2019/11/12 by Isabella Czedik-Eysenberg, Czedik-Eysenberg, Isabella, Oliver Wieczorek +3 · 1 citation
Arts and Humanities · Computer Science · #Audio and Speech Processing (eess.AS) #Computation and Language (cs.CL) #Diverse Musicological Studies #FOS: Computer and information sciences #FOS: Electrical engineering #H.5.5 #Music History and Culture #Music and Audio Processing #Sound (cs.SD) #electronic engineering #information engineering
paper · pdf · doi:10.48550/arxiv.1911.04952
openalex publication_date 2019/11/12 · openalex created_date 2022/07/26 · openalex updated_date 2026/07/28
We look into the connection between the musical and lyrical content of metal\nmusic by combining automated extraction of high-level audio features and\nquantitative text analysis on a corpus of 124.288 song lyrics from this genre.\nBased on this text corpus, a topic model was first constructed using Latent\nDirichlet Allocation (LDA). For a subsample of 503 songs, scores for predicting\nperceived musical hardness/heaviness and darkness/gloominess were extracted\nusing audio feature models. By combining both audio feature and text analysis,\nwe (1) offer a comprehensive overview of the lyrical topics present within the\nmetal genre and (2) are able to establish whether or not levels of hardness and\nother music dimensions are associated with the occurrence of particularly harsh\n(and other) textual topics. Twenty typical topics were identified and projected\ninto a topic space using multidimensional scaling (MDS). After Bonferroni\ncorrection, positive correlations were found between musical hardness and\ndarkness and textual topics dealing with 'brutal death', 'dystopia', 'archaisms\nand occultism', 'religion and satanism', 'battle' and '(psychological)\nmadness', while there is a negative associations with topics like 'personal\nlife' and 'love and romance'.\n