Innovation Owner
Mr. PONGSAKORN SAKSAKULCHAI
Student
Details
This research presents an Aspect-Based Sentiment Analysis (ABSA) system for e-commerce reviews, utilizing WangchanBERTa to identify key aspects and sentiments. The project compares various AI models to provide actionable insights via a dashboard for consumers and merchants.
In today’s rapidly expanding e-commerce environment, the massive volume of product reviews makes it crucial to summarize user opinions in a way that is both comprehensible and practically applicable. This research presents a system for analyzing product reviews using Aspect-Based Sentiment Analysis (ABSA), a Natural Language Processing (NLP) technique that identifies key aspects of a review (such as shipping, product quality, and packaging) and evaluates the sentiment (positive, negative, or neutral) associated with each aspect.
This project focuses on developing AI for Thai-language ABSA by utilizing WangchanBERTa, a model trained on Thai data, and comparing it with various standard approaches such as:
- TF-IDF + Logistic Regression
- Word2Vec + BiLSTM
- Multilingual BERT (mBERT/XLM-R)
These are evaluated in terms of accuracy, speed, and resource usage. Additionally, a dashboard visualization is provided to help users quickly grasp review trends. The expected outcome is to create an AI tool that can be practically employed in the e-commerce industry, enabling consumers to make easier purchasing decisions and assisting merchants in effectively improving their products and services.
Objective
The objectives include developing a Thai-language ABSA system, comparing AI model performance, creating an intuitive dashboard, and fostering research to enhance e-commerce competitiveness.
- To develop a product review analysis system using Aspect-Based Sentiment Analysis (ABSA) techniques that can accurately summarize opinions on various product aspects in the Thai language context.
- To compare the performance between traditional Natural Language Processing approaches and Deep Learning techniques for Thai ABSA.
- To design and develop a Dashboard Visualization for summarizing analysis results in an intuitive format, applicable for decision-making in the e-commerce industry.
- To generate knowledge and resources that support further research in Thai AI and NLP, both academically and commercially.
- To support consumers in making better purchasing decisions and assist entrepreneurs in improving products and services, ultimately enhancing the competitiveness of the e-commerce industry.