arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2407.18787cs.CY
收藏

音乐歌词中道德价值观的自动检测

Automatic Detection of Moral Values in Music Lyrics

Queen Mary University of London(伦敦大学玛丽女王学院);ISI Foundation(ISI基金会)

Vjosa Preniqi, Iacopo Ghinassi, Julia Ive, Kyriaki Kalimeri, Charalampos Saitis

AI总结:

本研究基于MFT理论,利用GPT-4生成合成歌词微调BERT模型来检测真实音乐歌词中的道德价值观,其准确率比域外和零样本基线模型分别高出5%和12%,实现了免标注且有效的歌词道德学习。

摘要:

道德价值观在我们如何评估信息、做出决策以及对重要社会问题形成判断方面发挥着根本作用。从歌词中快速提取道德特征的可能性,使我们能够更深入地理解自身的音乐收听行为。基于道德基础理论(MFT),我们利用由大型语言模型(GPT-4)生成的2,721首合成歌词对一组基于Transformer的语言模型(BERT)进行微调,并以此在由两位专家标注的200首真实音乐歌词中检测道德价值观。我们将其预测能力与一系列基线模型进行评估对比,包括域外(在MFT标注的社交媒体文本上微调的BERT)和零样本(GPT-4)分类。所提出的模型在各项实验中取得了最佳准确率,加权F1平均得分为0.8。该性能平均比域外和零样本模型高出5%。在考察二元分类的精确率时,所提出的模型平均比基线模型高出12%。我们的方法有助于实现免标注且有效的歌词道德学习,并为大语言模型关于音乐中道德表达的知识蒸馏,以及这些技术对创意产业和音乐文化的潜在影响提供了有益见解。

英文摘要:

Moral values play a fundamental role in how we evaluate information, make decisions, and form judgements around important social issues. The possibility to extract morality rapidly from lyrics enables a deeper understanding of our music-listening behaviours. Building on the Moral Foundations Theory (MFT), we tasked a set of transformer-based language models (BERT) fine-tuned on 2,721 synthetic lyrics generated by a large language model (GPT-4) to detect moral values in 200 real music lyrics annotated by two experts.We evaluate their predictive capabilities against a series of baselines including out-of-domain (BERT fine-tuned on MFT-annotated social media texts) and zero-shot (GPT-4) classification. The proposed models yielded the best accuracy across experiments, with an average F1 weighted score of 0.8. This performance is, on average, 5% higher than out-of-domain and zero-shot models. When examining precision in binary classification, the proposed models perform on average 12% higher than the baselines.Our approach contributes to annotation-free and effective lyrics morality learning, and provides useful insights into the knowledge distillation of LLMs regarding moral expression in music, and the potential impact of these technologies on the creative industries and musical culture.

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。

↑