构建首个斯里兰卡僧伽罗语音乐视频评论数据集，助力跨文化音乐情感分析
Linguistic Analysis of Sinhala YouTube Comments on Sinhala Music Videos: A Dataset Study
- 基于27个僧伽罗语音乐视频评论，筛选出63,471条有效语料
- 发现YouTube评论库能代表通用僧伽罗语语料，适合作为研究基础
- 生成964个专用停用词，其中182个与英文停用词匹配，利于多语言对比
本研究聚焦于僧伽罗语音乐视频的社交媒体评论，探索音乐信息检索（MIR）与音乐情感识别（MER）在该领域的应用。通过选取27个包含20首不同僧伽罗语歌曲的YouTube视频，收集并筛选出93,116条评论，经高级过滤与音译处理后，最终获得63,471条高质量僧伽罗语评论。研究还算法生成了964个专属僧伽罗语停用词，其中182个在翻译后与NLTK英文停用词完全一致。对比分析显示，僧伽罗语YouTube评论库可良好代表通用语料。该精心构建的数据集与停用词资源，为未来跨文化音乐情感计算研究提供了重要支持。
原文摘要 · Abstract (English)
This research investigates the area of Music Information Retrieval (MIR) and Music Emotion Recognition (MER) in relation to Sinhala songs, an underexplored field in music studies. The purpose of this study is to analyze the behavior of Sinhala comments on YouTube Sinhala song videos using social media comments as primary data sources. These included comments from 27 YouTube videos containing 20 different Sinhala songs, which were carefully selected so that strict linguistic reliability would be maintained and relevancy ensured. This process led to a total of 93,116 comments being gathered upon which the dataset was refined further by advanced filtering methods and transliteration mechanisms resulting into 63,471 Sinhala comments. Additionally, 964 stop-words specific for the Sinhala language were algorithmically derived out of which 182 matched exactly with English stop-words from NLTK corpus once translated. Also, comparisons were made between general domain corpora in Sinhala against the YouTube Comment Corpus in Sinhala confirming latter as good representation of general domain. The meticulously curated data set as well as the derived stop-words form important resources for future research in the fields of MIR and MER, since they could be used and demonstrate that there are possibilities with computational techniques to solve complex musical experiences across varied cultural traditions
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。