MPlist: Context aware music playlist

Considering emotions and contextual factors in music recommendation: a systematic literature review

“…In recent years, there have been several attempts to incorporate contextual information to improve music recommendation [85,77,25,46,49,117,88]. In general, this information is composed of data such as location, time, date, and acceleration.…”

“…The proposal is a hybrid approach that combines collaborative methods with user history. Cheng and Shen [25] did not use social network information, but in return, took advantage of the user's history in the music recommendation approach, as in [49,85]. The authors present a system called "Just-for-Me" that considers contexts associated with the user's location and global trends in music popularity.…”

“…To do this, they analyze the user's feedback before recommending new music because they understand that whether a user likes a musical piece in a particular context, then he/she will listen to that musical piece; otherwise, he/she will skip the musical piece without listening to it until the end. Magara et al [85] have proposed the MPlist that recovers the context via listening history. To do this, they use data from various sensors on a user's intelligent mobile device and use them to infer the context and user activity, generating a playlist based on contextual preferences.…”

“…Clearly, such information can influence the user's need for information, therefore, can enrich conventional knowledge such as user's preferences when providing recommendations [19]. In line with Magara's observations [85], users create music playlists manually for various contexts and activities in which they are interested. When their activity or context change, they have to update and reload a playlist based on a new search that fits the new situation.…”

“…Other applications of music recommendation can be found in the literature. For example, TagFlip, MeDJ, ContextPlay, Moodplay, SAfeDJ, MPlist, and m-Motion [63,52,62,5,51,85,37,7]. TagFlip enables active music discovery based on social music tags.…”