近日，实验室博士生白泽文关于方面级情感分析的研究被期刊 Knowledge-Based Systems (KBS) 录用。KBS是人工智能领域的顶级期刊之一，属于中科院一区，中国计算机学会推荐C类期刊。

题目：Intuition meets analytics: Reasoning implicit aspect-based sentiment quadruplets with a dual-system framework（直觉遇见分析：基于双系统框架推理隐式方面情感四元组）

摘要：The implicit sentiments pose a challenge to aspect sentiment quad prediction (ASQP), and replicating human cognitive processes is essential for understanding them. However, existing methods fail to model from a human cognitive perspective, leading to limited performance. Inspired by the dual-process theory in psychology, which identifies two distinct but synergistic modes of reasoning–intuitive and analytic, we present a straightforward and effective strategy-level approach: Dual System-based Reasoning framework with Intuitive Reactions (DuSR2). This framework includes the Intuitive System based on intuitive reactions and the Analytic System based on complex reasoning. Specifically, we first employ commonsense reasoning tools to estimate human intuitive reactions to enhance the original text, enriching semantic information. Then we integrate the enhanced text with analytic instruction, conducting complex reasoning to capture implicit sentiments. Experimental results show that DuSR2 significantly advances the state-of-the-art performance on four datasets of ASQP task. Detailed evaluation confirms the effectiveness, universality, and robustness of DuSR2 in handling various scenarios.

中文摘要：隐式情感对方面情感四元组预测（ASQP）任务构成挑战，模拟人类认知过程对于理解这些情感至关重要。然而，现有方法未能从人类认知视角进行建模，导致性能受限。受认知学中双系统理论的启发，该理论识别出两种截然不同但相互协作的推理模式——直觉过程和分析过程，我们提出了一种简洁而有效的策略级方法：基于双系统的直觉反应推理框架（DuSR²，Dual System-based Reasoning framework with Intuitive Reactions）。该框架包括基于直觉反应的直觉系统和基于复杂推理的分析系统。具体而言，我们首先使用常识推理工具来推理人类的直觉反应，以增强原始文本，丰富语义信息。然后，我们将增强后的文本与分析指令相结合，进行复杂推理以捕捉隐式情感。实验结果表明，DuSR² 在四个 ASQP 任务数据集上显著提升了最先进的性能。详细评估证实了 DuSR2 在处理各种场景时的有效性、通用性和鲁棒性。