Transformer提升情感分析准确率，却加剧了情感极化，损害商业中立性。
The Dark Side of AI Transformers: Sentiment Polarization & the Loss of Business Neutrality by NLP Transformers
- 用预训练模型提升情感分类精度，但引发另一类情感判断偏差。
- 实验显示部分情感类别准确率上升，另一类却严重失衡。
- 适合关注AI伦理与工业级应用可靠性的研究者阅读。
迁移学习与Transformer的广泛应用显著提升了复杂计算任务的准确性，尤其在情感分析领域成效明显。然而，实验发现，这些模型在提升某一类情感识别准确率的同时，导致了另一类情感判断的极端化，并破坏了原本应有的中立性。这种非中立性在依赖情感分析输出的实用自然语言处理场景中构成严重问题，影响其在产业界任务中的可靠性与可信赖度。
原文摘要 · Abstract (English)
The use of Transfer Learning & Transformers has steadily improved accuracy and has significantly contributed in solving complex computation problems. However, this transformer led accuracy improvement in Applied AI Analytics specifically in sentiment analytics comes with the dark side. It is observed during experiments that a lot of these improvements in transformer led accuracy of one class of sentiment has been at the cost of polarization of another class of sentiment and the failing of neutrality. This lack of neutrality poses an acute problem in the Applied NLP space, which relies heavily on the computational outputs of sentiment analytics for reliable industry ready tasks.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。