Clustering of Countries Based on Happiness Index


GÜR İ., Atasoy F.

9th International Symposium on Innovative Approaches in Smart Technologies, ISAS 2025, Gaziantep, Türkiye, 27 - 28 Haziran 2025, (Tam Metin Bildiri) identifier

  • Yayın Türü: Bildiri / Tam Metin Bildiri
  • Doi Numarası: 10.1109/isas66241.2025.11101875
  • Basıldığı Şehir: Gaziantep
  • Basıldığı Ülke: Türkiye
  • Anahtar Kelimeler: clustering, happiness, k-means, spectral
  • Samsun Üniversitesi Adresli: Evet

Özet

Happiness has been an important topic that has been considered throughout the ages. The most important factor that shows the happiness of the society is the happiness of the individual. Considering the subjective and multifaceted nature of happiness, various indices and scales have been prepared for happiness analysis. One of these, the World Happiness Report, has provided important information for evaluating and understanding the different aspects and parameters of happiness. In this study, the data published in the World Happiness Report in 2023 were used to cluster countries as happy, unhappy and medium-level. In this study, the optimum number of clusters was determined as three and the Elbow Method was used. Partitioning algorithms K-Means and Spectral clustering algorithms were used as clustering algorithms. Internal validation indices were used to evaluate the performances of these algorithms. In terms of SI, the K-Means algorithm was 0.280 and Spectral clustering 0.279, respectively. This shows that both algorithms provide consistent results for this dataset.