Analytical methods involving electronic tongue technique combined with chemometrics analysis was proposed to discriminate oil variety and predict oil quality parameters. All the studied Camellia oil samples from pressing, n-hexane extraction and scCO2 extraction, were successfully discriminated by principal component analysis (PCA) and hierarchical cluster analysis (HCA). Furthermore, Multi Factor Linear Regression Model (MLRM) was established allowing predictive capacity of oil quality indicators, such as acid value (AV) and peroxide value (POV). The practical potential of e-tongue for the discrimination and assessment of Camellia oils has shown promising application in the characterization of Camellia oils in the oil quality evaluation.