Application of Topic Models in the Analysis of Public Policy: A Review of the Research Status in Domestic and Foreign

Long Yixuan, Yi Huifang

Knowledge Management Forum ›› 2020, Vol. 5 ›› Issue (5) : 305-316.

PDF(2592 KB)
PDF(2592 KB)
Knowledge Management Forum ›› 2020, Vol. 5 ›› Issue (5) : 305-316. DOI: 10.13266/j.issn.2095-5472.2020.029

Application of Topic Models in the Analysis of Public Policy: A Review of the Research Status in Domestic and Foreign

Author information +
History +

Abstract

[Purpose/significance] This paper comprehensively summarizes the application of topic models in public policy texts, which helps researchers learn from existing research results and provides theoretical and practical support for future development. [Method/process] This paper used bibliometric analysis to study from the perspectives of time trend, organization distribution, periodical distribution, etc., and summarized the application status in detail. Secondly, the LDA topic model was used to identify the main international and domestic research directions and conducted a comparative analysis. Finally, this paper summarized the problems in the application and proposed future prospects. [Result/conclusion] The application of topic models in the analysis of public policy texts is on the rise overall and has broad prospects. The starting time of domestic and foreign research is equivalent, but domestic research needs to be improved in terms of research scope, research depth, cooperation methods, and research methods. In addition, in the future development, there are problems with the applicability of the topic model's own methods and the granularity of research content. It is necessary to further combine the characteristics of public policy texts to improve the topic model and refine research efforts.

Key words

topic model / pubic policy / text analysis / LDA

Cite this article

Download Citations
Long Yixuan , Yi Huifang. Application of Topic Models in the Analysis of Public Policy: A Review of the Research Status in Domestic and Foreign[J]. Knowledge Management Forum. 2020, 5(5): 305-316 https://doi.org/10.13266/j.issn.2095-5472.2020.029

