Please wait a minute...
Data Analysis and Knowledge Discovery  2018, Vol. 2 Issue (7): 34-45    DOI: 10.11925/infotech.2096-3467.2018.0075
Current Issue | Archive | Adv Search |
Evolution and Regional Differences of E-commerce Policies for Rural Poverty Reduction Based on Topic over Time Model
Yu Chuanming1(), Guo Yajing1, Gong Yutian1, Huang Manyu2, Peng Hufeng1
1School of Information and Safety Engineering, Zhongnan University of Economics and Law, Wuhan 430073, China
2School of Business Administration, Zhongnan University of Economics and Law, Wuhan 430073, China
Download: PDF (1125 KB)   HTML ( 5
Export: BibTeX | EndNote (RIS)      
Abstract  

[Objective] This paper reveals the evolution and regional differences of E-commerce policies for rural poverty reduction from 2008 to 2017. [Methods] First, we used the ToT (Topic over Time) model to investigate the probability distributions of time-topics and topics-words related to E-commerce policies for rural poverty reduction. Then, we analyzed the evolution of the policy contents by calculating the average intensity of topics in each year and extracted the top n topic words with the highest probabilities. Third, we divided the data from each province into the eastern, central and western regions, and then analyzed the regional differences of policies according to the probability distribution of topics and words. [Results] E-commerce policies for rural poverty reduction had the starting, exploring and developing stages. The eastern, central and western regions have different focuses on logistics, platforms and personnel training. [Limitations] The regional differences of E-commerce policies need more fine-grained analysis. [Conclusions] Compared with the traditional word frequency counting method, the ToT model effectively reveals the policy evolution and their regional differences.

Key wordsTopic over Time Model      E-commerce Policy for Rural Poverty Reduction      Regional Difference Analysis      Policy Evolution     
Received: 22 January 2018      Published: 15 August 2018
ZTFLH:  TP391  

Cite this article:

Yu Chuanming,Guo Yajing,Gong Yutian,Huang Manyu,Peng Hufeng. Evolution and Regional Differences of E-commerce Policies for Rural Poverty Reduction Based on Topic over Time Model. Data Analysis and Knowledge Discovery, 2018, 2(7): 34-45.

URL:

https://manu44.magtech.com.cn/Jwk_infotech_wk3/EN/10.11925/infotech.2096-3467.2018.0075     OR     https://manu44.magtech.com.cn/Jwk_infotech_wk3/EN/Y2018/V2/I7/34

符号 描述
K 电商扶贫政策主题的数量
M 电商扶贫相关文档的数量
V 电商扶贫词项的数量
Nm 文档m中单词的数量
