It is known that the polymorphism of genes involved in ethanol metabolism can influence the risk of alcohol-related cancers, mainly head and neck cancers (HNCs). The present meta-analysis aims to assess the association between ALDH2 rs671 polymorphism and susceptibility to HNC, based on genetic models and evaluating 15 case-control studies. Medline, Cochrane Library, Web of Science, and Scopus databases were searched without any restrictions until April 15, 2020. Odds Ratio (OR) was the effect estimate used to demonstrate the association between the gene polymorphism and HNC, RevMan 5.3 software was used to conduct the meta-analysis. The CMA 2.0 software was used to evaluate publication bias through funnel plots and to perform sensitivity analysis and meta-regression. Out of 225 records retrieved through four databases, 15 full-texts were included in the meta-analysis. The pooled ORs for the risk of HNC based on allele, homozygote, heterozygote, recessive, and dominant models of ALDH2 rs671 polymorphism were 1.08 (95% CI: 0.93, 1.24; P = 0.31), 0.64 (95% CI: 0.51, 0.81; P = 0.0002), 1.41 (95% CI: 1.17, 1.71; P = 0.0004), 1.53 (95% CI: 1.15, 2.05; P = 0.003), and 0.56 (95% CI: 0.46, 0.68; P < 0.00001), respectively. The present meta-analysis illustrated an association between ALDH2 rs671 polymorphism and HNC susceptibility. In particular, the GA genotype were linked to high-risk NHC, while the AA genotype was associated with reduced HNC risk.