基于社交媒体的医药领域关联主题预测方法研究<sup>*</sup>

doi:10.11925/infotech.2096-3467.2021.0583

数据分析与知识发现

2021, Vol. 5

Issue (12): 98-109 https://doi.org/10.11925/infotech.2096-3467.2021.0583

研究论文

本期目录 | 过刊浏览 | 高级检索

基于社交媒体的医药领域关联主题预测方法研究^*

吴胜男¹,田若楠²,蒲虹君¹,梁雯琪²,张亚飞²,于琦¹,贺培凤^1,²(

)

¹山西医科大学管理学院太原 030000
²山西医科大学人文社会科学学院太原 030000

Predicting Related Medical Topics from Social Media

Wu Shengnan¹,Tian Ruonan²,Pu Hongjun¹,Liang Wenqi²,Zhang Yafei²,Yu Qi¹,He Peifeng^1,²(

)

¹School of Management, Shanxi Medical University, Taiyuan 030000, China
²School of Humanities and Social Sciences, Shanxi Medical University, Taiyuan 030000, China

摘要
图/表
参考文献
相关文章
Metrics

全文: PDF (3431 KB) HTML ( 28 )
输出: BibTeX | EndNote (RIS)

摘要

【目的】 从社交媒体视角出发,提出一种全新的知识发现思路和方法,预测医药领域主题关联机会,实现新兴主题早发现、早研究。【方法】 以社交媒体为数据源,针对医药卫生领域文本挖掘研究方法存在的不足,提出Co-LDA主题模型和链路预测相结合的方法,预测核心主题关联机会。并选用新浪微博中糖尿病类药物数据为实验样本,对所提方法进行实例验证。【结果】 医药研究领域不含权主题共现网络链路预测AUC值高于含权网络,且最优指标为Katz指标;未来糖尿病药物领域研究最可能和药效学研究与治疗方案的改进、医药行业发展以及药物新适应症研究产生关联。【局限】 仅从语义角度进行主题挖掘,缺乏情感和时间维度的多层次分析;链路预测算法复杂度高且对于连通性较差的网络预测效果欠佳。【结论】 利用所提方法从社交媒体角度预测医药领域主题关联机会具有一定的科学性和有效性。

	服务

	把本文推荐给朋友
	加入引用管理器
	E-mail Alert
	RSS
	作者相关文章
	吴胜男
	田若楠
	蒲虹君
	梁雯琪
	张亚飞
	于琦
	贺培凤

关键词 ：知识发现, 主题关联, LDA, 链路预测

Abstract：

[Objective] This paper proposes a new knowledge discovery method for social media, aiming to predict the topic-related opportunities and emerging topics in medicine.[Methods] We developed a method combining the Co-LDA topic model and the link prediction algorithm to identify topic association opportunities. We examined the new model with data on diabetes drugs from social media. [Results] The AUC value of the prediction for the common network link without the right topics was higher than those with the right topics, while the Katz index is the optimal one. The future research on diabetes drugs is most likely to be related to the improvement of pharmacodynamic research and treatment plans. The development of the pharmaceutical industry and the new drug indications were related. [Limitations] We did not conduct multi-level analysis with emotional and time dimensions, and the new algorithm is very complex and did not perform well with poor network connectivity. [Conclusions] The proposed method could effectively predict the topic association opportunities in the field of medicine.

Key words： Knowledge Discovery Topic Association LDA Link Prediction

收稿日期: 2021-06-15 出版日期: 2022-01-20

ZTFLH:

G250

基金资助:* 国家自然科学基金青年项目(71804102);国家自然科学基金青年项目(71573162);国家自然科学基金面上项目(71573162)

通讯作者: 贺培凤,ORCID：0000-0002-3742-6983 E-mail: hepeifeng2006@126.com

引用本文:

吴胜男, 田若楠, 蒲虹君, 梁雯琪, 张亚飞, 于琦, 贺培凤. 基于社交媒体的医药领域关联主题预测方法研究^*[J]. 数据分析与知识发现, 2021, 5(12): 98-109.
Wu Shengnan, Tian Ruonan, Pu Hongjun, Liang Wenqi, Zhang Yafei, Yu Qi, He Peifeng. Predicting Related Medical Topics from Social Media. Data Analysis and Knowledge Discovery, 2021, 5(12): 98-109.

