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, allowing both consumers and merchants to gain more efficient access to in-depth insights. 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, and Multilingual BERT (mBERT/XLM-R) to assess their performance 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.
ปัจจุบันการซื้อขายสินค้าออนไลน์เติบโตขึ้นอย่างรวดเร็ว ทำให้ข้อมูลรีวิวสินค้าจากผู้บริโภคมีปริมาณเพิ่มขึ้นเป็นจำนวนมาก รีวิวเหล่านี้มีบทบาทสำคัญในการตัดสินใจซื้อของลูกค้าและการปรับปรุงคุณภาพสินค้าของร้านค้า อย่างไรก็ตาม ปริมาณข้อมูลที่มากเกินไปและความหลากหลายของรูปแบบการแสดงความคิดเห็นทำให้การสรุปและวิเคราะห์ข้อมูลเหล่านี้เป็นไปได้ยาก ผู้บริโภคต้องใช้เวลามากในการอ่านรีวิวจำนวนมากเพื่อสรุปแนวโน้มความคิดเห็น ในขณะที่ร้านค้าประสบปัญหาในการวิเคราะห์ข้อมูลรีวิวเพื่อปรับปรุงผลิตภัณฑ์และบริการ เพื่อแก้ไขปัญหานี้ งานวิจัยนี้นำเสนอการประยุกต์ใช้ Aspect-Based Sentiment Analysis (ABSA) ซึ่งเป็นเทคนิคใน Natural Language Processing (NLP) ที่สามารถแยกแยะ แง่มุมสำคัญของรีวิวสินค้า (Aspects) และวิเคราะห์ อารมณ์ของแต่ละแง่มุม (Sentiments) โดยอัตโนมัติ การนำเทคนิคนี้มาใช้จะช่วยให้ผู้บริโภคสามารถรับข้อมูลเชิงลึกจากรีวิวได้ง่ายขึ้น และช่วยให้ร้านค้าสามารถใช้ข้อมูลรีวิวเพื่อปรับปรุงสินค้าและบริการอย่างมีประสิทธิภาพ โครงงานนี้ยังมุ่งเน้นการศึกษาว่า แนวทาง AI แบบใดมีประสิทธิภาพสูงสุดในการทำ ABSA สำหรับภาษาไทย โดยเปรียบเทียบ วิธีการประมวลผลภาษาธรรมชาติแบบดั้งเดิม กับเทคนิคการเรียนรู้เชิงลึกที่ทันสมัย เพื่อให้ได้แนวทางที่เหมาะสมที่สุด พร้อมทั้งพัฒนา Dashboard Visualization ที่ช่วยให้ข้อมูลรีวิวถูกนำเสนอในรูปแบบที่เข้าใจง่ายและสามารถนำไปใช้งานจริงในอุตสาหกรรมอีคอมเมิร์ซ
คณะเทคโนโลยีการเกษตร
Threadfin breams is an economically important fish that can be found in fisheries in both the Gulf of Thailand and Andaman Sea and is cheap. In addition, the consumption of raw fish as sashimi is increasingly popular in Thailand. Therefore, it is necessary to promote its consumption to increase its value. This study investigated the preservation of threadfin breams (N. furcosus) for raw or sashimi consumption. The preservation of threadfin breams consisted of Ikejime (K) and cold seawater (S) methods, and the preservation of the fish by Gutting (G) and whole (W) and storing for 3 days on ice (I) or in a refrigerator (F). The freshness quality of threadfin breams was evaluated by sensory, physicochemical (TVB-N, TMA-N and pH), freshness index (Ki-value) and microbiological methods. It was found that after being stored for 3 days, the KGF group of threadfin breams had the highest overall sensory score, which was 8.36±0.80 points, and the KWI, SWI and SWF groups of threadfin breams had the lowest overall sensory scores, which were 8.13±0.77, 8.13±0.77 and 8.13±0.81 points, respectively. And the overall sensory scores of all experimental groups of fish increased significantly (p<0.05). The TVB-N value of threadfin breams in KGF group had the lowest TVB-N value, which was 1.37±0.93 mg nitrogen/100 g sample. The threadfin breams in SGI group had the highest TVB-N value, which was 2.36±1.15 mg nitrogen/100 g sample. The TVB-N of fish in all experimental groups increased significantly (p<0.05). The TMA-N value of threadfin breams in KGF group had the lowest TMA-N value, which was 1.56±0.88 mg nitrogen/100 g sample. The threadfin breams in SWF group had the highest TMA-N value, which was 2.17±1.22 mg nitrogen/100 g sample. The TMA-N of fish in all experimental groups increased significantly (p<0.05). The pH value of threadfin breams in KGF group had the lowest pH value, which was 6.40±0.12. The threadfin breams in SWF group had the highest pH value, which was 6.78±0.25. The pH of fish in all experimental groups increased significantly (p<0.05). Ki value The threadfin breams in KGF group had the lowest Ki value, which was 9.05±0.73%. The threadfin breams in KWI group had the highest Ki value, which was 12.88±4.19%. The Ki value of all experimental groups of fish increased without statistical significance (p>0.05). In terms of freshness quality in microbiology, it was found that in all experimental groups, Salmonella spp., S. aureus, B. cereus, C. perfringens and E. coli were found in all experimental groups of threadfin breams. All types of microorganisms in all groups of threadfin breams increased with statistical significance (p<0.05). When compared with the freshness quality criteria in terms of sensory, chemical, physical, freshness index and microbiology, it was found that all groups of threadfin breams were very fresh and suitable for raw consumption during the preservation and storage for 3 days. After 3 days of storage, the threadfin breams should be consumed cooked because the freshness quality of the fish is not suitable for raw consumption due to the increase in various parameters. The increase in various parameters is due to the deterioration of the fish and the activities of microorganisms. Therefore, threadfin breams is suitable to promote raw consumption within 3 days of storage. In addition, fish preservation, especially by Ikejime method, then cutting open the belly and storing in the refrigerator, can help improve the freshness of the fish. The results of this study can be used to develop techniques for preserving fish after capture for fishermen and can promote the increase in the value of threadfin breams in the future.
คณะบริหารธุรกิจ
This book introduces basic management concepts that are applicable to technological innovation development. It encompasses various tech settings like Agro & Health tech, in addition to the more commonly referred digital sector.
คณะวิศวกรรมศาสตร์
This research suggested natural hemp fiber-reinforced ropes (FRR) polymer usage to reinforce recycled aggregate square concrete columns that contain fired-clay solid brick aggregates in order to reduce the high costs associated with synthetic fiber-reinforced polymers (FRPs). A total of 24 square columns of concrete were fabricated to conduct this study. The samples were tested under a monotonic axial compression load. The variables of interest were the strength of unconfined concrete and the number of FRRlayers. According to the results, the strengthened specimens demonstrated an increased compressive strength and ductility. Notably, the specimens with the smallest unconfined strength demonstrated the largest improvement in compressive strength and ductility. Particularly, the compressive strength and strain were enhanced by up to 181% and 564%, respectively. In order to predict the ultimate confined compressive stress and strain, this study investigated a number of analytical stress–strain models. A comparison of experimental and theoretical findings deduced that only a limited number of strength models resulted in close predictions, whereas an even larger scatter was observed for strain prediction. Machine learning was employed by using neural networks to predict the compressive strength. A dataset comprising 142 specimens strengthened with hemp FRP was extracted from the literature. The neural network was trained on the extracted dataset, and its performance was evaluated for the experimental results of this study, which demonstrated a close agreement.