Louisiana State University, Baton Rouge, Louisiana 70803, USA.
Hum Factors. 2012 Aug;54(4):530-45. doi: 10.1177/0018720811425922.
The goal of this work is to develop and test an automated system methodology that can detect emotion from text and speech features.
Affective human-computer interaction will be critical for the success of new systems that will be prevalent in the 21st century. Such systems will need to properly deduce human emotional state before they can determine how to best interact with people.
Corpora and machine learning classification models are used to train and test a methodology for emotion detection. The methodology uses a stepwise approach to detect sentiment in sentences by first filtering out neutral sentences, then distinguishing among positive, negative, and five emotion classes.
Results of the classification between emotion and neutral sentences achieved recall accuracies as high as 77% in the University of Illinois at Urbana-Champaign (UIUC) corpus and 61% in the Louisiana State University medical drama (LSU-MD) corpus for emotion samples. Once neutral sentences were filtered out, the methodology achieved accuracy scores for detecting negative sentences as high as 92.3%.
Results of the feature analysis indicate that speech spectral features are better than speech prosodic features for emotion detection. Accumulated sentiment composition text features appear to be very important as well. This work contributes to the study of human communication by providing a better understanding of how language factors help to best convey human emotion and how to best automate this process.
Results of this study can be used to develop better automated assistive systems that interpret human language and respond to emotions through 3-D computer graphics.
本研究旨在开发和测试一种能够从文本和语音特征中检测情感的自动化系统方法。
情感人机交互对于 21 世纪流行的新型系统的成功至关重要。此类系统需要在确定如何与人类进行最佳交互之前，正确推断人类的情绪状态。
使用语料库和机器学习分类模型来训练和测试情绪检测方法。该方法采用逐步方法，通过首先过滤掉中性句子，然后区分积极、消极和五种情绪类别，来检测句子中的情感。
在伊利诺伊大学厄巴纳-香槟分校（UIUC）语料库中，分类情感和中性句子的结果达到了 77%的召回准确率，在路易斯安那州立大学医学剧（LSU-MD）语料库中，情绪样本的召回准确率为 61%。一旦过滤掉中性句子，该方法检测负面句子的准确率高达 92.3%。
特征分析的结果表明，语音频谱特征比语音韵律特征更适合情感检测。累积情感构成的文本特征似乎也非常重要。这项工作通过提供对语言因素如何帮助最佳传达人类情感以及如何最佳自动化这一过程的更好理解，为人类交流的研究做出了贡献。
本研究的结果可用于开发更好的自动化辅助系统，这些系统可以通过 3-D 计算机图形理解人类语言并对情感做出反应。