链接本文:

https://manu44.magtech.com.cn/Jwk_infotech_wk3/CN/10.11925/infotech.2096-3467.2021.0583 或 https://manu44.magtech.com.cn/Jwk_infotech_wk3/CN/Y2021/V5/I12/98

Fig.1 基于Co-LDA的主题识别方法

Fig.2 基于主题共现网络的链路预测

指标		基于节点局部信息的相似性指标
指标		不含权算法	含权算法
AA	$S xy = ∑ z ∈ (x) ? Γ (y) 1 lg k (z)$ ^[20]		$S y x = ∑ z ∈ Γ (x) ? Γ (y) W xz + W zy 2 lg (1 + S z)$ ^[21]
PA	$S xy = k (x) k (y)$ ^[22]		$S xy PA = ∑ x' ∈ (x', x) w (x', x) ∑ y' ∈ (y', y) w (y', y)$ ^[23]
RA	$S xy = ∑ z ∈ Γ (x) ? Γ (y) 1 k (z)$ ^[24]		$S xy RA = ∑ z ∈ Γ (x) ? Γ (y) W xz + W zy S z$ ^[21]
CN	$S xy = \| Γ (x) ? Γ (y) \|$ ^[25]		$S xy CN = ∑ z ∈ Γ (x) ? Γ (y) W xz + W zy$ ^[21]
Salton	$S xy = \| Γ (x) ? Γ (y) \| k (x) k (y)$ ^[26]		$S xy salton = ∑ z ∈ Γ (x) ? Γ (y) W xz + W zy s (x) s (y)$ ^[27]
Jaccard	$S xy = \| Γ (x) ? Γ (y) \| \| Γ (x) ? Γ (y) \|$ ^[28]		$S xy Ja = ∑ z ∈ Γ (x) ? Γ (y) W xz + W zy s (x) + s (y) - w (x, y)$ ^[27]
Sorenson	$S xy = 2 \| Γ (x) ? Γ (y) \| k (x) + k (y)$ ^[29]		$S xy so = 2 ∑ z ∈ Γ (x) ? Γ (y) W xz + W zy s (x) + s (y) 12$ ^[27]
大度节点有利	$S xy = \| Γ (x) ? Γ (y) \| min k (x), k (y)$ ^[30]		$S xy = ∑ z ∈ Γ (x) ? Γ (y) W xz + W zy min s (x), s (y)$ ^[27]
大度节点不利	$S xy = \| Γ (x) ? Γ (y) \| max k (x), k (y)$ ^[31]		$S xy = ∑ z ∈ Γ (x) ? Γ (y) W xz + W zy max s (x), s (y)$ ^[27]
LHN-Ⅰ	$S xy = \| Γ (x) ? Γ (y) \| k (x) k (y)$ ^[31]		$S xy LHN = ∑ z ∈ Γ (x) ? Γ (y) W xz + W zy s (x) s (y)$ ^[27]
指标	基于路径的相似性指标
LP	$S = A 2 + ∂ A 3$ ^[26]		$S xy LP = ∑ l xy n ∈ L (x, y) l xy 2 ∂ l xy 3$ ^[28]
Katz	$S = (I - ∂ A - 1) - I$ ^[32] $∂$ 小于A最大特征值的倒数		$S = (I - ∂ A) - 1 - I$ ^[32] A为含权矩阵,且 $∂$ 小于A最大特征值的倒数