${{\vec{\vartheta }}_{m}}$ 文档m上的主题多项分布, Θ=$\{{{\vec{\vartheta }}_{m}}\}_{m=1}^{M}$(M×Kmatrix)
${{\vec{\varphi }}_{k}}$ 主题k上的词项多项分布, Φ=$\{{{\vec{\varphi }}_{k}}\}_{k=1}^{K}$(K×Vmatrix)
${{\vec{\psi }}_{k}}$ 主题k随时间变化的贝塔分布, Ψ=$\{{{\vec{\psi }}_{k}}\}_{k=1}^{K}$(K×2 matrix)
${{z}_{m,n}}$ 文档m中第n个词的主题
${{w}_{m,n}}$ 文档m中的第n个词
${{t}_{m,n}}$ 文档m中第n个词的时间戳
\[\vec{\alpha }\] 文档多项分布${{\vec{\vartheta }}_{m}}$的狄利克雷先验分布, K维向量
$\vec{\beta }$ 主题多项分布${{\vec{\varphi }}_{k}}$的狄利克雷先验分布, V维向量
省、直
辖市
文本
数量
省、直
辖市
文本
数量
省、直
辖市
文本
数量
北京 68 新疆 213 浙江 389
青海 100 江西 258 江苏 396
辽宁 103 吉林 297 安徽 415
广西 104 海南 303 山西 419
西藏 115 湖南 307 贵州 443
天津 136 甘肃 325 陕西 455
内蒙古 148 广东 325 四川 469
上海 169 河北 331 山东 534
宁夏 183 云南 337 重庆 566
福建 184 黑龙江 354
湖北 201 河南 359
第一类 第二类 第三类 第四类
topic9 topic8 topic15 topic11
自考网0.0309 农产品0.0106 企业0.0162 推进0.0275
专业0.0309 发展0.0077 建设0.0144 物流0.0266
考试0.0154 销售0.0059 服务0.0121 发展0.024
企业0.0132 农民0.0057 农产品0.0118 信息0.0168
技术0.0121 平台0.0054 农业0.0111 流通0.0097
发展0.011 模式0.0051 农民0.0067 示范0.0096
服务0.011 物流0.005 实现0.0063 网上0.0086
市场0.011 企业0.0047 工作0.006 特色0.0075
专科0.0099 市场0.0047 支持0.0058 经营0.0074
物流0.0099 通过0.0045 产业0.0052 关于0.0066
产品0.0099 问题0.0042 加快0.0051 品牌0.0064
平台0.0099 表0.0041 淘宝0.005 京东0.0062
区域 主题 词项
东部 topic2
0.27
企业0.0139创业0.0122服务0.0118物流0.0099推进0.0079政策0.0073工作0.0066重点0.005加强0.0049
topic5
0.19
跨境0.0106培训0.01销售0.0098合作0.0071全国0.0067大0.0064体系0.0063京东0.0063扶贫0.0062
topic4
0.18
发展0.023互联网0.0202淘宝0.0138网络0.0116开展0.01通过0.0079政府0.0075推动0.0074建设0.0073
中部 topic10
0.52
发展0.017企业0.0131建设0.0094服务0.0081平台0.0079物流0.0067互联网0.0043市场0.0043工作0.0042
topic1
0.12
创业0.0157产业园0.008发展0.0076中心0.0075农产品0.0074培训0.0062服务中心0.0058脱贫0.0057创新0.005
topic6
0.09
发展0.0079农产品0.007建设0.0067苏宁0.0058统筹0.0049安徽0.0046带动0.0041贫困村0.004县域0.0037
西部 topic6
0.52
发展0.0215企业0.0109农产品0.0092服务0.0076平台0.0076物流0.0054创业0.0051互联网0.0051销售0.0051
topic9
0.2
项目0.0082公司0.008贵州0.0072培训0.0067新疆0.0063四川0.0062建设0.0061精准0.006网店0.0048
topic7
0.09
记者0.0154培育0.0146脱贫0.0064省级0.0063贫困村0.0056青年0.0047安全0.0045乡村0.0044龙头企业0.0042
全国 中部 湖北
topic5 topic10 topic1 topic10 topic3 topic10
发展0.0139 专业0.0135 创业0.0157 发展0.017 发展0.0149 创业0.0519
企业0.0095 技术0.0124 产业园0.008 企业0.0131 农产品0.0094 妇女0.0188
农产品0.0084 项目0.0114 发展0.0076 建设0.0094 企业0.0091 创新0.0137
建设0.0072 公司0.0104 中心0.0075 服务0.0081 平台0.0069 服务0.0098
平台0.0064 企业0.0093 农产品0.0074 平台0.0079 京东0.0052 青年0.0075
网络0.0052 互联网0.0093 培训0.0062 农产品0.0073 湖北0.0047 巾帼0.0069
物流0.005 青年0.0093 服务中心0.0058 物流0.0067 产业0.0043 家政0.0066
服务0.0049 市场0.0083 脱贫0.0057 农业0.0062 市场0.0043 妇联0.0059
市场0.0047 大赛0.0083 创新0.005 互联网0.0043 销售0.0039 项目0.0058
模式0.0038 信息0.0072 精准0.0048 市场0.0043 十堰0.0037 手工0.0058
[1] 杨永超. 供给侧改革背景下我国农村电商创新发展路径[J]. 经济研究参考, 2017(18): 35-36.
