RISS 학술연구정보서비스

검색

인기 검색어

    다국어 입력

    http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.

    변환된 중국어를 복사하여 사용하시면 됩니다.

    예시)
    • 中文 을 입력하시려면 zhongwen을 입력하시고 space를누르시면됩니다.
    • 北京 을 입력하시려면 beijing을 입력하시고 space를 누르시면 됩니다.
    닫기
    KCI등재

    Analyzing the roles of a song’s auditory and lyrical features in predicting its success and user ratings with Transformer-based algorithms and statistical analysis approaches

    한글로보기

    https://www.riss.kr/link?id=A109262793

    • 0

      상세조회
    • 0

      다운로드
    서지정보 열기
    • 내보내기
    • 내책장담기
    • 공유하기
      • URL 복사
    • 오류접수
    인용문이 복사되었습니다.

    부가정보

    다국어 초록 (Multilingual Abstract) kakao i 다국어 번역

    This study analyzed and compared the roles of the auditory and lyrical characteristics of a song in predicting its success and audiences’ evaluation using two distinct analytic approaches: deep learning algorithms and statistical analyses. For the prediction tasks, we utilized two separate music datasets to enhance the robustness of the analysis. Using statistical methods, we assessed the explanatory powers of the auditory and lyrical features of a song with the effects of external factors of the song controlled for. The predictions based on the Transformer-based models revealed that 1) for predicting a song’s success, the performances of the models based on auditory features were marginally superior to those of the models based on lyrical features, whereas 2) for predicting user evaluations, the lyrical features of a song played a more significant role than the auditory features. The results also indicated that external factors of a song, such as the singer’s popularity, media coverage, and promotion, played a more significant role than the musical features of the song. However, the statistical analyses showed that after controlling the effects of external factors, there still exist statistically significant roles of auditory and lyrical features in explaining a song’s success and user ratings.
    번역하기

    This study analyzed and compared the roles of the auditory and lyrical characteristics of a song in predicting its success and audiences’ evaluation using two distinct analytic approaches: deep learning algorithms and statistical analyses. For the p...

    This study analyzed and compared the roles of the auditory and lyrical characteristics of a song in predicting its success and audiences’ evaluation using two distinct analytic approaches: deep learning algorithms and statistical analyses. For the prediction tasks, we utilized two separate music datasets to enhance the robustness of the analysis. Using statistical methods, we assessed the explanatory powers of the auditory and lyrical features of a song with the effects of external factors of the song controlled for. The predictions based on the Transformer-based models revealed that 1) for predicting a song’s success, the performances of the models based on auditory features were marginally superior to those of the models based on lyrical features, whereas 2) for predicting user evaluations, the lyrical features of a song played a more significant role than the auditory features. The results also indicated that external factors of a song, such as the singer’s popularity, media coverage, and promotion, played a more significant role than the musical features of the song. However, the statistical analyses showed that after controlling the effects of external factors, there still exist statistically significant roles of auditory and lyrical features in explaining a song’s success and user ratings.

    더보기

    참고문헌 (Reference)

    1 GMI, "Youtube Users Statistics 2023"

    2 Reisz, N., "To what extent homophily and influencer networks explain song popularity"

    3 Fan, J., "Study of Chinese and UK hit songs prediction" 640-652, 2013

    4 Yang, L. -C., "Revisiting the problem of audio-based hit song prediction using convolutional neural networks" 2017

    5 Araujo, C. V. S., "Predicting music popularity using music charts" IEEE 859-864, 2019

    6 Park, E. L., "KoNLPy: Korean NLP in Python"

    7 Yu, L. -C., "Hit song prediction for pop music by siamese cnn with ranking loss"

    8 Pachet, F., "Hit Song Science Is Not Yet a Science" 2008

    9 Zangerle, E., "Hit Song Prediction: Leveraging Lowand High-Level Audio Features" 2019

    10 IFPI, "GLOBAL MUSIC REPORT 2023"

    1 GMI, "Youtube Users Statistics 2023"

    2 Reisz, N., "To what extent homophily and influencer networks explain song popularity"

    3 Fan, J., "Study of Chinese and UK hit songs prediction" 640-652, 2013

    4 Yang, L. -C., "Revisiting the problem of audio-based hit song prediction using convolutional neural networks" 2017

    5 Araujo, C. V. S., "Predicting music popularity using music charts" IEEE 859-864, 2019

    6 Park, E. L., "KoNLPy: Korean NLP in Python"

    7 Yu, L. -C., "Hit song prediction for pop music by siamese cnn with ranking loss"

    8 Pachet, F., "Hit Song Science Is Not Yet a Science" 2008

    9 Zangerle, E., "Hit Song Prediction: Leveraging Lowand High-Level Audio Features" 2019

    10 IFPI, "GLOBAL MUSIC REPORT 2023"

    11 Salganik, M. J., "Experimental study of inequality and unpredictability in an artificial cultural market" 311 (311): 854-856, 2006

    12 Wooldridge, J. M., "Econometric analysis of cross section and panel data" MIT press 2010

    13 Le, Q., "Distributed representations of sentences and documents" PMLR 1188-1196, 2014

    14 Silva, M. O., "Collaboration as a driving factor for hit song classification" 66-74, 2022

    15 Zangerle, E., "Can Microblogs Predict Music Charts? An Analysis of the Relationship Between#Nowplaying Tweets and Music Charts" 2016

    16 Devlin, J., "Bert : Pre-training of deep bidirectional transformers for language understanding"

    17 Dhanaraj, R., "Automatic Prediction of Hit Songs" 488-491, 2005

    18 Vaswani, A., "Attention is all you need" 30 : 2017

    19 Dosovitskiy, A., "An image is worth 16x16 words : Transformers for image recognition at scale"

    20 Merritt, S. H., "Accurately predicting hit songs using neurophysiology and machine learning" 6 : 1154663-, 2023

    21 이도연 ; 장병희, "A Study on Development of a Prediction Model for Korean Music Box Office Based on Deep Learning" 20 (20): 10-18, 2020

    22 Kamal, J., "A Classification Based Approach to the Prediction of Song Popula" 2021

    더보기

    분석정보

    View

    상세정보조회

    0

    Usage

    원문다운로드

    0

    대출신청

    0

    복사신청

    0

    EDDS신청

    0

    동일 주제 내 활용도 TOP

    더보기

    주제

    연도별 연구동향

    연도별 활용동향

    연관논문

    연구자 네트워크맵

    공동연구자 (7)

    유사연구자 (20) 활용도상위20명

    해외이동버튼