Table 1 链路预测相似性指标定义

Table 2 2型糖尿病类药物

Fig.3 糖尿病药物主题模型JS距离曲线

主题编号	主题名	主题编号	主题名
Topic1	国家集中药品采购	Topic22	新闻媒体对降糖药的报道
Topic2	降低药品价格,改善行业生态	Topic23	2型糖尿病治疗方案研究
Topic3	国内糖尿病高仿药上市	Topic24	临床试药员招募
Topic4	二甲双胍和胰岛素联合用药疗效显著	Topic25	药物作用机制
Topic5	保健品非法添加苯乙双胍,病死率增加	Topic26	药物疗效与饮食控制的关联研究
Topic6	药物剂量与不良反应的关系	Topic27	用药后疗效追踪
Topic7	二甲双胍和胰岛素联合治疗产生不良反应	Topic28	胰岛素介入治疗效果研究
Topic8	两病联合治疗效果	Topic29	调节血糖类保健产品功效介绍
Topic9	二甲双胍可降低糖耐量受损人群患病风险	Topic30	二甲双胍药物不良反应研究
Topic10	格列吡嗪通过促进胰岛素的分泌降低血糖	Topic31	阿卡波糖和二甲双胍联合治疗研究
Topic11	二甲双胍疗效研究	Topic32	药物服用方法
Topic12	消渴丸（成分含格列本脲）治疗风险	Topic33	二甲双胍与癌细胞关联研究
Topic13	DPP4抑制剂降糖效果	Topic34	磺脲类药物致胃肠道反应及肝功能损害副作用
Topic14	降糖药疗效比对研究	Topic35	阿卡波糖与药物间相互作用研究
Topic15	生活方式干预治疗效果	Topic36	卒中保护效应研究
Topic16	二甲双胍与多囊卵巢综合征间关系研究	Topic37	格列本脲适宜用药人群研究
Topic17	二甲双胍无效时,可引入磺脲类药物	Topic38	二甲双胍格列齐特片疗效研究
Topic18	阿卡波糖临床治疗效果	Topic39	饮食疗法
Topic19	SGLT-2抑制剂类有肾脏保护作用	Topic40	糖尿病前期人群预防方法
Topic20	胰岛素治疗致不良心血管事件发生率升高	Topic41	二甲双胍新适应症
Topic21	西格列汀安全性研究	Topic42	低血糖与降糖药关系研究