[1] (Yang Yongchao.Innovative Development of Rural E-commerce in China under the Background of Supply-side Reform[J]. Review of Economic Research, 2017(18): 35-36. )
[2] 吕岩威, 刘洋. 推动农村一二三产业融合发展的路径探究[J]. 当代经济管理, 2017, 39(10): 38-43.
[2] (Lv Yanwei, Liu Yang.Research on the Path of Promoting the Convergence and Development of Rural Primary, Secondary and Tertiary Industry[J]. Contemporary Economic Management, 2017, 39(10): 38-43.)
[3] 鲁钊阳. 新型农业经营主体发展的福利效应研究[J]. 数量经济技术经济研究, 2016, 33(6): 41-58.
[3] (Lu Zhaoyang.The Welfare Effects from the Development of the New Agricultural Management Entities[J]. The Journal of Quantitative & Technical Economics, 2016, 33(6): 41-58.)
[4] 刘亚军. 互联网条件下的自发式包容性增长——基于一个“淘宝村”的纵向案例研究[J]. 社会科学, 2017(10): 46-60.
[4] (Liu Yajun.The Spontaneous Inclusive Growth under the Circumstance of Internet: A Longitudinal Case Study of “Taobao Village”[J]. Journal of Social Sciences, 2017(10): 46-60.)
[5] 成晨, 丁冬. “互联网+农业电子商务”: 现代农业信息化的发展路径[J]. 情报科学, 2016, 34(11): 49-52, 59.
[5] (Cheng Chen, Ding Dong.“Internet+Agricultural E-commerce”: Development Path of Modern Agricultural Informatization[J]. Information Science, 2016, 34(11): 49-52, 59.)
[6] 刘亚军, 储新民. 中国“淘宝村”的产业演化研究[J]. 中国软科学, 2017(2): 29-36.
doi: 10.3969/j.issn.1002-9753.2017.02.004
[6] (Liu Yajun, Chu Xinmin.The Industrial Evolution of TAOBAO Villages[J]. China Soft Science, 2017(2): 29-36.)
doi: 10.3969/j.issn.1002-9753.2017.02.004
[7] 王慧敏, 王欣, 李民. 互联网+三农, 探索农村电商新模式——以巢湖汤山电商村三瓜公社为例[J]. 农村经济与科技, 2017, 28(6): 75-76, 105.
[7] (Wang Huimin, Wang Xin, Li Min.Internet + Agricultural, Exploring a New Mode of Rural E-commerce —— A Case Study of Sangua Commune[J]. Rural Economy and Science-Technology, 2017, 28(6): 75-76, 105.)
[8] Feldman R.Text Mining[M]. Oxford University Press, 2002: 749-757.
[9] Gabrilovich E, Markovitch S.Wikipedia-based Semantic Interpretation for Natural Language Processing[J]. Journal of Artificial Intelligence Research, 2009, 34(4): 443-498.
doi: 10.1613/jair.2669
[10] Booth D E.Data Mining Methods and Models[J]. Technometrics, 2007, 49(4): 500.
doi: 10.1198/tech.2007.s697
[11] 吴恒, 陈燕翎. 基于UGC文本挖掘的游客目的地选择信息研究——以携程蜜月游记为例[J]. 情报科学, 2017, 35(1): 101-105.
[11] (Wu Heng, Chen Yanling.Study on Information of Tourists’ Destination Selections Based on UGC and Text Mining——Taking Honeymoon Travel Notes from Ctrip as an Example[J]. Information Science, 2017, 35(1): 101-105.)
[12] 徐映梅, 高一铭. 基于互联网大数据的CPI舆情指数构建与应用——以百度指数为例[J]. 数量经济技术经济研究, 2017(1): 94-112.
