arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2408.12694cs.CL
收藏

走向歌曲歌词中的个人价值观估计

Towards Estimating Personal Values in Song Lyrics

Delft University of Technology(代尔夫特理工大学);SiriusXM/Pandora

Andrew M. Demetriou, Jaehun Kim, Sandy Manolios, Cynthia C. S. Liem

AI总结:

本研究基于社会科学理论,采用透视主义方法收集歌曲歌词的个人价值观标注并进行聚合,结合预训练词嵌入模型与验证词典实现价值观的自动化估计,为下游音乐个性化任务提供支持。

摘要:

西方国家广泛消费的大多数音乐都包含歌曲歌词,美国样本报告称几乎所有的歌曲库都包含歌词。与此同时,社会科学理论表明,个人价值观——指导我们决策和行为的抽象目标——在沟通中扮演着重要角色:我们分享对我们重要的事物以协调努力、解决问题和应对挑战。因此,歌曲歌词中传达的价值观可能与听众的价值观相似或不同,并进而影响听众对歌曲的反应。这表明,致力于歌词中价值观的自动化估计可能有助于下游的MIR任务,特别是个性化。然而,作为高度主观的文本,歌曲歌词在采样待标注歌曲、标注方法以及选择聚合方法方面提出了挑战。在本项目中,我们采取一种基于社会科学理论的透视主义方法,用于收集标注、估计其质量并进行聚合。然后,我们通过使用经过验证的价值观词典,将聚合评分与基于预训练句子/词嵌入模型的估计进行比较。我们讨论了在概念上“模糊”的解决方案来应对采样和标注挑战,在标注质量和自动化估计方面取得了有希望的初步结果,并提出了未来的方向。

英文摘要:

Most music widely consumed in Western Countries contains song lyrics, with U.S. samples reporting almost all of their song libraries contain lyrics. In parallel, social science theory suggests that personal values - the abstract goals that guide our decisions and behaviors - play an important role in communication: we share what is important to us to coordinate efforts, solve problems and meet challenges. Thus, the values communicated in song lyrics may be similar or different to those of the listener, and by extension affect the listener's reaction to the song. This suggests that working towards automated estimation of values in lyrics may assist in downstream MIR tasks, in particular, personalization. However, as highly subjective text, song lyrics present a challenge in terms of sampling songs to be annotated, annotation methods, and in choosing a method for aggregation. In this project, we take a perspectivist approach, guided by social science theory, to gathering annotations, estimating their quality, and aggregating them. We then compare aggregated ratings to estimates based on pre-trained sentence/word embedding models by employing a validated value dictionary. We discuss conceptually 'fuzzy' solutions to sampling and annotation challenges, promising initial results in annotation quality and in automated estimations, and future directions.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