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

Lynam, Timothy

doi:10.5751/es-08778-210416

Cited by 20 publications

(11 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Formerly, Su et al (2004; used association rules to extract relationships between environmental factors and fish distribution or fishing grounds. In geoscience and remote sensing, some works use association rules for geographic data (Rodman et al, 2006), for landscape analysis (Ferrarini and Tomaselli, 2010), for finding relations between biophysical/social parameters and urban land surface temperature (Rajasekar and Weng, 2009) or adaptations to climate change (Lynam, 2016), and for image processing for urban environmental analysis (Du et al, 2007). Regarding water topics there are some works that used association rules for coastal water classification (Pereira and Ebecken, 2009), lake sediments analysis (Annoni and Brüggemann, 2008), water resource management (Castelletti et al, 2007), biofilm development in water supply systems (Ramos- Martínez et al, 2014), and fault detection in WWTP (Ruiz et al, 2011).…”

Section: Validationmentioning

confidence: 99%

Which method to use? An assessment of data mining methods in Environmental Data Science

Gibert

Izquierdo

Sànchez–Marrè

et al. 2018

Environmental Modelling & Software

View full text Add to dashboard Cite

Data Mining (DM) is a fundamental component of the Data Science process. Over recent years a huge library of DM algorithms has been developed to tackle a variety of problems in fields such as medical imaging and traffic analysis. Many DM techniques are far more flexible than more classical numerial simulation or statistical modelling approaches. These could be usefully applied to data-rich environmental problems. Certain techniques such as artificial neural networks, clustering, case-based reasoning or Bayesian networks have been applied in environmental modelling, while other methods, like support vector machines among others, have yet to be taken up on a wide scale. There is greater scope for many lesser known techniques to be applied in environmental research, with the potential to contribute to addressing some of the current open environmental challenges. However, selecting the best DM technique for a given environmental problem is not a simple decision, and there is a lack of guidelines and criteria that helps the data scientist and environmental scientists to ensure effective knowledge extraction from data. This paper provides a broad introduction to the use of DM in Data Science processes for environmental researchers. Data Science contains three main steps (pre-processing, data mining and post-processing). This paper provides a conceptualization of Environmental Systems and a conceptualization of DM methods, which are in the core step of the Data Science process. These two elements define a conceptual framework that is on the basis of a new methodology proposed for relating the characteristics of a given environmental problem with a family of Data Mining methods. The paper provides a general overview and guidelines of DM techniques to a non-expert user, who can decide with this support which is the more suitable technique to solve their problem at hand. The decision is related to the bidimensional relationship between the type of environmental system and the type of DM method. An illustrative two way table containing references for each pair Environmental System-Data Mining method is presented and discussed. Some examples of how the proposed methodology is used to support DM method selection are also presented, and challenges and future trends are identified.

show abstract

Section: Validationmentioning

confidence: 99%

Which method to use? An assessment of data mining methods in Environmental Data Science

Gibert

Izquierdo

Sànchez–Marrè

et al. 2018

Environmental Modelling & Software

View full text Add to dashboard Cite

show abstract

“…As with Moloney et al, Lynam (2016) draws on SR theory to contextualize his analysis and interpretation. Lynam took 660 micronarratives produced by respondents who were Australian academics or researchers, government employees, or members of the public, and analyzed them using a data analytic technique called topic modeling, which is new to the social representations literature.…”

Section: Lynam: Exploring Social Representations Of Adapting To Climamentioning

confidence: 99%

“…Both Lynam (2016) and Lynam and Fletcher (2015) demonstrate how different framings, by individuals and society, of climate change or adaptation to climate change differentially orient people to action. For example, those who framed climate change as a natural phenomenon tended to feel disempowered (Lynam and Fletcher 2015) and tended not to do anything other than seek guidance as to what to do (Lynam 2016).…”

Section: What We Have Learnedmentioning

confidence: 99%

See 1 more Smart Citation

Making sense of climate change: orientations to adaptation

Lynam

Walker

2016

E&S

Self Cite

View full text Add to dashboard Cite

“…A number of recent papers discuss applications—and potential perils—of topic modeling in social science and environmental science research (Grimmer & Stewart, ; Grubert & Algee‐Hewitt, ; Hillard, Purpura, & Wilkerson, ; Quinn, Monroe, Colaresi, Crespin, & Radev, ; Vilares & He, ; Wiedemann, ; Wilkerson & Casas, ). Nonetheless, topic modeling has barely permeated the climate change literature, with the majority of existing examples limited to studies that use social media data to analyze coverage of climate change issues (Cody, Reagan, Mitchell, Dodds, & Danforth, ; Jang & Hart, ; Kirilenko & Stepchenkova, ; Williams, McMurray, Kurz, & Hugo, ), including skepticism and belief about climate change (Boussalis & Coan, ; Elgesem, Steskal, & Diakopoulos, ; Farrell, ), and social representations of adaptation (Lynam, ; Lynam & Walker, ). Applications of topic modeling for adaptation research are thus largely unexplored, despite the potential to expand text‐based analysis to much larger scales than is currently possible.…”

Section: Introductionmentioning

confidence: 99%

Frontiers in data analytics for adaptation research: Topic modeling

Lesnikowski

Belfer

Rodman

et al. 2019

WIREs Climate Change

View full text Add to dashboard Cite

Rapid growth over the past two decades in digitized textual information represents untapped potential for methodological innovations in the adaptation governance literature that draw on machine learning approaches already being applied in other areas of computational social sciences. This Focus Article explores the potential for text mining techniques, specifically topic modeling, to leverage this data for large-scale analysis of the content of adaptation policy documents. We provide an overview of the assumptions and procedures that underlie the use of topic modeling, and discuss key areas in the adaptation governance literature where topic modeling could provide valuable insights. We demonstrate the diversity of potential applications for topic modeling with two examples that examine: (a) how adaptation is being talked about by political leaders in United Nations Framework Convention on Climate Change; and (b) how adaptation is being discussed by decision-makers and public administrators in Canadian municipalities using documents collected from 25 city council archives. This article is categorized under: Vulnerability and Adaptation to Climate Change > Institutions for Adaptation K E Y W O R D S climate change adaptation, governance, policy, quantitative text analysis, topic models 1 | INTRODUCTION Text-based research methods have been a cornerstone of qualitative social science methods since the 1950s (Lasswell, 1952). These approaches see documents as meaningful artifacts that can be analyzed for their thematic and semantic content (Krippendorff, 2013), and they form a core component of the climate change adaptation governance literature. In lieu of directly observable and measurable indicators such as greenhouse gas emissions, adaptation governance research relies on written records, surveys, and interviews as its primary information sources about how different actors are responding to climate change impacts. Content analysis methods are commonly applied to sources such as government reports, strategic planning documents, peer reviewed and gray literature, and media stories (Araos et al.

show abstract

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

Cited by 20 publications

References 43 publications

Which method to use? An assessment of data mining methods in Environmental Data Science

Which method to use? An assessment of data mining methods in Environmental Data Science

Making sense of climate change: orientations to adaptation

Frontiers in data analytics for adaptation research: Topic modeling

Contact Info

Product

Resources

About