[12] (Xu Yingmei, Gao Yiming.Construction of the Public Opinion Index of CPI Based on the Internet Big Data[J]. The Journal of Quantitative & Technical Economics, 2017(1): 94-112.)
[13] 孟雪井, 孟祥兰, 胡杨洋. 基于文本挖掘和百度指数的投资者情绪指数研究[J]. 宏观经济研究, 2016(1): 144-153.
[13] (Meng Xuejing, Meng Xianglan, Hu Yangyang.Research on Investor Sentiment Index Based on Text Mining and Baidu Index[J]. Macroeconomics, 2016(1): 144-153.)
[14] 孟雪井, 杨亚飞, 赵新泉. 财经新闻与股市投资策略研究——基于财经网站的文本挖掘[J]. 投资研究, 2016(8): 29-37.
[14] (Meng Xuejing, Yang Yafei, Zhao Xinquan.The Research on Financial News and Stock Market Investment Strategy[J]. Investment Research, 2016(8): 29-37.)
[15] 吴联仁, 李瑾颉, 齐佳音. 基于大规模文本数据情感挖掘的企业舆情研究[J]. 知识管理论坛, 2016(6): 457-463.
[15] (Wu Lianren, Li Jinjie, Qi Jiayin.Research on Enterprise Public Opinions Based on Large-scale Text Data Sentiment Mining[J]. Knowledge Management Forum, 2016(6): 457-463.)
[16] Setiawan J.Using Text Mining to Analyze Mobile Phone Provider Service Quality (Case Study: Social Media Twitter)[J]. International Journal of Machine Learning & Computing, 2014, 4(1): 106-109.
[17] Blei D M, Lafferty J D.Dynamic Topic Models[C]// Proceedings of the 23rd International Conference on Machine Learning. 2006: 113-120.
[18] Wang X, McCallum A. Topics over Time: A Non-Markov Continuous-Time Model of Topical Trends[C]// Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. ACM, 2006: 424-433.
[19] 史庆伟, 李艳妮, 郭朋亮. 科技文献中作者研究兴趣动态发现[J]. 计算机应用, 2013, 33(11): 3080-3083.
doi: 10.11772/j.issn.1001-9081.2013.11.3080
[19] (Shi Qingwei, Li Yanni, Guo Pengliang.Dynamic Finding of Authors’ Research Interests in Scientific Literature[J]. Journal of Computer Applications, 2013, 33(11): 3080-3083.)
doi: 10.11772/j.issn.1001-9081.2013.11.3080
[20] 范逢春. 建国以来基本公共服务均等化政策的回顾与反思:基于文本分析的视角[J]. 上海行政学院学报, 2016, 17(1): 46-57.
[20] (Fan Fengchun.A Retrospection and Reflection on the Equalization of Basic Public Services Since the Founding of PRC: A Discourse Analysis Approach[J]. The Journal of Shanghai Administration Institute, 2016, 17(1): 46-57.)
[21] 张国兴, 高秀林, 汪应洛, 等. 中国节能减排政策的测量、协同与演变——基于1978-2013年政策数据的研究[J]. 中国人口·资源与环境, 2014, 24(12): 62-73.
[21] (Zhang Guoxing, Gao Xiulin, Wang Yingluo, et al.Measurement, Coordination and Evolution of Energy Conservation and Emission Reduction Policies in China: Based on the Research of the Policy Data from 1978 to 2013[J]. China Polulation, Resources and Environment, 2014, 24(12): 62-73.)
