Exploring social representations of adapting to climate change using topic modeling and Bayesian networks

When something unfamiliar emerges or when something familiar does something unexpected people need to make sense of what is emerging or going on in order to act. Social representations theory suggests how individuals and society make sense of the unfamiliar and hence how the resultant social representations (SRs) cognitively, emotionally, and actively orient people and enable communication. SRs are social constructions that emerge through individual and collective engagement with media and with everyday conversations among people. Recent developments in text analysis techniques, and in particular topic modeling, provide a potentially powerful analytical method to examine the structure and content of SRs using large samples of narrative or text. In this paper I describe the methods and results of applying topic modeling to 660 micronarratives collected from Australian academics/researchers, government employees, and members of the public in 2010-2011. The narrative fragments focused on adaptation to climate change (CC) and hence provide an example of Australian society making sense of an emerging and conflict ridden phenomena. The results of the topic modeling reflect elements of SRs of adaptation to CC that are consistent with findings in the literature as well as being reasonably robust predictors of classes of action in response to CC. Bayesian Network (BN) modeling was used to identify relationships among the topics (SR elements) and in particular to identify relationships among topics, sentiment, and action. Finally the resulting model and topic modeling results are used to highlight differences in the salience of SR elements among social groups. The approach of linking topic modeling and BN modeling offers a new and encouraging approach to analysis for ongoing research on SRs.

[1]  Danielle S. McNamara,et al.  Computational Methods to Extract Meaning From Text and Advance Theories of Human Cognition , 2011, Top. Cogn. Sci..

[2]  Suchi Saria,et al.  Dissecting an Online Intervention for Cancer Survivors , 2015, Health education & behavior : the official publication of the Society for Public Health Education.

[3]  A. Carvalho Media(ted)discourses and climate change: a focus on political subjectivity and (dis)engagement , 2010 .

[4]  C. Grant,et al.  Constructions of Climate Change on the Radio and in Nepalese Lay Focus Groups , 2014 .

[5]  Bing Liu Sentiment Analysis and Opinion Mining Opinion Mining , 2011 .

[6]  Margaret E. Roberts,et al.  Computer-Assisted Text Analysis for Comparative Politics , 2015, Political Analysis.

[7]  Carlos José Parales Quenza On the Structural Approach to Social Representations , 2005 .

[8]  Ron Kohavi,et al.  A Study of Cross-Validation and Bootstrap for Accuracy Estimation and Model Selection , 1995, IJCAI.

[9]  James A. Evans,et al.  Machine Translation: Mining Text for Social Theory , 2016 .

[10]  Yiming Yang,et al.  RCV1: A New Benchmark Collection for Text Categorization Research , 2004, J. Mach. Learn. Res..

[11]  Marco Scutari,et al.  Learning Bayesian Networks with the bnlearn R Package , 2009, 0908.3817.

[12]  Gary Klein,et al.  Making Sense of Sensemaking 1: Alternative Perspectives , 2006, IEEE Intelligent Systems.

[13]  T. Lynam,et al.  Research, part of a Special Feature on Making Sense of Climate Change, Orientations to Adaptation Using social representations theory to make sense of climate change: what scientists and nonscientists in Australia think , 2014 .

[14]  Juan-Zi Li,et al.  Semantic Mining of Social Networks , 2015, Semantic Mining of Social Networks.

[15]  K. Weick,et al.  Organizing and the Process of Sensemaking , 2005 .

[16]  Karl E. Weick,et al.  Organized sensemaking: A commentary on processes of interpretive work , 2012 .

[17]  W. Wagner,et al.  Relevance, discourse and the ‘hot’ stable core social representations—A structural analysis of word associations , 1996 .

[18]  Sean Gerrish,et al.  A Language-based Approach to Measuring Scholarly Impact , 2010, ICML.

[19]  Thomas Brendan Murphy,et al.  BayesLCA: An R Package for Bayesian Latent Class Analysis , 2014 .

