Applying Sentiment Product Reviews and Visualization for BI Systems in Vietnamese E-Commerce Website: Focusing on Vietnamese Context

Abstract

Product reviews become more important in the buying decision-making process of customers. Exploiting and analyzing customer product reviews in sentiments also become an advantage for businesses and researchers in e-commerce platforms. This study proposes a sentiment evaluation model of customer reviews by extracting objects, emotional words for emotional level analysis, using machine learning algorithms. The research object is the Vietnamese language, which has special semantic structures and characteristics. In this research model, emotional dictionaries and sets of extract rules are combined to build a data training data set based on the semantic dependency relationship between words in sentences of the given Vietnamese context. The recurrent neural network model (RNN) solves the emotional analysis issue, specifically, the long short-term memory neural network (LSTMs). This analysis model combines the vector representations of words with a continuous bag-of-words (CBOW) architecture. Our system is designed to crawl realistic data in an e-commerce website and automatically aggregate them. These data will be stored in MongoDB before processing and input into our model on the server. Then, the system can exploit the features in products reviews and classify customer reviews. These features extracted from different feedback on each shopping step and depending on the kinds of products. Finally, there is a web-app to connect to a server and visualize all the research results. Based on the research results, enterprises can follow up their customers in real-time and receive recommendations to understand their customers. From there, they can improve their services and provide sustainable consumer service.

Exploring consumer opinions on vegetarian food by sentiment analysis method

“…Wang, Pan, Dahlmeier, and Xiao (2016) 2018) used a sequencelabeling approach in conjunction with Bidirectional Recurrent Neural Networks (BRNN) and Conditional Random Fields (CRF) to extract opinion targets and assess their sentiment simultaneously so as to analyze smartphone reviews on YouTube and e-commerce. Le and Huh (2021) utilized customer reviews on Tiki with various products and services to solve the emotional analysis issue through a deep learning method with long short-term memory neural network LSTM (belong to RNN), combined with CBOW, and TF-IDF techniques.…”

“…Furthermore, Kotler's model contains five stages of the buying decision process which also showed some essential factors like appearance, price, brand, quality, and social media review (Kotler, 2000). In addition, the previous studies involving e-commerce field extracted aspects such as price (cost), quality, satisfy, shipment, design, package, fragrance, and so on (Clara, Adiwijaya, & Purbolaksono, 2020;Le & Huh, 2021;Nandal et al, 2020). Based-on the previous studies, this study continued surveying vagan food and identified food's features as well as customers' behavior relevant to the dataset to propose the five aspects for the model.…”

“…In order to have input data into the system, the authors need to build a list of lexicons for the dataset from sources. The vocabularies are based on some research such as (Dang et al, 2018;Le & Huh, 2021;Nguyen & Duong, 2019;Vu et al, 2012). Besides, for these descriptions of products, the authors identify the feature word and put them in the dictionary list.…”

“…Some previous research explored customer sentiment in regard to aspects of type products, such as accessories and cell phones with some aspects of battery, body, display, price, network, service, sound (Anoop & Asharaf, 2020); entertainment with two groups of display and buggy functionality & performance (Alqaryouti, Siyam, Monem, & Shaalan, 2020); drug with aspects of effectiveness and side effects (Han, Liu, & Jing, 2020). Other previous studies compiled feedback on aspects of both the product and the service, for instance, restaurant with aspects of ambiance, experience, location, person, price, restaurant, service, style options, and sustenance (de Kok et al, 2018); fashion, toy, book, laptop, voucher, and so on with aspects of quality, shipment, price, design and satisfy (Le & Huh, 2021;B. Nguyen et al, 2021).…”

Word Sense Disambiguation Using Prior Probability Estimation Based on the Korean WordNet

“…In particular, Korean lacks language resources such as machine-readable dictionaries and sense-tagged corpora, compared with English. Therefore, in order to overcome the limitations of these linguistic resources in minority languages such as Korean and Vietnamese, it is urgent to study a method for clarification of vocabulary [5].…”