Aspect Extraction (AE) is a key task in Aspect-Based Sentiment Analysis (ABSA), yet it remains difficult to apply in low-resource and code-switched contexts like Taglish, a mix of Tagalog and English commonly used in Filipino e-commerce reviews. This paper introduces a comprehensive AE pipeline designed for Taglish, combining rule-based, large language model (LLM)-based, and fine-tuning techniques to address both aspect identification and extraction. A Hierarchical Aspect Framework (HAF) is developed through multi-method topic modeling, along with a dual-mode tagging scheme for explicit and implicit aspects. For aspect identification, four distinct models are evaluated: a Rule-Based system, a Generative LLM (Gemini 2.0 Flash), and two Fine-Tuned Gemma-3 1B models trained on different datasets (Rule-Based vs. LLM-Annotated). Results indicate that the Generative LLM achieved the highest performance across all tasks (Macro F1 0.91), demonstrating superior capability in handling implicit aspects. In contrast, the fine-tuned models exhibited limited performance due to dataset imbalance and architectural capacity constraints. This work contributes a scalable and linguistically adaptive framework for enhancing ABSA in diverse, code-switched environments.

翻译：方面提取（Aspect Extraction, AE）是基于方面的情感分析（Aspect-Based Sentiment Analysis, ABSA）中的一项关键任务，但在低资源与语码转换（如塔加洛语与英语混合的Taglish，常见于菲律宾电子商务评论）的语境中，其应用仍具挑战性。本文提出一个专为Taglish设计的综合性AE流程，结合了基于规则、基于大语言模型（LLM）以及微调技术，以同时处理方面识别与提取任务。通过多方法主题建模，开发了一个层次化方面框架（Hierarchical Aspect Framework, HAF），并设计了一种用于显性与隐性方面的双模式标注方案。在方面识别任务中，评估了四种不同的模型：一个基于规则的系统、一个生成式LLM（Gemini 2.0 Flash），以及两个在不同数据集（基于规则标注与LLM标注）上微调的Gemma-3 1B模型。结果表明，生成式LLM在所有任务中均取得了最佳性能（宏平均F1值0.91），在处理隐性方面表现出卓越能力。相比之下，微调模型由于数据集不平衡与架构容量限制，性能表现有限。本研究为在多样化、语码转换环境中增强ABSA提供了一个可扩展且语言自适应的框架。