<![CDATA[Listening to songs has become a norm in society, serving many different purposes, and songs are released frequently nowadays, especially by media-service providers. Users need to overcome the struggle of selecting specific songs because of the enormous information provided by media-service providers. The song recommendation model can play an important part in this puzzlement as an automatic song selector, thus improving the user's experience. In this research, the song recommendation model uses Word2Vec Skip-Gram that functions as a query expansion for the sole purpose of finding the desired lyrics by producing a weight for query expansion. TF-IDF is first used to select the words in the lyrics that will be expanded. The model will give a list of 10 recommended songs. The evaluation results of the recommended song list shows the highest average of precision@10 score of 0.584 and the highest Mean Average Score (MAP) score of 0.7278.]]>
Copyrights © 2019