Table 3 糖尿病药物主题

Fig.4 糖尿病药物文档-主题概率累计图

Table 4 糖尿病药物主题词对共现强度（部分）

Fig.5 糖尿病药物不含权主题共现网络

Fig.6 糖尿病药物含权主题共现网络

Table 5 各指标含权和不含权算法AUC均值

Table 6 糖尿病药物主题关联组合及Katz指标与相似值

[1]	Breault J L, Goodall C R, Fos P J. Data Mining a Diabetic Data Warehouse[J]. Artificial Intelligence in Medicine, 2002, 26(1-2): 37-54. pmid: 12234716
[2]	Koh H C, Tan G. Data Mining Application in Healthcare[J]. Journal of Healthcare Information Management, 2005, 19(2): 64-72.
[3]	Fetro C, Scherman D. Drug Repurposing in Rare Diseases: Myths and Reality[J]. Therapies, 2020, 75(2): 157-160. doi: 10.1016/j.therap.2020.02.006
[4]	郭洪涛, 郑光, 张志华, 等. 基于文本挖掘探索六味地黄丸临床适应症[J]. 世界科学技术-中医药现代化, 2013, 15(3): 535-538.
[4]	(Guo Hongtao, Zheng Guang, Zhang Zhihua, et al. Exploring Clinical Indications of Liuwei-Dihuang Pill Through Text Mining[J]. World Science and Technology-Modernization of Traditional Chinese Medicine, 2013, 15(3): 535-538.)
[5]	丁雯, 张雪芳, 陈雯, 等. 高血压病人认知功能与血压变异性关系的Meta分析[J]. 中西医结合心脑血管病杂志, 2021, 19(3): 389-395.
[5]	(Ding Wen, Zhang Xuefang, Chen Wen, et al. The Relationship Between Cognitive Function and Blood Pressure Variability in Patients with Hypertension: A Meta-Analysis[J]. Chinese Journal of Integrative Medicine on Cardio/Cerebrovascular Disease, 2021, 19(3): 389-395.)
[6]	Kim M, Baek I, Song M. Topic Diffusion Analysis of a Weighted Citation Network in Biomedical Literature[J]. Journal of the Association for Information Science & Technology, 2018, 69(2): 329-342.
[7]	Gopalakrishnan V, Jha K, Jin W, et al. A Survey on Literature Based Discovery Approaches in Biomedical Domain[J]. Journal of Biomedical Informatics, 2019, 93: 103141. doi: S1532-0464(19)30059-0 pmid: 30857950
[8]	Blei D M, Ng A Y, Jordan M I, et al. Latent Dirichlet Allocation[J]. Journal of Machine Learning Research, 2003, 3: 993-1022.
[9]	张涛, 马海群. 一种基于LDA主题模型的政策文本聚类方法研究[J]. 数据分析与知识发现, 2018, 2(9): 59-65.
[9]	(Zhang Tao, Ma Haiqun. Clustering Policy Texts Based on LDA Topic Model[J]. Data Analysis and Knowledge Discovery, 2018, 2(9): 59-65.)
[10]	岳丽欣, 周晓英, 陈旖旎. 期刊论文核心研究主题识别及其演化路径可视化方法研究: 以我国医疗健康信息领域期刊论文为例[J]. 图书情报工作, 2020, 64(5): 89-99.
[10]	(Yue Lixin, Zhou Xiaoying, Chen Yini. Research on Topic Identification of Papers Core Research Subjects and Evolution Path Visualization Method: Taking China’s Journal of Medical and Health Information as an Example[J]. Library and Information Service, 2020, 64(5): 89-99.)
[11]	周靖, 佘玉轩, 熊赟. MaLDA:基于LDA的用药分析[J]. 计算机工程与应用, 2016, 52(18): 8-13.
[11]	(Zhou Jing, She Yuxuan, Xiong Yun. MaLDA:Medication Analysis Based on LDA[J]. Computer Engineering and Applications, 2016, 52(18): 8-13.)
[12]	高慧颖, 刘嘉唯, 杨淑昕. 基于改进LDA的在线医疗评论主题挖掘[J]. 北京理工大学学报, 2019, 39(4): 427-434.
[12]	(Gao Huiying, Liu Jiawei, Yang Shuxin. Identifying Topics of Online Healthcare Reviews Based on Improved LDA[J]. Transactions of Beijing Institute of Technology, 2019, 39(4): 427-434.)
[13]	Cannistraci C V, Alanis-Lobato G, Ravasi T. From Link-Prediction in Brain Connectomes and Protein Interactomes to the Local-Community-Paradigm in Complex Networks[J]. Scientific Reports, 2013, 3: 1613. doi: 10.1038/srep01613 pmid: 23563395
[14]	Shibata N, Kajikawa Y, Sakata I. Link Prediction in Citation Networks[J]. Journal of the American Society for Information Science and Technology, 2012, 63(1): 78-85. doi: 10.1002/asi.v63.1
[15]	Kossinets G. Effects of Missing Data in Social Networks[J]. Social Networks, 2006, 28(3): 247-268. doi: 10.1016/j.socnet.2005.07.002
