Possibility of Discourse Analysis using Topic Modeling

다국어 초록 (Multilingual Abstract)

This study is an attempt to introduce topic modeling as a method for discourse analysis in order to explore new possibilities for discourse analysis. Human language data, which is used for discourse analysis, holds plenty of information, however, traditional research methods on language data have several limitations. Topic modeling, which is a statistical analysis method applied to language data, is suitable for a discourse analysis for three reasons: (1) The “topic” extracted via topic modeling contains useful information for inferring discourse. The information shows the key functions of the particular discourse. (2) Topic modeling’s multiple topic assumption makes it possible to examine the dynamics of discourses. (3) Recent topic modeling techniques allow researchers to study changes in discourse over time as well as interactions between discourse and non-discursive factors. Although topic modeling methods have limitations, the shortcomings can be complemented and remedied. Furthermore, text mining, including topic modeling, is not limited to discourse analysis and can be applied to the study of various variables and concepts in social science. The social sciences must make an effort to better understand and best utilize these new methods.

참고문헌 (Reference)

1 Roberts, Margaret E, "stm : R package for structural topic models" 10 (10): 1-40, 2014

2 Dickinson, R., "Weber’s Sociology of the Press and Journalism: Continuities in Contemporary Sociologies of Journalists and the Media" 13 (13): 197-215, 2013

3 Viera, Anthony J., "Understanding Interobserver Agreement : The Kappa Statistic" 37 (37): 360-363, 2005

4 Johan Bollen, "Twitter mood predicts the stock market" Elsevier BV 2 (2): 1-8, 2011

5 Steinskog, Asbjørn, "Twitter Topic Modeling by Tweet Aggregation" 2017

6 Qiang, Jipeng, "Topic modeling over short texts by incorporating word embeddings" 2017

7 Alvarez-Melis, David, "Topic Modeling in Twitter: Aggregating Tweets by Conversations" 519-522, 2016

8 Foucault, Michel, "The Order of Things: An Archaeology of the Human Sciences" Psychology Press 2002

9 Foucault, Michel, "The History of Sexuality: An Introduction, volume I" Vintage 1990

10 Kozlowski, Austin C., "The Geometry of Culture: Analyzing Meaning through Word Embeddings"

11 Foucault, Michel, "The Archaeology of Knowledge" Tavistock Publications 1972

12 Blei, David M., "Text Mining: Classification, Clustering, and Applications" Chapman and Hall/CRC 101-124, 2009

13 Kwartler, Ted, "Text Mining in Practice with R" John Wiley & Sons 2017

14 Quan, Xiaojun, "Short and Sparse Text Topic Modeling via Self-Aggregation" 2015

15 Sejeong Kwon, "Rumor Detection over Varying Time Windows" Public Library of Science (PLoS) 12 (12): e0168344-, 2017

16 David M. Blei, "Probabilistic topic models" Association for Computing Machinery (ACM) 55 (55): 77-84, 2012

17 Lukes, Steven, "Power: A Radical View" Palgrave Macmillan 2005

18 Danner, Deborah D, "Positive Emotions in Early Life and Longevity : Findings from the Nun Study" 80 (80): 804-813, 2001

19 Foucault, Michel, "Orders of Discourse" 10 (10): 7-30, 1971

20 Slater, Michael D, "News Coverage of Cancer in the United States : A National Sample of Newspapers, Television, and Magazines" 13 (13): 523-537, 2008

21 James A. Evans, "Machine Translation: Mining Text for Social Theory" Annual Reviews 42 (42): 21-50, 2016

22 Blei, David M, "Latent Dirichlet Allocation" 3 : 993-1022, 2003

23 Dosse, François, "History of Structuralism: The Rising Sign, 1945-1966 (Vol. 1)" U of Minnesota Press 1-, 1997

24 Foucault, Michel, "History of Madness" Routledge 2013

25 Deleuze, Gilles, "Foucault" University of Minnesota Press 1988

26 Hong, Liangjie, "Empirical Study of Topic Modeling in Twitter" 2010

27 Blei, David M., "Dynamic Topic Models" 2006

28 Foucault, Michel, "Discipline and Punish: The Birth of the Prison" Vintage 1977

29 Pons, Pascal, "Computing communities in large networks using random walks" 2005

30 Santo Fortunato, "Community detection in networks: A user guide" Elsevier BV 659 : 1-44, 2016

31 Fortunato, Santo, "Community Detection in Graphs" 486 (486): 75-174, 2010

32 Ham, Yugeun, "Big data, gyungyoungeul bagguda [Big data changes management]" Samsung Economic Research Institute 2012

33 James, Gareth, "An Introduction to Statistical Learning (Vol. 6)" Springer 2013

34 Jónsson, Elıas, "An Evaluation of Topic Modelling Techniques for Twitter"

35 David M. Blei, "A correlated topic model of Science" Institute of Mathematical Statistics 1 (1): 17-35, 2007

36 Gerlach, Martin, "A Network Approach to Topic Models" 4 (4): 1360-, 2018

37 Zhao Yang, "A Comparative Analysis of Community Detection Algorithms on Artificial Networks" Springer Science and Business Media LLC 6 (6): 30750-, 2016