[论文解读] A Review on Text-Based Emotion Detection -- Techniques, Applications, Datasets, and Future Directions

Sheetal Kusal, Shruti Patil+4 more|arXiv (Cornell University)|Apr 26, 2022

Sentiment Analysis and Opinion Mining被引用 20

一句话总结

本论文对从 2005 年到 2021 年的文本情感检测（TBED）进行了系统性文献综述，覆盖主要数据库的 63 项研究，概述了模型、数据集、应用及未来挑战。

ABSTRACT

Artificial Intelligence (AI) has been used for processing data to make decisions, interact with humans, and understand their feelings and emotions. With the advent of the internet, people share and express their thoughts on day-to-day activities and global and local events through text messaging applications. Hence, it is essential for machines to understand emotions in opinions, feedback, and textual dialogues to provide emotionally aware responses to users in today's online world. The field of text-based emotion detection (TBED) is advancing to provide automated solutions to various applications, such as businesses, and finances, to name a few. TBED has gained a lot of attention in recent times. The paper presents a systematic literature review of the existing literature published between 2005 to 2021 in TBED. This review has meticulously examined 63 research papers from IEEE, Science Direct, Scopus, and Web of Science databases to address four primary research questions. It also reviews the different applications of TBED across various research domains and highlights its use. An overview of various emotion models, techniques, feature extraction methods, datasets, and research challenges with future directions has also been represented.

研究动机与目标

• 在日益以文本为主的在线交流背景下，推动文本情感检测（TBED）的研究。
• 系统性回顾 2005–2021 年发表的 TBED 相关文献，以总结方法、数据集和应用。
• 识别研究差距与未来方向，为 TBED 研究与实践提供指导。

提出的方法

• 对 2005 年至 2021 年发表的 TBED 文献进行系统性文献综述。
• 检索 IEEE、ScienceDirect、Scopus 与 Web of Science 数据库中的 63 篇研究论文。
• 综合情感模型、特征提取方法、数据集、应用与挑战等信息。
• 突出 TBED 的未来发展方向和潜在研究优先级。

实验结果

研究问题

• RQ1 TBED 使用了哪些情感模型，它们如何影响检测性能？
• RQ2 在跨数据集的 TBED 研究中，哪些特征提取方法和建模技术占主导？
• RQ3 TBED 存在哪些数据集，它们的特征和局限性是什么？
• RQ4 TBED 的主要应用与挑战是什么，未来有哪些方向被提出？

主要发现

• 由于文本数据的增长和对具情感意识的 AI 的需求，TBED 受到显著关注。
• 综述覆盖了跨多领域的 TBED 中使用的情感模型、特征提取方法和数据集。
• TBED 的应用覆盖商业、金融和其他领域，凸显了其实践相关性。
• 本文讨论了挑战并概述了推进 TBED 研究的未来方向。