Updated on 2025/07/01

写真a

 
INOSHITA Keito
 
Organization
Graduate School of Business and Commerce Business and Commerce Major
External link

Degree

  • Master's Degree (Data Science) ( 2025.3   Shiga University )

Research Interests

  • Bias Detection

  • Deep Learning

  • Data Mining

  • Machine Learning

  • Sentiment Analysis

  • Natural Language Processing

  • Large Language Model

Research Areas

  • Informatics / Statistical science

  • Informatics / Computer system

  • Informatics / Information security

  • Informatics / Intelligent informatics

  • Informatics / Kansei informatics

Education

  • Shiga University   Graduate School of Data Science

    2023.4 - 2025.3

      More details

    Country: Japan

    researchmap

  • Sapporo University   School of Society and Collaboration   Business Administration major

    2020.4 - 2023.3

      More details

    Country: Japan

    Notes: Dropped out at the end of the third year to skip to graduate school

    researchmap

  • Kansai University

    2025.4

      More details

Research History

  • Shiga University

    2025.4

      More details

  • 日本セーフティソサイエティ研究センター   研究員

    2025.4

      More details

  • 国立研究開発法人科学技術振興機構 (JST) 次世代研究者挑戦的研究プログラム (SPRING) 関西大学SPRINGスカラシップ研究学生

    2025.4

      More details

Professional Memberships

  • 日本感性工学会

    2025.6 - Present

      More details

  • 情報知識学会

    2025.3 - Present

      More details

  • 言語処理学会

    2025.2 - Present

      More details

  • 日本データベース学会

    2025.2 - Present

      More details

  • 日本情動学会

    2025.2 - Present

      More details

  • 人工知能学会

    2025 - Present

      More details

  • ACL (Association for Computational Linguistics)

    2024 - Present

      More details

  • IEEE Computer Society

    2023 - Present

      More details

  • 情報処理学会

    2023 - Present

      More details

▼display all

Committee Memberships

  •   International Conference on Natural Language Processing for Digital Humanities (NLP4DH) - Program Committee  

    2025.1 - Present   

      More details

    Committee type:Academic society

    researchmap

  •   IEEE Kansai Section Young Professionals Affinity Group - Associate  

    2024.10 - Present   

      More details

Papers

  • GNN-Enhanced Multimodal Fusion with Contrastive Learning for Smart Health Oriented High Performance Recommendation System Reviewed

    Keito Inoshita, Ryutaro Matsuoka, Xiaokang Zhou, Zhigao Zheng, Akira Kawai, Katsutoshi Yada

    Proceedings of the 2025 IEEE International Conference on High Performance Computing and Communications (IEEE HPCC) (to appear)   2025.8

     More details

    Authorship:Lead author  

    researchmap

  • Enhancing Sentiment Analysis Accuracy and Evaluating Task Affinity Using Large Language Models Reviewed

    Keito Inoshita

    Proceedings of the 2025 IEEE International Conference on Artificial Intelligence for Learning and Optimization (IEEE ICoAILO) (to appear)   2025.8

     More details

    Authorship:Lead author, Corresponding author   Publishing type:Research paper (international conference proceedings)  

    researchmap

  • Multi-Scale Convolutional Fusion with Contrastive Feature Alignment for Imbalanced Data Classification Reviewed

    Keito Inoshita Takato Ueno, Xiaokang Zhou

    Proceedings of the 30th International Conference on Natural Language & Information Systems (NLDB) (to appear)   2025.7

     More details

    Authorship:Lead author   Publishing type:Research paper (international conference proceedings)  

    researchmap

  • Dual-Branch Feature Extraction via Discrepancy-Aware Fusion with Evidential Deep Learning for Sarcasm Detection Reviewed

    Takato Ueno, Keito Inoshita

    Proceedings of the 2025 IEEE International Conference on Industry 4.0, Artificial Intelligence, and Communications Technology (IEEE IAICT) (to appear)   2025.7

     More details

    Authorship:Corresponding author  

    researchmap

  • Evaluation of the Automated Labeling Method for Taxonomic Nomenclature Through Prompt-Optimized Large Language Model Reviewed

    Keito Inoshita, Kota Nojiri, Haruto Sugeno, Takumi Taga

    Proceedings of the 2025 IEEE International Conference on Industry 4.0, Artificial Intelligence, and Communications Technology (IEEE IAICT) (to appear)   2025.7

     More details

    Authorship:Lead author, Corresponding author  

    researchmap

  • A Multi-Agent Probabilistic Inference Framework Inspired by Kairanban-Style CoT System with IdoBata Conversation for Debiasing

