Supplementary Material for review (Revealing the co-occurrence patterns of the group emotions from social media data)

his repository includes the data, code, and step-by-step instructions for reproducing the findings presented in our IJGIS manuscript, including Tables 1、3、4 and Figures 1–9. All files are anonymized and provided to support reproducibility.SectionFigure/TableScript(s)InputOutput3.1Table 3Code/bert.pydata/wh_data_cleaned.csvModel accuracy assessment3.1Table 4Code/bert.pydata/wh_data_cleaned.csvExamples of emotional structures3.1Figure 4Code/graph.pyResult/bert/wh/128Different types of emotions3.2Figure 5Code/mode_heatmap.pysentiment_density.csvDistribution of kernel density 3.3Figures 7-8Code/tree_v2.pyResult/bert/wh/128/clustering_results.pklEmotional grid management 4.2Table 5-6Code/tree_v2.pyResult/bert/wh/128/clustering_results.pklindexSectionFigure/TableSource/Production MethodsOutput2.2Table 1data/wh_data_cleaned.csvExamples of data 2.2Figure 1ArcGIS proHeatmap of the social media data 2.2Figure 2Customize images based on power pointThe proposed framework2.2Figure 3Customize images based on power pointFixed Grids vs. Adaptive Grids3.2Figure 6Data/emotion_prediction_wh.csv(Customize images based on EXCEL)Percentages of different emotional patterns4.1Figure 9Data/emotion_prediction_wh.csv(Customize images based on EXCEL)Histogram of comparisons among different types of emotions