We report on new flavor tagging algorithms developed to determine the quark-flavor content of bottom (B) mesons at Belle II. The algorithms provide essential inputs for measurements of quark-flavor mixing and charge-parity violation. We validate and evaluate the performance of the algorithms using hadronic B decays with flavor-specific final states reconstructed in a data set corresponding to an integrated luminosity of 62.8 fb(-1), collected at the gamma(4S) resonance with the Belle II detector at the SuperKEKB collider. We measure the total effective tagging efficiency to be epsilon(eff) = (30.0 +/- 1.2(stat) +/- 0.4(syst))% for a category-based algorithm and epsilon(eff) = (28.8 +/- 1.2(stat) +/- 0.4(syst))% for a deep-learning-based algorithm.
