Intuition meets analytics: Reasoning implicit aspect-based sentiment quadruplets with a dual-system framework

Abstract

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.