• Journal of Korea Multimedia Society
• /
• v.21 no.1
• /
• pp.45-50
• /
• 2018

This research paper describes how to summarize music lyrics using the TextRank algorithm. This method can summarize music lyrics as important lyrics. Therefore, we recommend music more effectively than analyzing the number of words and recommending music.

• Journal of Korea Multimedia Society
• /
• v.24 no.8
• /
• pp.1184-1191
• /
• 2021

In a pop song, the creator's intention is communicated to the user through music and lyrics. Lyric meaning is as important as music, but in most cases lyrics are delivered to users in a static form without non-verbal cues. Providing lyrics in a static text format is inefficient in conveying the emotions of a music. Recently, lyrics video with kinetic typography are increasingly provided, but producing them requires expertise and a lot of time. Therefore, in this system, the emotions of the lyrics are found through the analysis of the text of the lyrics, and the deep learning model is trained with the data obtained by converting the melody into a Mel-spectrogram format to find the appropriate emotions for the music. It sets properties such as motion, font, and color using the emotions found in the music, and automatically creates a kinetic typography video. In this study, we tried to enhance the effect of conveying the meaning of music through this system.

• Journal of Korea Entertainment Industry Association
• /
• v.13 no.8
• /
• pp.267-280
• /
• 2019

The hybrid phenomenon of pronunciation of K-Pop lyrics, which is the diction fusion phenomenon of lyrics, is not a strategic measure for an overseas expansion but a natural formation in the course of history of K-Pop. With the debut of Seo Tai-ji and Boys in 1992, the course of K-Pop changed and settled from ballad to dance music. After three years, the success of a hip hop dance music, 'Come Back Home', opened up a door to Korean Americans who ascertained the potential competitiveness of a hip hop music in K-Pop market. And the writer insists that such advance of Korean Americans into K-Pop market is the origin of the bilingual usage and diction fusion phenomenon of K-Pop lyrics. Therefore, this research will look into the pronunciation system of Korean and English in order to understand the bilingual pronunciation system shown in the lyrics sung by Korean American hip hop singers in the 1990s. Moreover, through Korean pronunciation system, this analysis will discover the main cause of continual acceptance and application of Korean American's broken Korean in the diction of lyrics. Last but not least, this exploration will show the correlation of English pronunciation method of Korean lyrics appeared in K-Pop and the diction of Korean lyrics used by Korean American hip hop singers in late 90s. This research will identify the primary cause of the diction fusion phenomenon in the course of history of K-Pop.

• Journal of the Korea Society of Computer and Information
• /
• v.29 no.5
• /
• pp.177-187
• /
• 2024

177-Existing music recommendation systems do not sufficiently consider the discrepancy between the intended emotions conveyed by song lyrics and the actual emotions felt by users. In this study, we generate topic vectors for lyrics and user comments using the LDA model, and construct a user preference model by combining user behavior trajectories reflecting time decay effects and playback frequency, along with statistical characteristics. Empirical analysis shows that our proposed model recommends music with higher accuracy compared to existing models that rely solely on lyrics. This research presents a novel methodology for improving personalized music recommendation systems by integrating emotion recognition and user behavior analysis.

• KIISE Transactions on Computing Practices
• /
• v.22 no.10
• /
• pp.479-487
• /
• 2016

People can listen to almost every type of music by music streaming services without possessing music. Ironically it is difficult to choose what to listen to. A music recommendation system helps people in making a choice. However, existing recommendation systems have high computation complexity and do not consider context information. Emotion is one of the most important context information of music. Lyrics can be easily computed with various language processing techniques and can even be used to extract emotion of music from itself. We suggest a music-level similarity evaluation method using emotion and structure. Our result shows that it is important to consider semantic information when we evaluate similarity of music.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2022.07a
• /
• pp.471-474
• /
• 2022

음원 스트리밍 서비스 시장은 지속해서 성장해왔다. 그중 최근에 가장 성장세가 돋보이는 서비스는 Spotify와 Youtube music이다. 두 서비스의 추천시스템은 사용자가 좋아할 만한 음악을 계속해서 추천해 줌으로써 많은 사랑을 받고 있다. 추천시스템 성능은 추천에 활용할 수 있는 변수(Feature) 수에 비례한다고 볼 수 있다. 최대한 많은 정보를 알아야 사용자가 원하는 추천이 가능하기 때문이다. 본 논문에서는 기존에 존재하는 감정분류 방법론인 사전기반과 딥러닝 BERT를 사용한 머신기반 방법론을 적절하게 결합하여 장점을 유지하면서 단점을 보완한 하이브리드 감정 분석 모델을 제안함으로써 가사에서 느껴지는 감정 비율을 분석한다. 감정 비율을 음원 가중치 변수로 사용하면 감정 정보를 포함한 고도화된 추천을 기대할 수 있다.