[16]	Wang W, Lv H, Zhao Y, et al. DLS: A Link Prediction Method Based on Network Local Structure for Predicting Drug-Protein Interactions[J]. Frontiers in Bioengineering and Biotechnology, 2020, 8: 330. doi: 10.3389/fbioe.2020.00330 pmid: 32391341
[17]	Kaya B, Poyraz M. Finding Relations Between Diseases by Age-Series Based Supervised Link Prediction [C]//Proceedings of the 2015 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining. 2015: 1097-1103.
[18]	安莹, 王志娜, 陈先来, 等. 带权疾病网络上的潜在共病关系预测[J]. 湖南大学学报(自然科学版), 2019, 46(12): 33-40.
[18]	(An Ying, Wang Zhina, Chen Xianlai, et al. Prediction of Latent Comorbidity Relationship in Weighted Disease Network[J]. Journal of Hunan University (Natural Sciences), 2019, 46(12): 33-40.)
[19]	Granovetter M S. The Strength of Weak Ties[J]. American Journal of Sociology, 1973, 78(6): 1360-1380. doi: 10.1086/225469
[20]	Adamic L A, Adar E. Friends and Neighbors on the Web[J]. Social Networks, 2003, 25(3): 211-230. doi: 10.1016/S0378-8733(03)00009-1
[21]	Zhou T, Lv L, Zhang Y C. Predicting Missing Links via Local Information[J]. The European Physical Journal B, 2009, 71(4): 623-630. doi: 10.1140/epjb/e2009-00335-8
[22]	Barabási A L, Albert R. Emergence of Scaling in Random Networks[J]. Science, 1999, 286(5439): 509-512. doi: 10.1126/science.286.5439.509
[23]	Murata T, Moriyasu S. Link Prediction of Social Networks Based on Weighted Proximity Measures [C]//Proceedings of the IEEE/WIC/ACM International Conference on Web Intelligence. 2007: 85-88.
[24]	陈嘉颖, 于炯, 杨兴耀, 等. 基于复杂网络节点重要性的链路预测算法[J]. 计算机应用, 2016, 36(12): 3251-3255, 3268.
[24]	(Chen Jiaying, Yu Jiong, Yang Xingyao, et al. Link Prediction Algorithm Based on Node Importance in Complex Networks[J]. Journal of Computer Applications, 2016, 36(12): 3251-3255, 3268.)
[25]	Lorrain F, White H C. Structural Equivalence of Individuals in Social Networks[J]. The Journal of Mathematical Sociology, 1971, 1(1): 49-80. doi: 10.1080/0022250X.1971.9989788
[26]	Salton G, McGill M J. Introduction to Modern Information Retrieval[M]. Auckland: MuGraw-Hill, 1983.
[27]	岳增慧, 许海云, 王倩飞. 基于局部信息相似性的学科引证知识扩散动态链路预测研究[J]. 情报理论与实践, 2020, 43(2): 84-91, 99.
[27]	(Yue Zenghui, Xu Haiyun, Wang Qianfei. Dynamic Link Prediction of Knowledge Diffusion in Disciplinary Citation Networks Based on Local Information[J]. Information Studies: Theory & Application, 2020, 43(2): 84-91, 99.)
[28]	Jaccard P. Etude Comparative de la Distribution Florale dans une Portion des Alpes et des Jura[J]. Bulletin de la Société Vaudoise des Sciences Naturelles, 1901, 37: 547-579.
[29]	Sørensen T. A Method of Establishing Groups of Equal Amplitude in Plant Sociology Based on Similarity of Species and Its Application to Analyses of the Vegetation on Danish Commons[J]. Biologiske Skrifter/Kongelige Danske Videnskabernes Selskab, 1948, 5: 1-34.
[30]	Ravasz E, Somera A L, Mongru D A, et al. Hierarchical Organization of Modularity in Metabolic Networks[J]. Science, 2002, 297(5586): 1551-1555. pmid: 12202830
[31]	Leicht E A, Holme P Newman M E. Vertex Similarity in Networks[J]. Physical Review E, Statistical, Nonlinear & Soft Matter Physics, 2006, 73(2): Article No. 026120.
[32]	Bai M, Hu K, Tang Y. Link Prediction Based on a Semi-Local Similarity Index[J]. Chinese Physics B, 2011, 20(12): 128902. doi: 10.1088/1674-1056/20/12/128902
[33]	Hanley J A, McNeil B J. The Meaning and Use of the Area under a Receiver Operating Characteristic (ROC) Curve[J]. Radiology, 1982, 143(1): 29-36. pmid: 7063747
