arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2502.07541cs.CL
收藏

检测绿色洗脑:一种自然语言处理文献综述

Detecting Greenwashing: A Natural Language Processing Literature Survey

LIX, CNRS, Inria, École polytechnique(LIX、CNRS、Inria、巴黎高等学院);Institut Polytechnique de Paris(巴黎高等理工学院)

Tom Calamai, Oana Balalau, Théo Le Guenedal, Fabian M. Suchanek

AI总结:

本文综述了NLP在检测绿色洗脑中的应用,指出当前方法在数据标注和模型设计上的不足,提出需结合可靠标注与可解释模型以提升检测效果。

摘要:

绿色洗脑指的是企业或政府故意误导公众对其环境影响的实践。本文提供了一种全面且方法学严谨的自然语言处理(NLP)方法论综述,用于检测文本数据中的绿色洗脑,重点关注企业气候沟通。我们不将绿色洗脑视为单一任务,而是考察研究人员所使用的NLP问题集,即所谓的气候NLP任务,从气候话题检测到识别欺骗性沟通模式。我们的关注点是这些方法的理论基础:任务是如何制定的,数据集是如何构建的,以及模型评估如何影响可靠性。我们的综述揭示了一幅碎片化的图景:几个子任务在受控环境下表现出近乎完美的性能,但涉及模糊性、主观性或推理的任务仍具挑战性。关键的是,目前尚不存在经过验证的绿色洗脑案例数据集。我们主张,推进自动绿色洗脑检测需要结合可靠数据标注和可解释模型设计的原则性NLP方法。未来的工作应利用第三方判断,如经过验证的媒体报道或监管记录,以减轻标注主观性和法律风险,并采用分解的流程来支持人类监督、可追溯推理和高效的模型设计。

英文摘要:

Greenwashing refers to practices by corporations or governments that intentionally mislead the public about their environmental impact. This paper provides a comprehensive and methodologically grounded survey of natural language processing (NLP) approaches for detecting greenwashing in textual data, with a focus on corporate climate communication. Rather than treating greenwashing as a single, monolithic task, we examine the set of NLP problems, also known as climate NLP tasks, that researchers have used to approximate it, ranging from climate topic detection to the identification of deceptive communication patterns. Our focus is on the methodological foundations of these approaches: how tasks are formulated, how datasets are constructed, and how model evaluation influences reliability. Our review reveals a fragmented landscape: several subtasks now exhibit near-perfect performance under controlled settings, yet tasks involving ambiguity, subjectivity, or reasoning remain challenging. Crucially, no dataset of verified greenwashing cases currently exists. We argue that advancing automated greenwashing detection requires principled NLP methodologies that combine reliable data annotations with interpretable model design. Future work should leverage third-party judgments, such as verified media reports or regulatory records, to mitigate annotation subjectivity and legal risk, and adopt decomposed pipelines that support human oversight, traceable reasoning, and efficient model design.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