The social Internet of Things (SIoT) is promoted in the literature as enabling the integration of devices into users' daily lives. This integration can be achieved by exploiting the interconnectivity and the user friendliness offered by social network services (SNSs). The SIoT paradigm opens the door to studying the intelligence mechanisms required to enhance service adaptability. The authors study the integration of cognitive reasoning into the SIoT for providing recommendation of quotidian tasks in smart homes. Achieving situation characterization requires reasoning about physical as well as social aspects of context. Thus, as a service built on top of the social cloud (SoC), the authors propose an intelligent recommendation (InRe) framework that applies the reasoning mechanism on context elements that are represented using ontologies. Initial experiments with ThingsChat, a proof-of-concept prototype, indicate considerable improvement in adaptability of recommendation results to users' situations