arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1606.06259cs.CLcs.MM
收藏

MOSI:网络舆论视频中情感强度和主观性分析的多模态语料库

MOSI: Multimodal Corpus of Sentiment Intensity and Subjectivity Analysis in Online Opinion Videos

Carnegie Mellon University(卡内基梅隆大学);University of Washington(华盛顿大学)

Amir Zadeh, Rowan Zellers, Eli Pincus, Louis-Philippe Morency

摘要:

人们每天都在通过在线视频分享网站分享他们的观点、故事和评论。研究这些意见视频中的情感和主观性正在受到学术界和工业界越来越多的关注。虽然情感分析在文本方面已经取得了成功,但对于视频和多媒体内容来说,这是一个研究不足的研究问题。这方面研究的最大挫折是缺乏适当的数据集、方法、基线和统计分析,以了解不同模态来源的信息如何相互关联。本文向科学界介绍了第一个在线视频中情感和主观性分析的意见级注释语料库,称为多模态意见级情感强度数据集(MOSI)。该数据集被严格地标注了主观性、情感强度、每帧和每观点标注的视觉特征以及每毫秒标注的音频特征。此外,我们提出了在这个方向上的未来研究的基线,以及一个新的多模态融合的方法,共同建模口语和视觉手势。

英文摘要:

People are sharing their opinions, stories and reviews through online video sharing websites every day. Studying sentiment and subjectivity in these opinion videos is experiencing a growing attention from academia and industry. While sentiment analysis has been successful for text, it is an understudied research question for videos and multimedia content. The biggest setbacks for studies in this direction are lack of a proper dataset, methodology, baselines and statistical analysis of how information from different modality sources relate to each other. This paper introduces to the scientific community the first opinion-level annotated corpus of sentiment and subjectivity analysis in online videos called Multimodal Opinion-level Sentiment Intensity dataset (MOSI). The dataset is rigorously annotated with labels for subjectivity, sentiment intensity, per-frame and per-opinion annotated visual features, and per-milliseconds annotated audio features. Furthermore, we present baselines for future studies in this direction as well as a new multimodal fusion approach that jointly models spoken words and visual gestures.

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。

↑