Papers › RVISA: Reasoning and Verification for Implicit Sentiment Analysis

RVISA: Reasoning and Verification for Implicit Sentiment Analysis

2 Jul 2024arXiv:2407.02340archive 2025-07-28

Wenna Lai, Haoran Xie, Guandong Xu, Qing Li

With an increasing social demand for fine-grained sentiment analysis (SA), implicit sentiment analysis (ISA) poses a significant challenge with the absence of salient cue words in expressions. It necessitates reliable reasoning to understand how the sentiment is aroused and thus determine implicit sentiments. In the era of Large Language Models (LLMs), Encoder-Decoder (ED) LLMs have gained popularity to serve as backbone models for SA applications, considering impressive text comprehension and reasoning ability among diverse tasks. On the other hand, Decoder-only (DO) LLMs exhibit superior natural language generation and in-context learning capabilities. However, their responses may contain misleading or inaccurate information. To identify implicit sentiment with reliable reasoning, this study proposes RVISA, a two-stage reasoning framework that harnesses the generation ability of DO LLMs and the reasoning ability of ED LLMs to train an enhanced reasoner. Specifically, we adopt three-hop reasoning prompting to explicitly furnish sentiment elements as cues. The generated rationales are utilized to fine-tune an ED LLM into a skilled reasoner. Additionally, we develop a straightforward yet effective verification mechanism to ensure the reliability of the reasoning learning. We evaluated the proposed method on two benchmark datasets and achieved state-of-the-art results in ISA performance.

PaperPDF

Code

No code repository is listed for this paper in the archive or in Syntology's graph.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Aspect-Based Sentiment AnalysisAspect-Based Sentiment Analysis (ABSA)DecoderIn-Context LearningReading ComprehensionSentiment AnalysisText Generation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Aspect-Based Sentiment Analysis (ABSA) SemEval-2014 Task-4 RVISA Laptop (Acc) 86.68 #2 of 48 Archive leaderboard report
Aspect-Based Sentiment Analysis (ABSA) SemEval-2014 Task-4 RVISA Mean Acc (Restaurant + Laptop) 89.10 #2 of 48 Archive leaderboard report
Aspect-Based Sentiment Analysis (ABSA) SemEval-2014 Task-4 RVISA Restaurant (Acc) 91.52 #2 of 48 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections