Cross-Societal Analysis of Climate Change Awareness and Its Relation to SDG 13: A Knowledge Synthesis from Text Mining

Unraveling public perceptions of the Sustainable Development Goals for better policy implementation

Public participation is crucial for policy-making and can contribute to strengthening democracies and decision-making. Public participation can help to address sustainability challenges and plays a key role in attaining the Sustainable Development Goals (SDGs). While the SDGs are policy concepts, there has been limited research conducted on how the public perceives the SDGs. Public participation in scientific research has been carried out through citizen science (CS). This paper analyzes the public's perception of the SDGs through CS and how the public can participate in their implementation. The paper uses the OSDG community platform, a citizen science platform with >2000 participants, to analyze public perception of the SDGs. A set of 40,062 excerpts of text (v2023-01-01), a topic modeling and agreement scores by using CorTexT Manager software, was analyzed. The results show that some SDGs, e.g. health (SDG3) or life below water (SDG14), have higher levels of agreement from the public, whilst for other SDGs the public disagree on their perception, (e.g. zero hunger). The paper shows that issues affecting citizens' daily lives (e.g. in People related goals) tend to have a higher level of agreement among volunteers, while economic issues and directives have greater discrepancies. The results provide an overview of the differences in public perception on the SDGs and their implementation. The misperceptions regarding the SDGs should be reduced to achieve a better implementation, improve public participation, and help policy-making processes.

Research Trends on Climate Change and Circular Economy from a Knowledge Mapping Perspective

The circular economy (CE) has been proposed as a potentially significant catalyst to enhance the current response to the global climate crisis. The objective of this study was to investigate the scientific literature of the research between climate change and CE adopting a knowledge mapping approach. Based on a total of 789 peer-reviewed publications extracted from Scopus, we found that research on climate change and CE is continually growing and interdisciplinary in nature. Europe notably leads scientific production. Keyword evolution shows that CE has been influenced by more lines of research than climate change. We also found that waste management is the CE approach most associated with climate change, mitigation is the climate action most impacted by CE, and food is the most reported greenhouse gas (GHG)-emitting material. However, there are knowledge gaps in the integration of the social dimension, the promotion of climate change adaptation, and the association of sustainable development goal (SDG) 13. Finally, we identified four potentially valuable directions for future studies: (i) CE practices, (ii) bioeconomy, (iii) climate and energy, and (iv) sustainability and natural resources, in which carbon recovery technologies, green materials, regional supply chains, circular agriculture models, and nature-based solutions are promising themes.

Applying Text Mining, Clustering Analysis, and Latent Dirichlet Allocation Techniques for Topic Classification of Environmental Education Journals

Facing the big data wave, this study applied artificial intelligence to cite knowledge and find a feasible process to play a crucial role in supplying innovative value in environmental education. Intelligence agents of artificial intelligence and natural language processing (NLP) are two key areas leading the trend in artificial intelligence; this research adopted NLP to analyze the research topics of environmental education research journals in the Web of Science (WoS) database during 2011–2020 and interpret the categories and characteristics of abstracts for environmental education papers. The corpus data were selected from abstracts and keywords of research journal papers, which were analyzed with text mining, cluster analysis, latent Dirichlet allocation (LDA), and co-word analysis methods. The decisions regarding the classification of feature words were determined and reviewed by domain experts, and the associated TF-IDF weights were calculated for the following cluster analysis, which involved a combination of hierarchical clustering and K-means analysis. The hierarchical clustering and LDA decided the number of required categories as seven, and the K-means cluster analysis classified the overall documents into seven categories. This study utilized co-word analysis to check the suitability of the K-means classification, analyzed the terms with high TF-IDF wights for distinct K-means groups, and examined the terms for different topics with the LDA technique. A comparison of the results demonstrated that most categories that were recognized with K-means and LDA methods were the same and shared similar words; however, two categories had slight differences. The involvement of field experts assisted with the consistency and correctness of the classified topics and documents.