[34]	Chakraborty D P, Zhai X T. On the Meaning of the Weighted Alternative Free-Response Operating Characteristic Figure of Merit[J]. Medical Physics, 2016, 43(5): 2548-2557. doi: 10.1118/1.4947125 pmid: 27147365
[35]	中华医学会糖尿病学分会. 中国2型糖尿病防治指南(2017年版)[J]. 中国实用内科杂志, 2018, 38(4): 292-344.
[35]	(The Chinese Medical Association Diabetes Credit Association. Guidelines for the Prevention and Control of Type 2 Diabetes in CHINA (2017 Edition)[J]. Chinese Journal of Practical Internal Medicine, 2018, 38(4): 292-344.)
[36]	盛津芳, 刘家广, 王斌. 基于Katz自动编码器的城市路网链路预测模型[J]. 计算机工程与应用, 2019, 55(8): 116-123, 131.
[36]	(Sheng Jinfang, Liu Jiaguang, Wang Bin. Katz Auto Encoder for Urban Road Network Link Prediction Model[J]. Computer Engineering and Applications, 2019, 55(8): 116-123, 131.)
[37]	杨金庆, 魏雨晗, 黄圣智, 等. 基于科技文献的新兴主题识别研究综述[J]. 情报科学, 2020, 38(8): 159-163, 177.
[37]	(Yang Jinqing, Wei Yuxuan, Huang Shengzhi, et al. Research Review on Emerging Topic Identification Based on Scientific Literatures[J]. Infornation Science, 2020, 38(8): 159-163, 177.)
[38]	杜俊杰, 杨继红. 2型糖尿病的治疗新进展[J]. 中国临床保健杂志, 2020, 23(3): 302-306.
[38]	(Du Junjie, Yang Jihong. New Progress in the Treatment of Type 2 Diabetes[J]. Chinese Journal of Clinical Healthcare, 2020, 23(3): 302-306.)
[39]	娄霁月. 我国生物医药行业现状与发展趋势[J]. 大众标准化, 2019(16): 61, 63.
[39]	(Lou Jiyue. The Current Situation and Development of China's Biopharmaceutical Industry is Becoming[J]. Popular Standardization, 2019(16): 61, 63.)
[40]	国家卫生健康委员会药物政策与基本药物制度司. 巩固完善基本药物制度满足人民群众基本用药需求[J]. 中国卫生资源, 2020, 23(6): 525-526, 532.
[40]	(Department of Drug Policy and Essential Medicines System of the National Health Commission. To Consolidate and Improve the Basic Drug System to Meet the Basic Drug Needs of the People[J]. Chinese Health Resources, 2020, 23(6): 525-526, 532.)
[41]	DiMasi J A, Grabowski H G, Hansen R W. Innovation in the Pharmaceutical Industry: New Estimates of R&D Costs[J]. Journal of Health Economics, 2016, 47: 20-33. doi: 10.1016/j.jhealeco.2016.01.012
[42]	燕星. 二甲双胍联合化疗对肺癌合并糖尿病患者的临床疗效[J]. 慢性病学杂志, 2021, 22(2): 241-243.
[42]	(Yan Xing. Clinical Efficacy of Metformin Combination Chemotherapy in Patients with Combined Lung Cancer Diabetes[J]. Chronic Pathematology Journal, 2021, 22(2): 241-243.)
[43]	徐春花, 何卓俊, 曾立, 等. 肥胖的发病机制以及药物治疗研究概况[J]. 中国疗养医学, 2021, 30(2): 131-135.
[43]	(Xu Chunhua, He Zhuojun, Zeng Li, et al. Research Overview of the Pathogenesis of Obesity and Drug Therapy[J]. Chinese Journal of Convalescent Medicine, 2021, 30(2): 131-135.)
[44]	李美花, 张素娟. 二甲双胍治疗奥氮平致精神分裂症患者代谢综合征的疗效观察[J]. 中国现代医学杂志, 2021, 31(2): 82-86.
[44]	(Li Meihua, Zhang Sujuan. Efficacy of Metformin in Metabolic Syndrome Induced by Olanzapine in Schizophrenia Patients[J]. China Journal of Modern Medicine, 2021, 31(2): 82-86.)
[45]	Xu S, Ilyas I, Little P J, et al. Endothelial Dysfunction in Atherosclerotic Cardiovascular Diseases and Beyond: From Mechanism to Pharmacotherapies[J]. Pharmacological Reviews, 2021, 73(3): 924-967. doi: 10.1124/pharmrev.120.000096
[46]	Li R, Zeng X, Yang M, et al. Antidiabetic Agent DPP-4i Facilitates Murine Breast Cancer Metastasis by Oncogenic ROS-NRF2-HO-1 Axis via a Positive NRF2-HO-1 Feedback Loop[J]. Frontiers in Oncology, 2021, 11: 679816. doi: 10.3389/fonc.2021.679816
[47]	方合志, 沈丽君, 吴旭聪, 等. 二甲双胍靶向COX6B2在制备治疗胰腺癌药物中的应用: 中国, CN111419831A[P]. 2020-07-17.
[47]	(Fang Hezhi, Shen Lijun, Wu Xucong, et al. Metformin Targets COX6B2 in the Preparation of Drugs for the Treatment of Pancreatic Cancer: China, CN111419831A[P]. 2020-07-17.)