    Takato Ueno, Keito Inoshita

    arXiv   2025.6

     More details

  • Introducing Large Language Models to Human-Based Etymological Classification in Zooplankton

    Haruto Sugeno, Keito Inoshita, Kota Nojiri, Takumi Taga

    bioRxiv   2025.5

     More details

  • Automated Labeling of Scientific Names and Etymological Trend Analysis in Phytophagous Arthropods Using Large Language Model Reviewed

    Kota Nojiri, Keito Inoshita, Haruto Sugeno

    Zoological Science   2025.3

  • Bias Examination of International Conflict Structures in Large Language Models and Debiasing Methods Based on Active and Passive Approaches Reviewed

    Keito Inoshita

    じんもんこん2024論文集   2024.12

     More details

    Authorship:Lead author, Corresponding author  

    researchmap

  • Multi-Stage Evolutionary Model Merging with Meta Data Driven Curriculum Learning for Sentiment-Specialized Large Language Modeling Reviewed

    Keito Inoshita, Xiaokang Zhou, Akira Kawai

    Proceedings of the 10th IEEE International Conference on Data Science and Systems (IEEE DSS)   58 - 65   2024.12

     More details

    Authorship:Lead author   Publishing type:Research paper (international conference proceedings)  

    researchmap

  • Evolutionary Expert Model Merging with Task-Adaptive Iterative Self-Improvement Process for Large Language Modeling on Aspect-Based Sentiment Analysis Reviewed

    Keito Inoshita

    Proceedings of the 2024 IEEE International Conference on Internet of Things and Intelligence Systems (IEEE IoTaIS)   130 - 136   2024.11

     More details

    Authorship:Lead author, Corresponding author   Publishing type:Research paper (international conference proceedings)   Publisher:IEEE  

    DOI: 10.1109/iotais64014.2024.10799461

    researchmap

  • Multifaceted Exploration of Perceptions on the Ukraine-Russia War in the Japanese Twitter Space Reviewed

    Keito Inoshita

    Proceedings of the 2024 IEEE International Conference on Internet of Things and Intelligence Systems (IEEE IoTaIS)   58 - 64   2024.11

     More details

    Authorship:Lead author, Corresponding author   Publishing type:Research paper (international conference proceedings)   Publisher:IEEE  

    DOI: 10.1109/iotais64014.2024.10799391

    researchmap

  • Quantitative Analysis of Political Party Understanding and the Impact of Political Bias through ChatGPT Reviewed

    Keito Inoshita

    SHS Web of Conferences   204   03012 - 03012   2024.11

     More details

    Authorship:Lead author, Corresponding author   Publishing type:Research paper (scientific journal)   Publisher:EDP Sciences  

    In recent years, large language models (LLMs) such as ChatGPT have been utilized for acquiring political knowledge. However, there remain questions about their accuracy and fairness, as these models may harbour biases in understanding political parties. This study aims to quantify the understanding of Japanese political parties using the ChatGPT model and evaluate the model’s biases and their impacts. Specifically, we conducted experiments using pairs of questions and answers that reflect the stances of each party to investigate the extent to which the model demonstrates understanding toward specific parties. The experimental results revealed that ChatGPT-4 exhibits a significantly higher level of understanding towards the Liberal Democratic Party, while its understanding of newer parties like Reiwa Shinsengumi is lower. Additionally, the GPT model acting as a voter tends to have a positive bias towards certain parties and reflects progressive ideologies. It was also shown that the recognition of political parties influences the model’s understanding, with factors such as the number of seats, advertising expenses, and the frequency of party names in the dataset potentially playing crucial roles. Based on these findings, this study provides a foundation for enhancing the accuracy and fairness of party understanding using GPT models and proposes improvements for future research and practice.

    DOI: 10.1051/shsconf/202420403012

    researchmap

  • Assessing GPT's Legal Knowledge in Japanese Real Estate Transactions Exam Reviewed

    Keito Inoshita

    Proceedings of the 2024 International Conference on Innovation and Intelligence for Informatics, Computing, and Technologies (3ICT)   149 - 155   2024.11

     More details

    Authorship:Lead author, Corresponding author   Publishing type:Research paper (international conference proceedings)   Publisher:IEEE  

    DOI: 10.1109/3ict64318.2024.10824669

    researchmap

  • Corpus Development Based on Conflict Structures in the Security Field and LLM Bias Verification Reviewed

    Keito Inoshita

    Proceedings of the 4th International Conference on Natural Language Processing for Digital Humanities   504 - 512   2024.11