[20]  Andrew McCallum,et al.  Optimizing Semantic Coherence in Topic Models , 2011, EMNLP.

[21]  Ulrika Olausson,et al.  “We're the Ones to Blame”: Citizens' Representations of Climate Change and the Role of the Media , 2011 .

[22]  Mark Steyvers,et al.  Finding scientific topics , 2004, Proceedings of the National Academy of Sciences of the United States of America.

[23]  W. Bacon Sceptical climate part 2: climate science in Australian newspapers , 2013 .

[24]  Justin Grimmer,et al.  A Bayesian Hierarchical Topic Model for Political Texts: Measuring Expressed Agendas in Senate Press Releases , 2010, Political Analysis.

[25]  S. Jovchelovitch Narrative, Memory and Social Representations: A Conversation Between History and Social Psychology , 2012, Integrative Psychological and Behavioral Science.

[26]  David B. Dunson,et al.  Probabilistic topic models , 2011, KDD '11 Tutorials.

[27]  Jean-Guy Meunier,et al.  Text Mining Methods for Social Representation Analysis in Large Corpora , 2011 .

[28]  T. Lynam,et al.  Sensemaking: a complexity perspective , 2015 .

[29]  L. Whitmarsh Behavioural responses to climate change: Asymmetry of intentions and impacts , 2009 .

[30]  M. GÓmez-MartÍn,et al.  Assessing Knowledge Of Social RepresentationsOf Climate Change And Tourism , 2014 .

[31]  Victoria Wibeck Social representations of climate change in Swedish lay focus groups: Local or distant, gradual or catastrophic? , 2014, Public understanding of science.

[32]  Max Reinert,et al.  Alceste une méthodologie d'analyse des données textuelles et une application: Aurelia De Gerard De Nerval , 1990 .

[33]  Nicholas Smith,et al.  How the public engages with global warming: A social representations approach , 2013, Public understanding of science.

[34]  B. Nerlich,et al.  When climate science became climate politics: British media representations of climate change in 1988 , 2014, Public understanding of science.

[35]  Franz Pernkopf,et al.  Bayesian network classifiers versus selective k-NN classifier , 2005, Pattern Recognit..

[36]  Vicki G. Morwitz,et al.  The Journal of Consumer Research at 40 : A Historical Analysis , 2015 .

[37]  R. Gifford The dragons of inaction: psychological barriers that limit climate change mitigation and adaptation. , 2011, The American psychologist.

[38]  A. Carvalho,et al.  Media uses and social representations of climate change , 2009 .

[39]  Sophie A. Nicholson-Cole,et al.  Barriers perceived to engaging with climate change among the UK public and their policy implications , 2007 .

[40]  S. Lahlou,et al.  What are the “elements” of a representation? , 2011 .

[41]  E-Step Structural Topic Models for Open Ended Survey Responses , 2022 .

[42]  Michael N. Jones,et al.  Redundancy in Perceptual and Linguistic Experience: Comparing Feature-Based and Distributional Models of Semantic Representation , 2010, Top. Cogn. Sci..

[43]  Christina C. Hicks,et al.  Structural and Psycho-Social Limits to Climate Change Adaptation in the Great Barrier Reef Region , 2016, PloS one.

[44]  Bing Liu,et al.  Mining and summarizing customer reviews , 2004, KDD.

[45]  A. Reinert,et al.  Une méthode de classification descendante hiérarchique : application à l'analyse lexicale par contexte , 1983 .

[46]  B. Megyesi,et al.  Climate Change? No, Wise Resource Use is the Issue: Social Representations of Energy, Climate Change and the Future , 2012 .

[47]  S. Lahlou A Method to Extract Social Representations from Linguistic Corpora , 1996 .

[48]  B. Nerlich,et al.  Embracing and resisting climate identities in the Australian press: Sceptics, scientists and politics , 2015, Public understanding of science.

[49]  Olessia Koltsova,et al.  ‘LiveJournal Libra!’: The political blogosphere and voting preferences in Russia in 2011–2012 , 2015, New Media Soc..