Kyushu University Academic Staff Educational and Research Activities Database
Researcher information (To researchers) Need Help? How to update
Taketoshi Ushiama Last modified date:2023.11.27

Associate Professor / Media Eng.
Department of Media Design
Faculty of Design

Graduate School
Undergraduate School
Other Organization

E-Mail *Since the e-mail address is not displayed in Internet Explorer, please use another web browser:Google Chrome, safari.
 Reseacher Profiling Tool Kyushu University Pure
Academic Degree
Ph.D (Eng.)
Country of degree conferring institution (Overseas)
Field of Specialization
Environment Design, Web Informatics
Total Priod of education and research career in the foreign country
Outline Activities
Dr. Ushiama conducts research on digital content environment design for effective utilization of the large amount of digital content that exists on the Internet. In particular, he conducts research on information retrieval, information recommendation, and automatic content generation and editing using AI, machine learning, and web technologies. In terms of education, he teaches lectures and exercises on a wide range of areas related to the latest cyberspace design and information technology.
Research Interests
  • Interactive viewing support using generative AI
    keyword : Generative AI, Interactive viewing
  • Interactive educational environment using generative AI
    keyword : Generative AI, interactive agents
  • Automatic generation of illustrations for novels using generative AI
    keyword : Generated AI, illustrations
  • Improving the music listening experience for subscription services
    keyword : subscription services, Music Experience, Music Recommendation
  • Explainable recommendations and supporting users
    keyword : XAI, recommender system
  • Development of recommendation method based on empathy
    keyword : empathy, recommendation
  • Product selection support using online reviews
    keyword : Online review
  • Workout support using video
    keyword : video, workout, AI
  • Automatic generation of catch copy with AI
    keyword : AI, generation, catch copy, GAN
  • Automatic generation of advertisement images with AI
    keyword : AI, generation, image, GAN
  • Viewing support based on status estimation of sports using SNS
    keyword : SNS, Live Tweet
  • A Study on automatic generation of infographics from cooking recipes
    keyword : recipe, infographics
  • A study of IoT devices working with recipies
    keyword : IoT
  • A study of recommender system on interactive systems
    keyword : Recommender system, interactive system, time series data
  • Study on tweet filtering based on impression estimation by reader
    keyword : Impression estimation, Twitter, data mining
  • A study on extraction of response patterns of viewers of TV dramas using SNS
    keyword : SNS, sentiment analysis, response pattern, LDA
  • A study for extracting characteristic features of fun of music artists based on SNS
    keyword : SNS, profile, infomatrion extraction
  • A study on serious games to support collaboration between strangers in the local area
    keyword : Serious game, gamification, collaboration
  • A study on user recommendation with high serendipity in SNS
    keyword : SNS, recommendation, serendipity
  • A study on generating pictorial maps based on photos posted on SNS
    keyword : SNS, automatic generation, bigdata
  • A Study on composition support based on characteristics of existing songs
    keyword : Big data, AI, data mining
  • Recommendation Optimization based on feedbacks on user reviews
    keyword : review, feedback, optimization, recommendation
  • Recommendation of Fashion Information based on preference on trend
    keyword : SNS, fashion, recommendation
  • News Browsing Support Based on Reactions on SNS
    keyword : news categorization, SNS
  • Automatic Optimization of Web Pages based on User's Browsing Intention
    keyword : intention mining, optimization, web browsing
  • Visualizing Social and Cultural Patterns through SNS
    keyword : SNS, Visualization
  • Studies for User Adaptive Interface
    keyword : Interface, Web, Digital Contents, SNS
  • contents selection method based on diffrence enhancement
    keyword : example, contents selection
  • A browsing method for social streams using the kactel party effect
    keyword : Sound browsing, social stream
  • A Method for Recommending TV Anime Programs Based on User Behaviors of Social Viewing
    keyword : Twitter, Collaborative filtering
  • A ranking method for Art SNS
    keyword : SNS, ranking
  • microblog classification method based on user's responses
    keyword : microblog, response
  • A method for composing ad-hoc follow network on Twitter for information of real world events
    keyword : ad-hoc follow network, Twitter
  • Automatic Generation of Interactive Dance Tutorials Based on Behaviors of Dancers
    keyword : Behavior, dance, interactive tutorial
  • A method for effective item selection based on user behavir on smartphone
    keyword : behavior, smartphone, ranking
  • sosial infrastructure utlizing social media
    keyword : social infrastructure, sosial meida
  • A context-adaptive interface of a social stream based on dropped content
    keyword : dropped content, social stream
  • A ranking method of online reviews for efficient item selection
    keyword : review, ranking, recommendation
  • A Study on Recommendation System Corresponding to User’s Mental State
    keyword : recommendation
  • social viewing system for enrich the simpathy among users
    keyword : social viewing, shimpathy
  • A recombination method for musical artists based on relationship between them
    keyword : recommendation
  • Development of a comunication ware
    keyword : smart phone, communication support
  • A method for personalized ranking of items based on micro-blog articles
    keyword : ranking, microblog
  • A study for recommending touring places based on transfer logs of travelers
    keyword : recommendation, transfer logs, tourism
  • A study for a book recommendation method based on user reviews on the Internet
    keyword : recommendation, user reviews
  • A study for ranking geo-information based on GPS logs
    keyword : GPS logs, Geo-information, ranking
  • A study for detecting false rumors on micro-blog services
    keyword : Microblog,
  • Personal content environment based on the experience Web(X-Web)
    keyword : X-Web, personal content environment
  • A study on lifelog search
    keyword : Lifelog
  • A study on WWW search engine based on problem-solving cases
    keyword : Web search engine, problem-solving cases
