Edinburgh Napier University

  Music recommender systems are utilised by many music streaming platforms to provide new artist and song recommendations on a personalised basis to listeners. These algorithm-based systems apply dynamic data modelling techniques and are a recommendation source that add to the existing ecosystem of music recommendations both direct and indirect, such as word of mouth, musical journalism, TV and radio, and live events. This research investigated the extent to which user responses to music recommendations may vary across different perceived sources. Results suggest that listeners self-reported to prefer both algorithm- and peer-based recommendations over editorial/expert suggestions. When streaming data was studied, the duration of play was significantly longer for those tracks which were perceived to have been recommended by peers over both algorithms and experts. No difference was found in likelihood to spend time or money on artists when only the recommendation source was considered.