重新思考立场检测：基于理论指导的语言模型用户级推断研究议程
Rethinking stance detection: A theoretically-informed research agenda for user-level inference using language models
AI总结：
本文指出立场检测缺乏理论概念化和用户级分析，提出利用大语言模型灵活推断用户心理属性并纳入建模，最终给出四点研究议程以推动理论化、包容且实用的立场检测研究。
摘要：
立场检测已成为自然语言处理研究中的一项热门任务，这在很大程度上得益于大量针对特定目标的社交媒体数据。尽管在立场检测模型、数据集和应用方面已有大量研究，但我们强调了两个重要空白：(i) 缺乏对立场的理论概念化，以及 (ii) 立场在个体或用户层面的处理方式，而非消息层面。在本文中，我们首先回顾了立场作为个体层面构念的跨学科起源，以突出可能有助于纳入立场检测模型的相关属性（例如心理特征）。此外，我们认为最近的预训练语言模型和大语言模型（LLMs）可能提供一种灵活推断此类用户层面属性和/或将其纳入立场建模的方法。为了更好地说明这一点，我们简要回顾并综合了关于使用LLMs推断立场的新兴研究语料，特别是关于在此类任务中纳入用户属性的研究。最后，我们提出了一个四点议程，以推进具有理论依据、包容性和实际影响力的立场检测研究。
英文摘要：
Stance detection has emerged as a popular task in natural language processing research, enabled largely by the abundance of target-specific social media data. While there has been considerable research on the development of stance detection models, datasets, and application, we highlight important gaps pertaining to (i) a lack of theoretical conceptualization of stance, and (ii) the treatment of stance at an individual- or user-level, as opposed to message-level. In this paper, we first review the interdisciplinary origins of stance as an individual-level construct to highlight relevant attributes (e.g., psychological features) that might be useful to incorporate in stance detection models. Further, we argue that recent pre-trained and large language models (LLMs) might offer a way to flexibly infer such user-level attributes and/or incorporate them in modelling stance. To better illustrate this, we briefly review and synthesize the emerging corpus of studies on using LLMs for inferring stance, and specifically on incorporating user attributes in such tasks. We conclude by proposing a four-point agenda for pursuing stance detection research that is theoretically informed, inclusive, and practically impactful.
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。
