This study aimed to appraise seasonal variations in surface water quality on the coasts of Southwestern Vietnam using entropy-weighted water quality index (EWQI) and multivariate statistics: cluster analysis (CA), principal component analysis (PCA), and discriminant analysis (DA). Forty-nine samples monitored in Kien Giang province during the rainy and dry seasons were analysed for 16 physiochemical and biological parameters. Compared to the Vietnamese standard, surface water quality in the study areas was contaminated with organic matter (high biological oxygen demand and chemical oxygen demand), nutrients (high ammonium (NH4+), nitrite, and orthophosphate), total suspended solids (TSS), iron (Fe), and coliform. Seasonal variations in surface water quality in the coastal regions were observed. TSS, organic matter and microbial problems in water bodies tend to be more serious in the rainy seasons due to an increase in water flow containing pollutants from upstream and wastes from regional human activities. Meanwhile, the salinity in the dry season (0–32‰) was greatly higher, which caused only 10% of samples to be suitable for irrigation. CA extracted 11 and 13 clusters from 49 locations in the dry and rainy seasons, respectively. Five principal components obtained from PCA can explain 74 and 70% of total water quality variations in dry and rainy seasons, respectively. Moreover, the results of PCA suggested that natural factors (hydrological regimes, temperature, rainfall, sea-level rise) and human sources (domestic, agriculture, industry, and tourism) are accountable for these fluctuations. DA extracted 7 parameters (pH, TSS, salinity, Fe, nitrate, NH4+, and chloride) for leading the difference in water quality, with 88% of correct assignation. EWQI revealed that about 66% of total samples were classified as a very bad quality for drinking in the dry season. However, this ratio declined to 59% in the rainy season. Although the surface water quality was slightly improved during the rainy season, organic matter and microbial pollution need to be concerned. The findings of this study can provide insights into seasonal variations in surface water with the application of multivariate statistics and EWQI, which could support policymakers in developing water management strategies.