     More details

    Authorship:Lead author, Corresponding author   Publishing type:Research paper (international conference proceedings)   Publisher:Association for Computational Linguistics  

    DOI: 10.18653/v1/2024.nlp4dh-1.49

    researchmap

  • Sentiment Bias and Security Analysis in Training Datasets of Large Language Models Reviewed

    Keito Inoshita, Xiaokang Zhou

    Proceedings of the 14th IEEE International Conference on Big Data and Cloud Computing (IEEE BDCloud)   1 - 8   2024.11

     More details

    Authorship:Lead author   Publishing type:Research paper (international conference proceedings)  

    researchmap

  • The Efficient Development of Conflict Structure Datasets for Evaluating Sentiment Recognition Bias in Large Language Models Reviewed

    Keito Inoshita

    Proceedings of the 2024 International Conference on Electrical Engineering and Informatics (ICELTICs)   7 - 12   2024.9

     More details

    Authorship:Lead author, Corresponding author   Publishing type:Research paper (international conference proceedings)   Publisher:IEEE  

    DOI: 10.1109/iceltics62730.2024.10776050

    researchmap

  • Sentiment Analysis of Japanese Twitter Users Regarding the Ukraine-Russia War and Its Implications for Security Policy Reviewed

    Keito Inoshita

    Proceedings of the 11th International Conference on Information Technology, Computer, and Electrical Engineering (ICITACEE)   338 - 343   2024.8

     More details

    Authorship:Lead author, Corresponding author   Publishing type:Research paper (international conference proceedings)   Publisher:IEEE  

    DOI: 10.1109/icitacee62763.2024.10762783

    researchmap

  • Multi-Domain and Multi-View Oriented Deep Neural Network for Sentiment Analysis in Large Language Models Reviewed

    Keito Inoshita, Xiaokang Zhou, Shohei Shimizu

    Proceedings of the 2024 IEEE International Conferences on Internet of Things (iThings) and IEEE Green Computing & Communications (GreenCom) and IEEE Cyber, Physical & Social Computing (CPSCom) and IEEE Smart Data (SmartData) and IEEE Congress on Cybermatics   149 - 156   2024.8

     More details

    Authorship:Lead author   Publishing type:Research paper (international conference proceedings)   Publisher:IEEE  

    DOI: 10.1109/ithings-greencom-cpscom-smartdata-cybermatics62450.2024.00045

    researchmap

  • Assessment of Conflict Structure Recognition and Bias Impact in Japanese LLMs Reviewed

    Keito Inoshita

    Proceedings of the 5th Technology Innovation Management and Engineering Science International Conference (TIMES-iCON)   1 - 5   2024.6

     More details

    Authorship:Lead author, Corresponding author   Publishing type:Research paper (international conference proceedings)   Publisher:IEEE  

    DOI: 10.1109/times-icon61890.2024.10630720

    researchmap

▼display all

MISC

  • Assessing and Mitigating Language Models’ Classification Performance on Children’s Text

    Keito Inoshita, Yuken Kimura

    2025.9

     More details

    Authorship:Lead author, Corresponding author  

    researchmap

  • 大規模言語モデルは年齢を超えて文体を生成できるか

    井下 敬翔

    FIT2025 第24回情報科学技術フォーラム(to appear)   2025.9

     More details

    Authorship:Lead author, Corresponding author  

    researchmap

  • 学名が語る恣意性:語源に潜むバイアスの構造を可視化する

    野尻康太, 井下敬翔, 菅野遥登, 多賀匠

    日本動物学会 第96回名古屋大会(to appear)   2025.9

     More details

  • 自然言語処理による感情認識技術の研究動向と今後の課題

    原佑太郎, 井下敬翔

    第264回自然言語処理研究発表会 (to appear)   2025.7

     More details

    Authorship:Corresponding author  

    researchmap

  • 大規模言語モデルの政治的影響とガバナンスの指針

    井下敬翔

    第44回(R6年度)学生論文昭和池田賞   2025.6

     More details

    Authorship:Lead author, Corresponding author  

    researchmap

  • 回覧板と井戸端会議に着想を得たマルチエージェント確率的 推論フレームワークの検証

    上野孝斗, 井下敬翔

    研究報告人文科学とコンピュータ(CH) 2024-CH-136   2025.5

     More details

  • 学名の裏側をズバリ解明: 魚類と動物プランクトンの語源を大規模言語モデルで探る

    菅野遥登, 井下敬翔, 野尻康太, 多賀匠

    2025年度中国四国地区生物系三学会合同大会愛媛大会   2025.5

     More details

    Publishing type:Research paper, summary (national, other academic conference)  

