, 王桂娟, 张巍瀚, 蒲慧, 宋振金, 吴亚东. 文本情感可视分析技术及其在人文领域的应用[J]. 大数据, 2022, 8(6): 56-73.
[2]	吴建汉, 司世景, 王健宗, 肖京. 联邦学习攻击与防御综述[J]. 大数据, 2022, 8(5): 12-32.
[3]	任帅, 陈丹丹, 储根深, 白鹤, 李慧昭, 何远杰, 胡长军. 基于材料数值计算大数据的材料辐照机理发现[J]. 大数据, 2021, 7(6): 3-18.
[4]	于璠. 新一代深度学习框架研究[J]. 大数据, 2020, 6(4): 69-80.
[5]	张旭东, 孙圣力, 王洪超. 基于数据挖掘的触诊成像乳腺癌智能诊断模型和方法[J]. 大数据, 2019, 5(1): 68-76.
[6]	刘楚楚, 吕欣. 基于公开数据的特殊人群在线活动特征挖掘[J]. 大数据, 2018, 4(5): 15-28.
[7]	王秉睿, 兰慧盈, 陈云霁. 深度学习编程框架[J]. 大数据, 2018, 4(4): 56-63.
[8]	张国宾, 王晓蓉, 邓春宇. 基于关联分析与机器学习的配网台区重过载预测方法[J]. 大数据, 2018, 4(1): 105-116.
[9]	王冬海,卢峰,方晓蓉,郭刚. 海洋大数据关键技术及在灾害天气下船舶行为预测上的应用[J]. 大数据, 2017, 3(4): 81-90.
[10]	牟少敏, 温孚江, 宋长青. 农业大数据研究生培养模式探索[J]. 大数据, 2016, 2(1): 53-58.
[11]	林春雨, 李崇纲, 许方圆, 许会泉, 石磊, 卢祥虎. 基于大数据技术的P2P网贷平台风险预警模型[J]. 大数据, 2015, 1(4): 18-28.
[12]	黄宜华. 大数据机器学习系统研究进展[J]. 大数据, 2015, 1(1): 35-54.