An Image-based Global Climate Sentiment Index

As the impacts of climate change on global economic and social systems deepen, identifying and quantifying climate sentiment has become crucial for climate policy design, risk monitoring, and cross-sector governance. To address limitations in existing studies—particularly their reliance on textual data, which introduces strong language dependence and limits cross-country comparability—this study incorporates visual information as the medium for sentiment measurement. Using the Google Images search engine, we collect approximately 3.19 million climate-related images from 19 representative countries over the period 2015–2024. By detecting positive and negative sentiment embedded in visual data, we construct a globally comparable, long-horizon, multi-frequency Climate Sentiment Index. This index transcends linguistic boundaries, substantially improving the accuracy and cross-cultural robustness of sentiment identification. It provides a valuable data foundation and analytical tool for understanding public climate attitudes, tracing risk transmission channels, and analyzing the formation of market expectations, with broad applicability across economic, social, and environmental domains.The following provides an overview of the folders in this repository:<b>CSI_dataset</b>This folder contains the Climate Sentiment Index datasets. It includes 16 CSV files corresponding to global and national-level Climate Positive Sentiment Index (CPSI) and Climate Negative Sentiment Index (CNSI), each provided at four temporal resolutions (daily, weekly, monthly, and annual). In addition, this folder contains visualization figures illustrating the temporal trends of the indices. Four figures are provided, each corresponding to one temporal resolution (daily, weekly, monthly, and annual).<b>keywords</b>This folder contains the keyword lists used for image collection and filtering. These keywords define the scope of climate-related content and support the construction of the dataset.<b>source_code</b>This folder contains the main scripts used in this study, including model training, image classification, index calculation, and visualization. The scripts should be executed in sequence as described in the pipeline section.