Aspect Extraction from E-Commerce Product and Service Reviews
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866909981275586560 |
|---|---|
| author | Dionela, Valiant Lance D. Dy, Fatima Kriselle S. Hombrebueno, Robin James M. Nicolas, Aaron Rae M. Cheng, Charibeth K. Gonda, Raphael W. |
| author_facet | Dionela, Valiant Lance D. Dy, Fatima Kriselle S. Hombrebueno, Robin James M. Nicolas, Aaron Rae M. Cheng, Charibeth K. Gonda, Raphael W. |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_01827 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Aspect Extraction from E-Commerce Product and Service Reviews Dionela, Valiant Lance D. Dy, Fatima Kriselle S. Hombrebueno, Robin James M. Nicolas, Aaron Rae M. Cheng, Charibeth K. Gonda, Raphael W. Computation and Language Machine Learning 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. |
| title | Aspect Extraction from E-Commerce Product and Service Reviews |
| topic | Computation and Language Machine Learning |
| url | https://arxiv.org/abs/2601.01827 |