APPLYING MACHINE LEARNING TO CLASSIFY SENTIMENT TEXT FOR VIETNAMESE LANGUAGE ON SOCIAL NETWORK DATA

Hoanh-Su Le,Jong-Hwa Lee,Hyun-Kyu Lee 한국경영정보학회 2015 한국경영정보학회 학술대회논문집 Vol.2015 No.11

Since the government issued ICT priority policy for the last decade, Vietnam was reported to have impressed development of ICT infrastructure and Internet users. Until May of 2015, Vietnam has 39.7 millions of Internet users and 31 millions of social network user accounts. Facebook is the dominant website with more than 22 million Vietnamese users and 70% of those accesses Facebook via mobile phone. Several companies have utilized Facebook as the most effective interaction channels. The increasing of big text data such as posts and comments on Facebook that embed customer opinions requires method to mine sentiment text in Vietnamese language. This research applies machine learning with several algorithms such Naive-Bayes, decision trees and Support Vector Machine (SVM) for Vietnamese text data collected from fast-food industry on Facebook. The experiment results show that machine learning methods are able to classify Vietnamese sentiment text with the accuracy over 70%. Thus we proposed several recommendations for mining Vietnamese social text data.

Design Hybrid Models for Opinion Mining on Vietnamese Social Media Text Data

Hoanh-Su Le,Jong-Hwa Lee,Hyun-Kyu Lee 한국인터넷전자상거래학회 2016 인터넷전자상거래연구 Vol.16 No.2

The rapid development of information communications technology, especially Internet and smartphones, helps customers be more flexible and easier to access social networking sites and use them as effective communication tools. A huge number of informal messages are posted every day in social networking sites including comments, opinions and feedbacks about products, services or companies. These text data are not only in English but also in several other languages as the social networking sites develop across countries. It has become difficult and time consuming for individuals or organizations to effectively process the information underlined in these text data. Thanks to the development of opinion mining techniques, social media text data can be mined to explore customer opinions about products, services as well as information about competitors. This paper proposed models for opinion mining on Vietnamese social media text data. We collected social media text data from Facebook in Vietnam and designed a non-standard Vietnamese words dictionary to process informal Vietnamese text messages. We compared predictive performance of several opinion mining models in lexicon-based and machine learning approach and then proposed a hybrid model that combines the two approaches. The results show that using non-standard Vietnamese words dictionary improves predictive performance of opinion mining models, and hybrid models of lexicon-based and machine learning approach have better performance than single models. Based on this research outcomes, we provided recommendations in designing opinion mining models on non-English social media text data.

Exploring Current Research Topics and Trends based on the Keywords Analysis in the Leading Information Systems Journals

Hoanh-Su Le,Jong-Hwa Lee,Hyun-Kyu Lee 한국인터넷전자상거래학회 2014 인터넷전자상거래연구 Vol.14 No.2

The objective of this article is to explore research topics and trends by analyzing keywords used in the top Information Systems Leading Journals. Keywords used in 2180 research articles from the top 8 IS journals during 2009 to 2013 were collected with article subject, abstract, year of publication and Journal name. The collected keywords were refined from errors in spelling, inconsistences in abbreviations, compounding of words and word redundancy, then 11,815 keywords(and their occurrences) were input to frequencies analysis, word cloud analysis and cluster analysis. A list of the most frequently used keywords such as "electronic commerce", "pricing", "trust", "innovation", "game theory", etc., and their variability year by year and across journals are identified. In addition, "social" and "network" as separate words are seen frequently in recent years and some keywords are clustered together in a pattern. Based on these results, recent research trends and future research topics were discussed and recommended.

Motivations Triggering Electronic Word of Mouth Intention: A Study for E-Learning Websites at Vietnam

Su Le Hoanh,Tuan Nguyen Manh,이현규 한국경영교육학회 2014 경영교육연구 Vol.29 No.1

The primary objectives of this study are to identify the motivations triggering electronic word of mouth (eWOM) intention on E-learning websites in Vietnam, measure the level of influence of each motivation affecting eWOM intention, and show the differences in motivations of users based on demographic characteristics. The research was conducted through two steps, the preliminary and the main one. Preliminary study was done by qualitative exploratory methods. The results showed that the motivations triggering eWOM intention include: reputation, rewards, sense of belonging, enjoyment of helping and perceived of behavioral control. Official research was used by questionnaire survey with 334 samples collected. Data is used to assess the scales’ reliability and validity with Cronbach's alpha analysis, exploratory factor analysis, correlation and multiple regression analysis to test the hypotheses. The results showed that the motivations triggering eWOM intention include: reputation, rewards and sense of belonging. And the sense of belonging has the highest impact on eWOM intention. Research results help administrators of E-learning websites better understand the motivations triggering eWOM intention. Since then, they might have the direction to design website functionalities and terms of use to promote the active participation in eWOM. In addition, the findings also contribute to the additional theoretical basis of motivations triggering eWOM and measurement scales.