[22] 张永宁, 李辉, 丛男, 等. “情境-表达-结局”框架下中国减排政策变迁与反思——以“五年规划”为线索的文本挖掘[J]. 科技进步与对策, 2016, 33(20): 109-114.
doi: 10.6049/kjjbydc.2016040445
[22] (Zhang Yongning, Li Hui, Cong Nan, et al.The Evolution and Reflection of China’s Reduction Policies under the Framework of Context-Expression-Result[J]. Science & Technology Progress and Policy, 2016, 33(20): 109-114.)
doi: 10.6049/kjjbydc.2016040445
[23] 张永安, 闫瑾. 基于文本挖掘的科技成果转化政策内部结构关系与宏观布局研究[J]. 情报杂志, 2016, 35(2): 44-49.
doi: 10.3969/j.issn.1002-1965.2016.02.009
[23] (Zhang Yong’an, Yan Jin.Research on the Internal Structural Relation and Macro Layout of Scientific and Technological Achievements Transformation Policies Based on Text Mining[J]. Journal of Intelligence. 2016, 35(2): 44-49.)
doi: 10.3969/j.issn.1002-1965.2016.02.009
[24] 王印红, 李萌竹. 地方政府生态环境治理注意力研究——基于30个省市政府工作报告(2006—2015)文本分析[J]. 中国人口·资源与环境, 2017, 27(2): 28-35.
doi: 10.3969/j.issn.1002-2104.2017.02.006
[24] (Wang Yinhong, Li Mengzhu.Study on Local Government Attention of Ecological Environment Governance: Based on theText Analysis of Government Work Report in 30 Provinces and Cities (2006—2015)[J]. China Polulation, Resources and Environment, 2017, 27(2): 28-35.)
doi: 10.3969/j.issn.1002-2104.2017.02.006
[25] 李华姣, 张晗江, 刘乃榕, 等. 我国资源环境承载力的时空分布特征及研究热点——基于在线新闻文本分析[J]. 资源与产业, 2016, 18(6): 27-32.
doi: 10.13776/j.cnki.resourcesindustries.20161223.008
[25] (Li Huajiao, Zhang Hanjiang, Liu Nairong, et al.Temporal-Spatial Distribution Research Hot Topics of China’s Resources and Environment Carrying Capacity Based on On-Line News Reports[J]. Resources & Industries, 2016, 18(6): 27-32.)
doi: 10.13776/j.cnki.resourcesindustries.20161223.008
[26] 邵浩. 贸易文本的主题挖掘研究[J]. 计算机工程与应用, 2016, 52(11): 60-67.
doi: 10.3778/j.issn.1002-8331.1508-0205
[26] (Shao Hao.Topic Mining in Trade Policy Review[J]. Computer Engineering and Applications, 2016, 52(11): 60-67.)
doi: 10.3778/j.issn.1002-8331.1508-0205
[27] 张永安, 马昱. 基于R语言的区域技术创新政策量化分析[J]. 情报杂志, 2017, 36(3): 113-118.
doi: 10.3969/j.issn.1002-1965.2017.03.020
[27] (Zhang Yong’an, Ma Yu.Quantitative Analysis of Regional Technological Innovation Policies with R Language[J]. Journal of Intelligence, 2017, 36(3): 113-118.)
doi: 10.3969/j.issn.1002-1965.2017.03.020
[28] Python: An Interpreted High-level Programming Language for General-purpose Programming[EB/OL]. [2017-10-11].https://www.python.org/doc/.
[29] 单斌, 李芳. 基于LDA话题演化研究方法综述[J]. 中文信息学报, 2010, 24(6): 43-49.
doi: 10.3969/j.issn.1003-0077.2010.06.007
[29] (Shan Bin, Li Fang.A Survey of Topic Evolution Based on LDA[J]. Journal of Chinese Information Processing, 2010, 24(6): 43-49.)
doi: 10.3969/j.issn.1003-0077.2010.06.007
[30] Blei D M.Latent Dirichlet Allocation[J]. Journal of Machine Learning Research, 2003, 3: 993-1022.
[1] Jianhua Liu,Zhixiong Zhang,Qin Zhang. Revealing Sci-Tech Policy Evolution with Entity Relationship[J]. 数据分析与知识发现, 2019, 3(5): 57-67.
  Copyright © 2016 Data Analysis and Knowledge Discovery   Tel/Fax:(010)82626611-6626,82624938   E-mail:jishu@mail.las.ac.cn