Nowadays, Recommender Systems have become essential to users for finding “what they need” within large collections of items. Meanwhile, recent studies have demonstrated as user personality can effectively provide a more valuable information to significantly improve recommenders' performance, especially considering behavioural data captured from social network logs. In this work, we describe a novel music recommendation technique based on the identification of personality traits, moods and emotions of a single user, starting from solid psychological observations recognized by the analysis of user behavior within a social environment. In particular, users personality and mood have been embedded within a content-based filtering approach to obtain more accurate and dynamic results. Several experiments are then reported to show effectiveness of user personality and mood recognition recommendation, thus encouraging research in this direction.
An emotional recommender system for music / Moscato, V.; Picariello, A.; Sperlí, G.. - In: IEEE INTELLIGENT SYSTEMS. - ISSN 1541-1672. - (2021). [10.1109/MIS.2020.3026000]
An emotional recommender system for music
V. Moscato;A. Picariello;G. Sperlí
2021
Abstract
Nowadays, Recommender Systems have become essential to users for finding “what they need” within large collections of items. Meanwhile, recent studies have demonstrated as user personality can effectively provide a more valuable information to significantly improve recommenders' performance, especially considering behavioural data captured from social network logs. In this work, we describe a novel music recommendation technique based on the identification of personality traits, moods and emotions of a single user, starting from solid psychological observations recognized by the analysis of user behavior within a social environment. In particular, users personality and mood have been embedded within a content-based filtering approach to obtain more accurate and dynamic results. Several experiments are then reported to show effectiveness of user personality and mood recognition recommendation, thus encouraging research in this direction.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.