Machine Learning for Identifying Emotional Expression in Text: Improving the Accuracy of Established Methods.
Machine Learning for Identifying Emotional Expression in Text: Improving the Accuracy of Established Methods.
复制标题
DOI：
10.1007/s41347-017-0015-5
复制
发表时间：
2017-03-01
期刊：
影响因子：
--
通讯作者：
Giese-Davis, Janine
中科院分区：
文献类型：
--
作者：
Bantum, Erin O;Elhadad, Noemie;Giese-Davis, Janine
情感表达与人类功能的许多重要和有益的方面有关。准确捕捉文本中的情感表达随着人们在在线环境中花费更多时间而变得越来越重要。语言查询和单词计数（LIWC）是一种常用的程序，用于识别许多结构，包括情感表达。在一项早期研究（Bantum & Owen，2009）中，LIWC被证明具有良好的灵敏度，但阳性预测值较差。当前研究的目标是创建一种自动化机器学习技术来模仿手动编码。样本包括在线支持小组，癌症讨论板和表达性写作研究的成绩单，这导致了39，367个高级编码决策。在检查整个样本时，机器学习方法在负面情绪敏感度（LIWC敏感度= 0.85;机器学习敏感度= 0.41）之外的所有类别中都优于LIWC，尽管LIWC没有考虑亲社会情绪，如情感，兴趣和验证。当去除亲社会情绪时，LIWC的表现明显优于机器学习方法（p = 0.001）。
Expression of emotion has been linked to numerous critical and beneficial aspects of human functioning. Accurately capturing emotional expression in text grows in relevance as people continue to spend more time in an online environment. The Linguistic Inquiry and Word Count (LIWC) is a commonly used program for the identification of many constructs, including emotional expression. In an earlier study (Bantum & Owen, 2009) LIWC was demonstrated to have good sensitivity yet poor positive predictive value. The goal of the current study was to create an automated machine learning technique to mimic manual coding. The sample included online support groups, cancer discussion boards, and transcripts from an expressive writing study, which resulted in 39,367 sentence-level coding decisions. In examining the entire sample the machine learning approach outperformed LIWC, in all categories outside of Sensitivity for negative emotion (LIWC Sensitivity = .85; Machine Learning Sensitivity = .41), although LIWC does not take into consideration prosocial emotion, such as affection, interest, and validation. LIWC performed significantly better than the machine learning approach when removing the prosocial emotions (p =