Researcher Database

（Last updated : 2022-02-02 12:39:21）　

Visruth.jpg not found

KOVACS MATE

Department / Course College of Information Science and Engineering Department of Information Science and Engineering

Title / Position Assistant Professor

Academic background
1.	2018/04～2021/03	Doctoral Program (2nd Semester) │ Advanced Information Science and Engineering program │ Graduate School of Information Science and Engineering │ Ritsumeikan University │ Completed │ Doctor of Engineering
2.	2016/04～2018/03	Doctoral Program (1st Semester) │ Computer Science course │ Graduate School of Information Science and Engineering │ Ritsumeikan University │ Completed │ Master of Engineering
3.	2014/10～2016/03	MEXT Scholarship research program (Japanese studies) │ Center for Japanese Language and Culture │ Osaka University │ Graduated
4.	2011/10～2012/10	MEXT Scholarship program (Japanese language and culture) │ Center for Japanese Language and Culture │ Osaka University │ Graduated
5.	2009/09～2013/07	Japanese studies │ Oriental Languages and Cultures - Japanese Studies │ Karoli Gaspar University of the Reformed Church │ Graduated │ Bachelor's Degree in Japanese studies

Business career
1.	2021/04/01 ～	Starting Assistant Professor │ College of Information Science and Engineering │ Ritsumeikan University
2.	2020/04 ～ 2020/08	Academic Tutor │ College of Global Liberal Arts │ Ritsumeikan University
3.	2018/12 ～ 2019/04	Research Assistant │ Graduate School of Information Science and Engineering │ Ritsumeikan University
4.	2018/04 ～ 2021/02	Teaching Assistant │ College of Information Science and Engineering │ Ritsumeikan University
5.	2014/05 ～ 2014/09	Sales Executive │ │ JTB Corp.
Display All（7）

Qualification and license
1.	2012	JLPT N1
2.	2012	Kanji Kentei Level 2

Subject of research
1.	Development of a mathematical model of online review quality for machine learning systems
2.	Towards a Model of Online Petition Signing Dynamics in Taiwan

Research summary
Online reviews available on e-commerce websites influence the purchase decision-making process of customers, and companies often rely on this form of user-generated content to attract new customers and improve user experience. As the number of reviews increases over time, however, both the companies and the customers face an information overload, while the value of reviews depreciates. Therefore, e-commerce companies require systems to be developed to automatically assess the quality of reviews, and to identify relevant content. The goal of the research is to develop a mathematical model of online review quality, and to build a deep learning system based on the model, that would efficiently quantify the quality of reviews. The study would contribute to the fields of Data quality assessment and Customer need research, while its results would have an impact on the design and development of deep learning systems for customer-driven product innovation.

Present specialized field
Information Science, Computer Science (Keyword：data quality, deep learning, natural language processing, data mining)

Papers
1.	2021/12/07	An Unsupervised Approach for Customer Need Assessment in E-commerce: A Case Study of Japanese Customer Reviews │
2.	2021/09/13	Towards a Model of Online Petition Signing Dynamics on the Join Platform in Taiwan │
3.	2021	A Machine Learning Approach to Analyze Fashion Styles from Large Collections of Online Customer Reviews │ 2021 6th International Conference on Business and Industrial Research (ICBIR) IEEE Proceedings │ ,pp.153--158
4.	2020	Assessing Customer Needs Based on Online Reviews: A Topic Modeling Approach │ CEUR Proceedings of the 5th International Workshop on Innovations in Information and Communication Science and Technology │ ,pp.57--62
5.	2020	Expanding the Feature Space of Deep Neural Networks for Sentiment Classification │ International Journal of Machine Learning and Computing │ 10 (2),pp.271--276
Display All（10）

Academic conference presentation
1.	2021/09	An Unsupervised Approach for Customer Need Assessment in E-commerce: A Case Study of Japanese Customer Reviews
2.	2019	Expanding the Feature Space of Deep Neural Networks for Sentiment Classification
3.	2019	Latent variable-based multiple instance learning towards label-free polarity detection
4.	2019	Towards Assessing Online Customer Reviews from the Product Designer’s Viewpoint
5.	2019	We Know What You Will Do Next Summer: A Deep Learning Approach to Predict Internet Voting With Electoral Register Data
Display All（6）

Winning science prize
1.	2019	ICISS 2019 Committee Best Presentation Award at the International Conference on Information Science and System 2019
2.	2018	ICKE 2018 Committee Best Presentation Award at the International Conference on Knowledge Engineering 2018

Home Page
e-Society Laboratory

E-Mail Address

External Researcher ID
ORCID ID
0000-0001-5999-8061