Abstract
Aspect-based sentiment analysis (ABSA) in Arabic must recover both explicitly stated aspects and implicit aspects that are never named in the text. Implicit identification typically relies on an auxiliary knowledge source (e.g., a knowledge graph (KG)) linking opinion cues to aspect categories. For a lower-resource language, practitioners face a design choice: reuse a mature English KG through multilingual embeddings or build a smaller native Arabic KG.
This paper reports a controlled comparison of the two strategies within a single hybrid pipeline, evaluated on three Arabic benchmarks (M-ABSA, SemEval-2016 Arabic, and HAAD). We further compare two adaptation strategies for the generative extractor that feeds the KG—zero-shot prompting versus task-specific fine-tuning of an 8B-parameter large language model (LLM).
The native Arabic KG (Strategy 2) outperforms the cross-lingual English KG (Strategy 1) by +0.199 micro-F1 on M-ABSA and +0.251 on SemEval-2016, gaining on both precision and recall. Task-specific fine-tuning raises explicit-extraction micro-F1 significantly.
Blogger's Review: This study offers crucial insights into implicit aspect identification in Arabic, highlighting the advantages of local knowledge graphs in low-resource languages, particularly in terms of precision and recall. The localized strategy demonstrates greater adaptability and effectiveness compared to relying on translated cross-lingual models, making it a valuable reference for researchers in other languages.