    2003.04~2004.03Study on Objective Oriented WWW Search Based on Problem Solving Cases: The purpose of this study is to support for searching WWW pages adaptable for solving problems of users. For this purpose, we develop a data model for reorganizing WWW pages from the view of problem solving in the real world and for providing generalization and specialization operations on the problem solving cases..
  • A study on an asynchronous video communication system
    keyword : Asynchronous, video, communication
    2001.04~2003.03Research on asynchronous video comunication systems: This research aims to support effective communications using asynchronously transmitted video messages. For this objective, we develop data model for managing video messages based on their semantics and communication context..
  • A method for composing video storyboards based on semantics
    keyword : Video, storyboard, video database
    2000.04~2002.04We developed an approach for the browsing video databases with hyper-storyboard that are generated automatically from semantic content descriptions of video. In the hyper-storyboard, video frames are linked each other based on their semantic relationships, and end users can traverse these links. This mechanism supports nonlinear semantic content-based accesses of video, and users are able to observe interesting frames and scenes in video interactively according to situations..
  • A study on next generation GIS
    keyword : GIS
  • Study on Next Generation Interface based on Media Art Presentation
    keyword : Media art
  • A method of desktop search based on implicit link structure of personal content
    keyword : personal content, implicit link, data mining, desktop search
  • Browsing of digital content on mobile phone in the real world
    keyword : AR, mobile phone, content, browsing
  • A recommendation system for daily behavior of users based microblogging service
    keyword : Microblogging, twitter, recommendation
  • An automatic composition method for attractive photo slideshows
    keyword : Slideshow composition, attractiveness
  • A method for automatic composition of browsing route in a museum
    keyword : Museum, recommendation, HITS algorithm
  • A study on “stand reading” of e-book based on book reviews
    keyword : e-book, review, recommendation
  • A study on composing a personalized ranking chart for user generated contents (UGSs)
    keyword : User generated contents, personalized ranking
  • A method for virtual fusing actual contents in the real world using smartphones
    keyword : Augmented reality, personalized reality, smart phone, virtual fusion of contents
Academic Activities
1. Chihiro Maehara, Kotaro Yatsugi, Daewoong Kim and Taketoshi Ushiama, Innovations in Intelligent Machines – 2
Intelligent Paradigms and Applications
, Springer, pp. 131-141, 2012.02.
1. Teruki Nakahara, Taketoshi Ushiama, Personalized Prediction of Offensive News Comments by Considering the Characteristics of Commenters, Proceedings of the 38th ACM/SIGAPP Symposium on Applied Computing (SAC '23), 10.1145/3555776.3577670, 2023.03.
2. Nodoka Fujimoto, Taketoshi Ushiama, Situational Estimation of Sports Broadcasting using a Character Level Auto-Encoder for Live Tweets, Proceedings of The 2020 IEEE/WIC/ACM International Joint Conference on Web Intelligence and Intelligent Agent Technology, 2020.12.
3. Yan Zhou, Taketoshi Ushiama, LSTM-based recommendation approach for interaction records, 13th International Conference on Ubiquitous Information Management and Communication, IMCOM 2019 Proceedings of the 13th International Conference on Ubiquitous Information Management and Communication, IMCOM 2019, 10.1007/978-3-030-19063-7_74, 950-962, 2019.01, Interactive platforms such as Spotify and Steam currently play an increasingly important role on the Internet. Users continuously use the content on these platforms. Therefore, the most important data in interactive platforms are interaction records, which contain an enormous amount of information regarding user interests at any given time. However, previous recommendation approaches have been unable to process such records satisfactorily. Therefore, we propose an LSTM-based recommendation approach for interaction records. In our approach, we used a recurrent neural network (RNN) based on LSTM to make recommendations by learning user interests and their changing trend. We propose a pretreatment called serial filling at equal ratio to apply LSTM. Further, we used a dimensionality reduction technique based on matrix factorization to improve the system efficiency. Finally, we evaluated our approach using Steam datasets. As indicated by the results, our approach performs better than other conventional approaches in three aspects: Accuracy, efficiency, and diversity..
4. Yan Zhou, Taketoshi Ushiama, A collaborative filtering method for interactive platforms, Proceedings of 12th International Conference on Digital Information Management, 10.1109/ICDIM.2017.8244679, 75-80, 2017.09.
5. Tomoaki Imajo, Kazutoshi Sumiya, Taketoshi Ushiama, An SNS Based on Implicit Beneficial Social Relations in A Regional Community, Proceedings of the 10th International Conference on Ubiquitous Information Management and Communication, 2016.01, In this paper, we propose a novel Social Networking Service (SNS) for a regional community. The purpose of the SNS is to support and encourage people by making them aware beneficial social relations in the real world. The conventional SNSs can hardly deal with beneficial social relations, because they are implicit and dynamic. The proposed SNS is designed to provide positive information for two types of people: people who does community voluntary works, such as cleaning, as contributors, and people who receives benefit from them as beneficiary. This paper introduces the basic scheme based on the SNS for beneficial social relations, and evaluates the effectiveness of our scheme based on the result of the experimental studies. The experimental result shows the users of our SNS tend to consider the information about the voluntary works valuable if they have been performed in their living area, and it suggests that our proposed SNS system would work well in a regional community..
1. Tomoaki Imajyo, Taketoshi Ushiama, An SNS Based on Implicit Beneficial Social Relations in a Reginal Community, ACM the 10th International Conference on Ubiquitous Information Management and Communication, 2016.01.
Membership in Academic Society
  • The Association for Natural Language Processing
Educational Activities
Dr. Ushiama teaches the latest technologies for information retrieval, information recommendation, automatic content generation and editing, and their impact on society using the Web-based digital content usage environment and AI and machine learning technologies.
Professional and Outreach Activities
I have been one of lectures of the public cause of the WWW site design with DBMS since 2000..