Development of an AI Chatbot to Support Admissions and Career Guidance for Universities

Le Hoanh Su,Truong Dang-Huy,Tran Thi-Yen-Linh,Nguyen Thi-Duyen-Ngoc,Ly Bao-Tuyen,Nguyen Ha-Phuong-Truc ASCONS 2020 INTERNATIONAL JOURNAL OF EMERGING MULTIDISCIPLINAR Vol.4 No.2

The vocational guidance and advising education enrollment are one of the most important tasks in the enrollment process and promote the quality and reputation of the University. Admissions counseling offices at Universities and Colleges play a major role in vocational guidance and advising education enrollment. However, the support of these units is limited by office hours, speed and advisory efficiency, and besides, handling and answering questions process may also encounter obstacles such as: overload, misinformation, problem with the transmission, language barriers, expressions, limited time, support resources,… Thus we decided to do research to understand this situation. Then creating a dataset supports vocational guidance and advising education enrollment activities. We also design and integrate chatbot into the school system to support the admissions counseling process.

Designing an integrated text mining framework for evaluating cross-cultural and multi-lingual customer responses in social network marketing

Hoanh-Su Le,Jong-Hwa Lee,Hyun-Kyu Lee 한국경영학회 2015 한국경영학회 통합학술발표논문집 Vol.2015 No.08

The rapid growth of users in social networking services has urged many businesses to adopt and use social networking sites as the most effective tools for marketing. As a result, a big data of user-generated content in such social networking sites is available to every company in several countries and languages. This opens opportunities for international enterprises to evaluate customer responses cross cultures by performing quantitative data and multi-linguistic text mining. This article proposed a text mining framework on social network data to evaluate customer responses and explore customer opinions across cultures. We collected 38,539 posts and 613,873 comments in textual form, and their quantitative data such as number of posts, likes, shares and links on fanpages of Starbucks in United States, South Korea, Singapore and Vietnam. Then we designed a framework to perform text mining in English, Korean and Vietnamese languages for the posts and comments. The results showed that enterprises can extract business value and evaluate customer responses across cultures through mining social network data. Based on this study, we provided recommendations to help enterprises tailor their social network marketing strategy across cultures.

Applying Artificial Neural Network for Sentiment Analytics of Social Media Text Data in fastfood industry

Hoanh Su Le,Cuong Trieu,Thanh Ho,Jong-Hwa Lee,Hyun-Kyu Lee 한국인터넷전자상거래학회 2017 인터넷전자상거래연구 Vol.17 No.5

The increasing of users in social networking services in Vietnam help companies have better communication channels with customers. Nowadays, any companies can easily invest tools and human to monitor and harvest customer-generated contents not only about their own brands but also about their competitive brands on social media sites. In order utilize the value in the harvested data, certain analytic techniques are required. This paper proposed a method to apply mining social media data in the context of fastfood brands. We collected data from top fastfood chains including Lotteria, MacDonald, KFC, Vietnam Pizza Hut and Pepperonis Vietnam and applied machine learning to classify the sentiment of informal text data. The results show that applying neural network machine learning in sentiment analytics of social media text data is suitable for sentiment analytics and applicable for future data prediction in fastfood industry.

Analyzing Visitors’ Preferences on Tourism Accommodation Services by Opinion Mining

Hoanh-Su Le,Jong-Hwa Lee,Hyun-Kyu Lee 한국인터넷전자상거래학회 2017 인터넷전자상거래연구 Vol.17 No.2

Tourism is considered as one of the most important industries in Vietnam. The Government continuously keeps managing and asking for improving all sectors related to tourism. As an important infrastructure for tourism industries, hotels are highly considered for improving customer services. On hotel booking and reviews channels, customers express their opinions and feedback about their experienced hotels by writing online reviews, this is valuable source of information that hotel managers should utilize. In this study, we collected 22,383 online reviews about Vietnamese hotels written by foreign customers in English. Then we developed a hybrid model to perform opinion mining on social media text and explore for customer opinion. The results show that opinion mining on customers reviews can show services preferences on hotel services. Based on this result we recommend for improving customer satisfactions via diversifying across cultures services.

HOTEL SERVICES PREFERENCES ACROSS CULTURES : A CASE STUDY OF APPLYING OPINION MINING ON VIETNAMESE AND AMERICAN ONLINE REVIEWS

Hoanh-Su Le,Jong-Hwa Lee,Hyun-Kyu Lee 한국경영정보학회 2016 한국경영정보학회 학술대회논문집 Vol.2016 No.6

A research on students’ readiness for Education 4.0 program

Le Hoanh Su,Nguyen Thi Hong Linh,Vo Dang Hong Ngan,Le Kieu Oanh,Nguyen Ngoc Thanh,Tran Vuong Bao Tran ASCONS 2020 INTERNATIONAL JOURNAL OF EMERGING MULTIDISCIPLINAR Vol.4 No.1

Nowadays, in Vietnam, the government tends to have a great concern to the 4th Industrial Revolution, and Education 4.0 is also a matter to be paid attention to. In order to implement Education 4.0, besides technology and social, people are an important factor involved in the development of the education 4.0. The purpose of the study is to find out the factors affecting student readiness for education 4.0. The proposed model consists of 8 independent factors: Internet self-efficacy, Online communication self-efficacy, Self-regulation, Creativity, Self-discovery, Upgrade, Collaboration, Attitude and 1 dependent factor namely Readiness. Based on 361 samples, this quantitative research was conducted: reliability testing, exploratory factor analysis, correlation coefficients and linear regression. The result shows that there are four key factors affecting readiness including Self-regulation, Creativity, Upgrade and Attitude. The result of t-test shows that the group of students who had experienced online learning had higher readiness for the education 4.0 than the others.