社交媒体上的公共卫生讨论:评估自动化情绪分析方法
Lisa M Gandy1, Lana V Ivanitskaya2, Leeza L Bacon3
1Department of Computer Science, College of Sciences and Liberal Arts, Kettering University, Flint, MI, United States.
JMIR formative research
|January 8, 2025
概括
这项研究将自动化情绪分析工具与YouTube关于阿片类药物流行病的评论进行了比较. 对于不平衡的数据集,VADER和LIWC-22显示出有希望的结果,而ChatGPT 4.0表现不佳.
科学领域:
- 计算社会科学 计算社会科学
- 自然语言处理自然语言处理.
- 公共卫生信息学 公共卫生信息学
背景情况:
- 情绪分析对于社交媒体研究至关重要,但在手动和自动化方法之间做出选择需要指导.
- 在YouTube上关于阿片类药物流行病的讨论为情绪分析提供了一个复杂,不平衡的数据集.
研究的目的:
- 为了比较流行的自然语言处理 (NLP) 工具 (VADER,TEXT2DATA,LIWC-22) 和大型语言模型 (ChatGPT 4.0) 与手动情绪编码的性能.
- 评估情绪分析方法,基于诸如编程方便性和成本等实际考虑.
主要方法:
- 手动的情绪编码使用诱导性,代性的内容分析方法.
- 使用描述性统计,ROC曲线分析,混矩阵和协议指标 (Cohen κ,准确度,精度,灵敏度,F1分数,MCC) 的定量评估.
主要成果:
- 在不平衡的数据集中,LIWC-22的语调总结测量在估计负面情绪普遍性方面表现出色.
- 通过ROC分析,VADER在分类手动编码的负面评论方面表现最好.
- NLP工具显示与手动编码 (Cohen κ) 相当一致,而ChatGPT 4.0显示一致性较差,并且在多次尝试中失败.
结论:
- 建议使用VADER作为一种免费的情绪分析工具,特别是在更长的评论中,因为它具有强大的歧视能力.
- 建议使用LIWC-22的语调总结来估计不平衡数据集中的负面评论流行率.
- 聊天GPT 4.0还没有超过NLP模型来分析高度不平衡的社交媒体数据.
关键词:
聊天GPT 聊天GPT 聊天这就是LIWC-22的原因.瓦德尔 (VADER) 是一个伟大的人.在YouTube上播放视频.药物 药物 药物 药物 药物 药物机器学习是机器学习.药物 药物 药物 药物在阿片类药物阿片类药物.药品制品制品制品制品制品制品制品制品药物治疗药物治疗人口健康 人口健康公共卫生公共卫生.情绪分析是一种情绪分析.社交媒体 社交媒体瓦伦斯意识到词典的情感推理推理的词典.更多相关视频
06:39Electroencephalographic, Heart Rate, and Galvanic Skin Response Assessment for an Advertising Perception Study: Application to Antismoking Public Service Announcements
Published on: August 28, 2017
14.2K
07:12Protocol for Data Collection and Analysis Applied to Automated Facial Expression Analysis Technology and Temporal Analysis for Sensory Evaluation
Published on: August 26, 2016
9.4K
相关概念视频
01:54Attitudes
28.2K
Attitude is our evaluation of a person, an idea, or an object. We have attitudes for many things ranging from products that we might pick up in the supermarket to people around the world to political policies. Typically, attitudes are favorable or unfavorable: positive or negative (Eagly & Chaiken, 1993). And, they have three components: an affective component (feelings), a behavioral component (the effect of the attitude on behavior), and a cognitive component (belief and knowledge;...
28.2K
02:16Surveys
14.7K
Often, psychologists develop surveys as a means of gathering data. Surveys are lists of questions to be answered by research participants, and can be delivered as paper-and-pencil questionnaires, administered electronically, or conducted verbally. Generally, the survey itself can be completed in a short time, and the ease of administering a survey makes it easy to collect data from a large number of people.
14.7K
02:16Stereotype Content Model
14.0K
The Stereotype Content Model (SCM) was first proposed by Susan Fiske and her colleagues (Fiske, Cuddy, Glick & Xu, 2002; see also Fiske, 2012 and Fiske, 2017). The SCM specifies that when someone encounters a new group, they will stereotype them based on two metrics: warmth—or that group’s perceived intent, and how likely they are to provide help or inflict harm—and competence—or their ability to carry out that objective. Depending on the warmth-competence...
14.0K