This study aims to classify regions with different air pollution characteristics in Taiwan, and further to evaluate the air quality for each group. A selected multivariate analysis technique, cluster analysis, is applied to the pollution monitoring dataset which including PM_(10), SO_2, NO_2, CO and O_3. The obtained results have proved that the regions of different air pollution characteristic can be generally distinguished. All 22 regions are classified into six groups, and the pollution state for each group is characterized as: Group 1 (high SO_2/NO_2; low PM_(10)), Group 2 (high PM_(10)), Group 3 (high SO_2/PM_(10)), Group 4 (low SO_2/NO_2/CO; high O_3), Group 5 (low CO/NO_2; high O_3) and Group 6 (low PM_(10)/SO_2/NO_2/O_3/CO). Results of air quality evaluation revealed that the regions in group 6 (Ilan, Hualien and Taitung) have the best air quality, and the regions in group 3 (Kaohsiung and Kaohsiung City) have the worst air quality in Taiwan. The results from correlation analysis reveal that incidence of the respiratory system disease is significantly positively correlated with pollution of NO_2 and CO at 99% confidence level.