This paper presents the results of a behavioral experiment conducted between February 2020 and March 2021 on a sample of about 500 university students that were randomly matched with either a human or a humanoid robot partner to play an iterated Prisoner’s Dilemma, to test whether their choices were influenced by the nature and behavior of their partner. The results show that subjects are more likely to cooperate with human rather than with robotic partners; that they are more likely to cooperate after receiving a verbal reaction following a sub-optimal social outcome; and that the effect of the verbal reaction is not dependent on the nature of the partner. Our findings provide new evidence on the effects of verbal communication in strategic frameworks that involves humanoid robotic partners. The results are robust to: the exclusion of students of Economics-related subjects, the inclusion of a set of psychological and behavioral controls, the subjects’ perception on robots’ behavior, and gender biases in human–human interactions.