• Journal of Digital Convergence
• /
• v.11 no.3
• /
• pp.95-100
• /
• 2013

K-POP is getting population at the all over the world. K-POP is based on the hook song that made using repetitive lyrics and melody. The characteristics of the music is a bit simple and cheerful rhythm and melody easy to sing along, interesting lyrics and great dance skills. K-POP is spreading to various countries via various social networking services such as YouTube, Facebook, Twitter. K-POP dominated by the digital music market, showed a growing tendency to shorten the length of music, to create a music that can give a strong impression. And 60 second pre-listening function increased music used the chorus in the first part. But it was generated the result that made obscures the configuration of the music and the meaning of the lyrics. In this paper, we study the characteristics of K-POP music and will present three directions of the hook song music production. Finally, we compared to Kangnamstyle of Psy using the proposed three standards.

• The Journal of the Korea Contents Association
• /
• v.20 no.10
• /
• pp.89-99
• /
• 2020

In this study, we tried to produce moving-image works through sentiment analysis of music. First, Google natural language API was used for the sentiment analysis of lyrics, then the result was applied to the image visualization rules. In prior engineering researches, text-based sentiment analysis has been conducted to understand users' emotions and attitudes by analyzing users' comments and reviews in social media. In this study, the data was used as a material for the creation of artworks so that it could be used for aesthetic expressions. From the machine's point of view, emotions are substituted with numbers, so there is a limit to normalization and standardization. Therefore, we tried to overcome these limitations by linking the results of sentiment analysis of lyrics data with the rules of formative elements in visual arts. This study aims to transform existing traditional art works such as literature, music, painting, and dance to a new form of arts based on the viewpoint of the machine, while reflecting the current era in which artificial intelligence even attempts to create artworks that are advanced mental products of human beings. In addition, it is expected that it will be expanded to an educational platform that facilitates creative activities, psychological analysis, and communication for people with developmental disabilities who have difficulty expressing emotions.

• Proceedings of the KAIS Fall Conference
• /
• 2010.11b
• /
• pp.528-530
• /
• 2010

본 논문에서는 음악의 분석, 특히 대중가요의 가사 분석에 있어서 사회학적 관점인 기호학을 기초로 분석을 하였으며, 특히 '강산에'의 노래가사를 중심으로 분석을 하였다. 2집은 1994년에 발매 되었는데, 당시의 사회적 분위기와 맞물린 '비판적'가사의 흐름이외에도 '정서적', '의식적'인 구조에 대해서도 분석하였다.

• Korean Journal of Culture and Social Issue
• /
• v.26 no.3
• /
• pp.221-257
• /
• 2020

This study examined whether popular music lyrics, the new research topic, reflect changes in Koreans' cultural orientation and whether individuals' cultural orientation is related to the genre of popular music that they prefer. In Study 1, we content analyzed popular music lyrics from 1980 to 2018 to see if Koreans' cultural orientations changed over time. The analysis showed that as the release dates approached the 2010s, the lyrics expressed the ideal attitudes of individualist cultures more frequently than those of collectivist cultures; this suggests that Koreans have gradually become more individualistic over time. In Study 2, we examined the relationships between individuals' cultural orientations, preferences for various genres of popular music, and functions of music. The analysis showed that people with more collectivistic attitudes tended to prefer mid- and low-arousal music, such as Ballads and Rap/Hiphop, while those with less collectivistic attitudes preferred high-arousal music, such as Rock/Metal. This result is partly consistent with the hypothesis that collectivistic people would prefer lower to higher arousal music. In addition, our analysis showed the strongest positive relationship between collectivism and the social function of music; this result can be interpreted as indicating that collectivistic people use music to maintain good interpersonal relationships. This paper concludes by discussing the implications of these findings, the limitations of this study, and directions for further research.