Methods, apparatuses, and computer program products are described for aggregating user sessions for conversational exchanges using a virtual assistant. A user device can receive conversational inputs, convert the conversational inputs into textual strings, associate, based upon semantic analysis of different portions of the textual strings, a first network and a second network, and initiate, respectively, a first and second user session with a first response module of the first network and a second response module of the second network. The portions of textual strings can be transmitted to the first and second response modules via, respectively, the first and second user sessions. Once response fragments are received from the first and second response modules, the response fragments can be combined in a semantically suitable order to form a generated response.