From Context to Aspects: LLM Based Implicit Aspect Extraction with Paraphrased Input and Knowledge Graph Support

While aspect-based sentiment analysis (ABSA) has gained significant progress in the identification of explicit opinion targets, the more challenging case, implicit aspects, has not been sufficiently studied. Implicit aspect extraction is particularly challenging as it relies on contextual and semantic cues and requires systems to infer what reviewers mean rather than just say. In this paper, we propose a four-component hybrid solution for explicit and implicit aspect extraction that formulates aspect extraction as a controlled text generation task. The solution combines: (i) a fine-tuned decoder-only large language model as a generative baseline, (ii) an iterative residual generation strategy that recovers multiple aspects through successive regeneration passes, (iii) paraphrase-based input transformation to broaden the contextual signal, and (iv) domain-specific knowledge graphs activated by linguistic signals to infer implicit aspects. The novelty is not in the individual components themselves, but in the principled orchestration of these components and the gating logic for when each stage is activated. Extensive experiments are conducted on eight benchmark ABSA datasets in both English and Arabic including SemEval 2014, 2015, 2016, ACOS and M-ABSA for English and SemEval 2016, HAAD, and M-ABSA for Arabic. The proposed solution consistently outperforms strong baseline methods and recent state-of-the-art models on English datasets with F1-scores of 0.8533, 0.713, 0.7859, 0.793 and 0.664 respectively, and F1-scores of 0.7336, 0.4765 and 0.7601 on Arabic datasets respectively. These results demonstrate the effectiveness of generative modeling, iterative generation, paraphrasing and structured knowledge for aspect extraction, and the potential of the proposed approach for implicit aspect identification in particular for morphologically rich and low-resource languages such as Arabic.