[1]	单晓红,王春稳,刘晓燕,韩晟熙,杨娟. 开放式创新社区领先用户识别——知识基础观视角*[J]. 数据分析与知识发现, 2021, 5(9): 85-96.
[2]	李跃艳,王昊,邓三鸿,王伟. 近十年信息检索领域的研究热点与演化趋势研究——基于SIGIR会议论文的分析[J]. 数据分析与知识发现, 2021, 5(4): 13-24.
[3]	代冰,胡正银. 基于文献的知识发现新近研究综述 ^*[J]. 数据分析与知识发现, 2021, 5(4): 1-12.
[4]	伊惠芳,刘细文. 一种专利技术主题分析的IPC语境增强Context-LDA模型研究[J]. 数据分析与知识发现, 2021, 5(4): 25-36.
[5]	韩芳, 张生太, 冯凌子, 袁军鹏. *基于专利文献技术融合测度的突破性创新主题识别——以太阳能光伏领域为例**[J]. 数据分析与知识发现, 2021, 5(12): 137-147.
[6]	吴胜男, 蒲虹君, 田若楠, 梁雯琪, 于琦. *网络结构对链路预测算法的影响研究——基于元分析视角**[J]. 数据分析与知识发现, 2021, 5(11): 102-113.
[7]	王伟, 高宁, 徐玉婷, 王洪伟. 基于LDA的众筹项目在线评论主题动态演化分析^*[J]. 数据分析与知识发现, 2021, 5(10): 103-123.
[8]	蔡永明,刘璐,王科唯. 网络虚拟学习社区重要用户与核心主题联合分析*[J]. 数据分析与知识发现, 2020, 4(6): 69-79.
[9]	叶光辉,曾杰妍,胡婧岚,毕崇武. 城市画像视角下的社会公众情感演化研究*[J]. 数据分析与知识发现, 2020, 4(4): 15-26.
[10]	潘有能,倪秀丽. 基于Labeled-LDA模型的在线医疗专家推荐研究*[J]. 数据分析与知识发现, 2020, 4(4): 34-43.
[11]	刘玉文,王凯. 面向地域的网络话题识别方法^*[J]. 数据分析与知识发现, 2020, 4(2/3): 173-181.
[12]	黄微,赵江元,闫璐. 网络热点事件话题漂移指数构建与实证研究*[J]. 数据分析与知识发现, 2020, 4(11): 92-101.
[13]	胡正银,刘蕾蕾,代冰,覃筱楚. 基于领域知识图谱的生命医学学科知识发现探析*[J]. 数据分析与知识发现, 2020, 4(11): 1-14.
[14]	叶光辉,徐彤,毕崇武,李心悦. 基于多维度特征与LDA模型的城市旅游画像演化分析*[J]. 数据分析与知识发现, 2020, 4(11): 121-130.
[15]	王晰巍,张柳,黄博,韦雅楠. *基于LDA的微博用户主题图谱构建及实证研究^——以“埃航空难”为例**[J]. 数据分析与知识发现, 2020, 4(10): 47-57.

Viewed

Full text

Abstract

Cited

Shared

Discussed