PuBlicationS

University of Computer Studies, Mandalay

PUBLICATIONS

 Yu Mon Aye | Sint Sint Aung

Abstract

Nowadays, users’ desire reviews and online blogs sites to purchase the products. With the rapid grown in social networks, the online services are gradually more being used by online society to share their sight, opinion, feelings and incident about a particular product or event. Therefore, customer reviews are considered as a significant resource of information in Sentiment Analysis (SA) applications for decision making of economic. Sentiment analysis is a language processing task which is used to detect opinion articulated in online reviews to classify it into different polarity. Most of resources for sentiment analysis are built for English than other language. To overcome this problem, we propose the sentiment analysis for Myanmar language by considering intensifier and objective words to enhance sentiment classification for food and restaurant domain. This paper aims to overcome the language specific problem and to enhance the sentiment classification for informal text. We address lexicon-based sentiment analysis to enhance the sentiment analysis for Myanmar text reviews and show that the enhancement of sentiment classification improves the prediction accuracy.

Date:  13th June, 2018 16th International Conference on Software Engineering Research, Management and Applications (SERA). IEEE, 2018   | Weblink

 Yu Mon Aye | Sint Sint Aung

Abstract

Social media has just become as an influential with the rapidly growing popularity of online customers reviews available in social sites by using informal languages and emoticons. These reviews are very helpful for new customers and for decision making process. Sentiment analysis is to state the feelings, opinions about people’s reviews together with sentiment. Most of researchers applied sentiment analysis for English Language. There is no research efforts have sought to provide sentiment analysis of Myanmar text. To tackle this problem, we propose the resource of Myanmar Language for mining food and restaurants’ reviews. This paper aims to build language resource to overcome the language specific problem and opinion word extraction for Myanmar text reviews of consumers. We address dictionary based approach of lexicon-based sentiment analysis for analysis of opinion word extraction in food and restaurants domain. This research assesses the challenges and problem faced in sentiment analysis of Myanmar Language area for future.

Date:  1st May, 2018  International Journal of Advanced Engineering, Management and Science (IJAEMS) | Weblink

 Yu Mon Aye | Sint Sint Aung

Abstract

Internet users are rapid increase in online review sites. Customer’s reviews and comments on the web are an important information source. Therefore, knowing about these comments and reviews with their opinions is important for quality control to the business management. Opinions contain positive and negative opinions which containing likes and dislikes public generated content about products, services and politics. Subjectivity analysis is to state the feelings, opinions about people’s reviews together with sentiment. Most of researchers develop subjectivity and sentiment classification about English Language. There are no any resources for Myanmar language of subjectivity/ sentiment analysis. To overcome this problem, this paper proposed subjectivity/ sentiment analysis of Myanmar language for formal and informal restaurant reviews by using the lexicon based sentiment analysis. This research evaluates the challenges and language problem faced in subjectivity analysis of Myanmar text area for future.

Date:  1st November, 2018 32nd International Business Information Management Conference (IBIMA), At Seville, Spain, Volume: ISBN: 978-0-9998551-1-9 pp. 76-87 | Weblink

 Myat Su Wai | Sint Sint Aung

Abstract

Ontologies are set to play a vital role in the Semantic Web, e-Commerce, Bio-informatics, Artificial Intelligence, Natural Language Processing, and many other areas by providing a source of shared and precisely defined terms. Ontology is a formal representation of a set of concepts within a domain and the relationships between those concepts. There are several types of ontology and ontology markup languages. Domain ontologies are reusable vocabularies of the concepts within the domain and their relationships. Domain ontology may also be used to define the domain. When data is marked up using ontologies, software agents can better understand the semantics and therefore more intelligently locate and integrate data for a wide variety of tasks. Many research areas have been increased about ontology, ontology mapping and ontology markup languages. In this paper, we study on several types of ontology markup languages for building domain ontology with example domain.

Date:  5th February, 2015 13th International Conference on Computer Applications (ICCA 2015) | Weblink

 Myat Su Wai | Sint Sint Aung

Abstract

Due to the rapid expansion of the internet, business through e-commerce has become popular. Many products are being sold on the internet and the merchants selling the products ask their customers to write reviews about the products that they have purchased. Opinion mining and sentiment classification are not only technically challenging because of the need for natural language processing, but also very useful in practice. In this study, ontology based compararive sentence and relation mining for sentiment classification in mobile phone (product) reviews are studied. POS taggers are used to tag sentiment words in the input sentences. In this study, Naive Bayes classifier is also used for sentiment classification. Moreover, the comparison between with ontology and without ontology are aiso described. This study is very useful for manufacturers and customers in E-commerce Sites, Review Sites, Blog etc.

Date: 26th August, 2015 International Conference on Genetic and Evolutionary Computing,Advanced in Artificial Intelligence vol 2, ISBN 978-3-319-23207-2 (e-book), 2015, pp.439-446, Yangon, Myanmar.  | Weblink