References

[1]
陈振明. 政策科学——公共政策分析导论[M]. 北京: 中国人民大学出版社,2003: 19.
[2]
苏竣. 公共科技政策导论[M]. 北京: 科学出版社, 2014: 8-9.
[3]
LI J, WANG H J, ZHANG Z, et al. A policy-based process mining framework: mining business policy texts for discovering process models[J]. Information systems and e-business management, 2010, 8(2): 169-188.
[4]
PRIOR L, HUGHES D, PECKHAM S. The discursive turn in policy analysis and the validation of policy stories[J]. Journal of social policy, 2012, 41(2): 271-289.
[5]
LEE J Y, LEE J. A text mining analysis of US-Chinese leaders on trade policy[J]. Journal of international logistics and trade, 2019, 17(3): 67-76.
[6]
MISOOK K. Trends of sports policy through the analysis of big data text-mining: with a focus on the inauguration of the MCST minister[J]. The Korean journal of sport, 2019, 17(2): 519-529.
[7]
杨慧, 杨建林. 融合LDA模型的政策文本量化分析——基于国际气候领域的实证[J]. 现代情报, 2016, 36(5): 71-81.
[8]
HOFMANN T. Probabilistic latent semantic analysis[C]// Fifteenth conference on uncertainty in artificial intelligence. San Francisco: Morgan Kaufmann Publishers Inc, 1999: 289-296.
[9]
LIU L Q, MEI S Y. Visualizing the GVC research: a co-occurrence network based bibliometric analysis[J]. Scientometrics, 2016, 109(2): 1-25.
[10]
DEREK J S P. Networks of scientific papers[J]. Science, 1965, 149(3683): 510-515.
[11]
GARFIELD E. Citation indexes for science: a new dimension in documentation through association of ideas[J]. Science, 1964, 144(3619): 649.
[12]
BLEI D M, NG A Y, JORDAN M I. Latent Dirichlet allocation [J]. The journal of machine learning research, 2003, 3(3): 993-1022.
[13]
BLEI D M, LAFFERTY J D. Dynamic topic models [C]// Proceedings of the 23rd international conference on machine learning. New York: ACM Press, 2006: 113-120.
[14]
ROSEN-ZVI M, GRIFFITHS T, STEYVERS M, et al. The author-topic model for authors and documents[C]// Proceedings of the 20th conference on uncertainty in artificial intelligence. Arlington: AUAI Press, 2004: 487-494.
[15]
ROSEN-ZVI M, CHEMUDUGUNTA C, GRIFITHS T, et al. Learning author-topic models from text corpora[J]. ACM transactions on information systems (TOIS), 2010, 28(1): 4-42.
[16]
曲靖野, 陈震, 郑彦宁. 基于主题模型的科技报告文档聚类方法研究[J]. 图书情报工作, 2008, 62(4): 113-120.
[17]
王丽, 沈湘. 文本预处理后的LDA模型主题发现与技术演进研究[J]. 农业图书情报, 2019, 31(4): 19-28.
[18]
曹树金, 吴育冰, 韦景竹, 等. 知识图谱研究的脉络, 流派与趋势——基于 SSCI与CSSCI期刊论文的计量与可视化[J]. 中国图书馆学报, 2015, 41(5): 16-34.
[19]
余传明, 郭亚静, 龚雨田,等. 基于主题时间模型的农村电商扶贫政策演化及地区差异分析[J]. 数据分析与知识发现, 2018, 19(7): 34-45.
[20]
HAYNES E, GREEN J, GARSIDE R, et al. Gender and active travel: a qualitative data synthesis informed by machine learning[J]. International journal of behavioral nutrition and physical activity, 2019, 16(1): 135-146.
[21]
李少博. 基于主题的科技政策分析系统设计与实现[D]. 石家庄: 石家庄铁道大学, 2016.
[22]
王倩倩. 科技政策领域的个性化语义检索系统研究[D]. 石家庄: 石家庄铁道大学, 2016.
[23]
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, 21(9): 59-64.
[24]
刘雨农, 吴柯烨, 权昭瑄. 人文社科专题数据库建设的主题选择研究[J]. 现代情报, 2019, 39(12): 11-18.
[25]
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.
[26]
郎玫. 大数据视野下中央与地方政府职能演变中的匹配度研究——基于甘肃省14市(州)政策文本主题模型(LDA)[J]. 情报杂志, 2018, 37(9): 78-85.
[27]
MARK A, CHRISTOPHER B, JESSE A. Documents as data: a content analysis and topic modeling approach for analyzing responses to ecological disturbances[J]. Ecological informatics, 2019, 51: 82-95.
[28]
WEN Q, QIANG M, XIA B Q, et al. Discovering regulatory concerns on bridge management: an author-topic model based approach[J]. Transport policy, 2019, 75: 161-170.
[29]
LUCAS C, NIELSEN R A, ROBERTS M E, et al. Computer-assisted text analysis for comparative politics[J]. Political analysis, 2015, 23(2): 254-277.
[30]
RUHL J B, NAY J, GILLIGAN J M. Topic modeling the president: conventional and computational methods[J]. George Washington law review, 2018, 86(5): 1243-1315.
[31]
DU H S, ZHAN B Q, XU J H, et al. The influencing mechanism of multi-factors on green investments: a hybrid analysis[J]. Journal of cleaner production, 2019, 239(1): 1-12.
[32]
CERON A, GREENE Z. Verba volant, scripta manent? Intra-party politics, party conferences, and issue salience in France[J]. Party politics, 2019, 25(5): 701-711.
[33]
HSU A, BRANDT J, WIDERBERG O, et al. Exploring links between national climate strategies and non-state and subnational climate action in nationally determined contributions (NDCs)[J]. Climate policy, 2019, 19(6): 443-457.
[34]
ISOAHO K, MOILANEN F, TOIKKA A. A big data view of the European Energy Union: shifting from a floating signifier to an active driver of decarbonisation?[J]. Politics and governance, 2019, 7(1): 28-44.
[35]
伊惠芳, 吴红, 马永新, 等. 基于LDA和战略坐标的专机技术主题分析——以石墨烯领域为例[J]. 情报杂志, 2018, 37(5): 97-102.
[36]
王丽, 沈湘. 文本预处理后的LDA模型主题发现与技术演进研究[J]. 农业图书情报, 2019, 31(4):19-28.
[37]
刘自强, 许海云, 岳丽欣, 等. 基于Chunk-LDAvis的核心技术主题识别方法研究[J]. 图书情报工作, 2019, 63(9): 73-84.

龙艺璇:提出研究命题,设计研究方案,进行数据处理与分析,撰写论文内容;

伊惠芳:收集与分析研究数据,修订论文内容。

PDF(2592 KB)

Accesses

Citation

Detail

Sections
Recommended

/