We use the "social shaping of technology and society" framework to qualitatively analyze data collected through observation of human-robot interaction (HRI) between social actors in a nursing home (staff, residents, visitors) and the socially assistive robot PARO. The study took place over the course of three months, during which PARO was placed in a publicly accessibly space where participants could interact with it freely. Social shaping focuses attention on social factors that affect the use and interpretation of technology in particular contexts. We therefore aimed to understand how different social actors make sense of and use PARO in daily interaction. Our results show participant gender, social mediation, and individual sense making led to differential use and interpretation of the robot, which affected the success of human-robot interactions. We also found that exposure to others interacting with PARO affected the nursing staff's perceptions of robots and their potential usefulness in eldercare. This shows that social shaping theory provides a valuable perspective for understanding the implementation of robots in long-term HRI and can inform interaction design in this domain.