摘要
在当今数字化与网络化时代,图像、音频和视频等多媒体内容已成为互联网信息高速公路上传送数据的重要部分,基于音乐情感的检索技术应运而生。音乐的群众情感则由大量的普通用户通过各种形式表达出来,其中论坛中带交互性的音乐评论则为典型的音乐情感表达形式。从海量Web文本信息中得到音乐的情感等属性并将结果合理地返回给依据情感搜索的用户是一个创新性的解决方案。实践结果证明,音乐论坛主题挖掘系统相对于目前的基于音乐本身的研究具有更大的合理性,对用户的搜索返回具有更强的说服力。
Images, audio, video and other multimedia transmitting on the Internet have become an important part of the digital and network era, retrieval technology based on the music emotion rises. The popular emotion of music expresses by the massive ordinary users through various forms. Interactive music reviews in forums are the typical music emotion expression forms. Extracting music attributes from the magnanimous Web and giving the reasonable emotion results to the searcher are innovative solutions. The experimental results show that, relative to the current system based on the music itself, this solution is more reasonable, and the results returned to the user are more convincing.
出处
《计算机科学》
CSCD
北大核心
2009年第5期172-176,共5页
Computer Science
基金
863国家重点基金项目(07AA01Z440)
四川省应用技术研究与开发项目支撑计划(2008GZ0009)资助
关键词
情感化
文本挖掘
音乐情感
情感计算
Affectivity, Text mining, Music affection, Affection calculate
