Since interactions with social robots are novel and exciting for many people, one concern is the extent to which people’s behavioural and emotional engagement with robots might develop from initial interactions with a robot, when a robot’s novelty is especially salient, and sustained over time. This challenge is particularly noticeable in interactions designed to support people’s wellbeing, with limited evidence for how social robots can support people’s emotional health over time. Accordingly, this research is aimed at studying how long-term repeated interactions with a social robot affect people’s self-disclosure behaviour toward the robot, perceptions of the robot, and how it affected factors related to well-being. We conducted a mediated long-term online experiment with participants conversing with the social robot Pepper 10 times over 5 weeks. We found that people self-disclose increasingly more to a social robot over time, and found the robot to be more social and competent over time. Participants’ moods got better after talking to the robot and across sessions, they found the robot’s responses to be more comforting over time, and they also reported feeling less lonely over time. Finally, our results stress that when the discussion theme was supposedly more emotional, participants felt lonelier and stressed. These results set the stage for addressing social robots as conversational partners and provide crucial evidence for their potential introduction as interventions supporting people’s emotional health through encouraging self-disclosure.