Embodiments disclosed herein generally relate to a method and system of determining an overall sentiment of a facility. A computing system receives a video stream, including a plurality of frames, of one or more patrons in a facility over a first time period. The video stream includes data indicative of a sentiment of each of the one or more patrons. The computing system parses the plurality of frames to determine the sentiment of the patron based at least on audio and visual cues of the patron captured in the video stream during the first time period. The computing system aggregates one or more sentiments corresponding to the one or more patrons in a data set indicative of an overall sentiment of the facility. The computing system generates a sentiment value corresponding to the overall sentiment of the facility. The computing system outputs the overall sentiment of the facility.