    researchmap

  • 職場環境におけるマルチモーダル感情認識技術の現状と展望

    井下敬翔, 尾崎博信

    情報知識学会誌   35 ( 2 )   151 - 156   2025.5

     More details

    Authorship:Lead author, Corresponding author   Publishing type:Research paper, summary (national, other academic conference)  

    researchmap

  • 大規模言語モデル (LLM) を用いた学名の語源分類と命名傾向の時系列変化

    野尻康太, 井下敬翔, 菅野遥登

    2025年度中国四国地区生物系三学会合同大会愛媛大会   2025.5

     More details

    Publishing type:Research paper, summary (national, other academic conference)  

    researchmap

  • 京都・滋賀・奈良3府県の観光拠点間における口コミの類似性に着目した観光候補地群の分析

    尾﨑博信, 井下敬翔

    情報知識学会誌   35 ( 2 )   327 - 323   2025.5

     More details

    Publishing type:Research paper, summary (national, other academic conference)  

    researchmap

  • 感情データが導く生成AI時代のWell-beingな職場環境

    井下敬翔

    第25回理工学系学生科学技術論文コンクール入賞論文集   2025.3

     More details

    Authorship:Lead author, Corresponding author  

    researchmap

  • スポーツ長官賞: スポーツの小型化とモジュール型小規模競技場によるウェルビーイングな都市デザイン Invited

    井下敬翔

    社会教育   44 ( 45 )   2025.3

     More details

    Authorship:Lead author  

    researchmap

  • Enhancing Workplace Well-being Through Generative AI-Driven Emotion Analysis Invited

    Keito Inoshita

    Globe, Universe, Next future, Discussions And Mentions   1 ( 2 )   109 - 114   2025.1

     More details

    Authorship:Lead author, Corresponding author   Publishing type:Article, review, commentary, editorial, etc. (trade magazine, newspaper, online media)  

    researchmap

  • 視点の改革:中国に対するバイアスを超えて

    井下敬翔

    人民中国   2025.1

     More details

    Authorship:Lead author   Publishing type:Book review, literature introduction, etc.  

    researchmap

  • パーソナル AI と組織 AI による ⼈事管理の⾰新と最適化

    井下敬翔

    人と仕事の未来研究所第1回懸賞論文   2024.12

     More details

    Authorship:Lead author, Corresponding author   Publishing type:Article, review, commentary, editorial, etc. (other)  

    researchmap

  • スポーツの小型化とモジュール型小規模競技場によるウェルビーイングな都市デザイン, Invited

    井下敬翔

    月刊体育施設   ( 12月 )   43 - 44   2024.12

     More details

    Authorship:Lead author   Publishing type:Article, review, commentary, editorial, etc. (trade magazine, newspaper, online media)  

    researchmap

  • ベイズ深層学習とLLMを活用した公衆衛生基準に基づくトコジラミ分布予測サービスの提案

    井下敬翔

    2024.11

     More details

    Authorship:Lead author   Publishing type:Article, review, commentary, editorial, etc. (other)  

    researchmap

  • 核兵器に頼る国のリーダーへ:リアリズムと革新による平和への道

    井下敬翔

    「核なき未来」オピニオン   2024.8

     More details

    Authorship:Lead author   Publishing type:Book review, literature introduction, etc.  

    researchmap

  • A Novel Dataset Development Method for Evaluating Sentiment Recognition Bias of Large Language Models in Conflict Structures

    Keito Inoshita

    研究報告人文科学とコンピュータ(CH)   2024-CH-136 ( 2 )   1 - 4   2024.6

     More details

    Authorship:Lead author, Corresponding author   Publishing type:Meeting report  

    researchmap

  • 日本語Twitter空間における戦争認識の多角的探索 :ウクライナ-ロシア戦争への反応と洞察

    井下敬翔

    研究報告人文科学とコンピュータ(CH)   2024-CH-135 ( 1 )   1 - 8   2024.5

     More details

    Authorship:Lead author, Corresponding author   Publishing type:Meeting report  

    researchmap

▼display all

Presentations

  • 価値を生み出す学びと実績のサイクル

    井下敬翔

    滋賀大学サステナウィーク  2024.11 

     More details

    Presentation type:Public lecture, seminar, tutorial, course, or other speech  

    researchmap

Awards

  • 奨励賞-ISUZU AI Innovation Challenge 2024

    2025.6  

    井下敬翔

     More details

  • 特別奨励賞-第44回(R6年度)学生論文昭和池田賞

    2025.6  

    井下敬翔

     More details

  • 入賞-第25回理工系学生科学技術論文コンクール

    2025.3  

    井下敬翔

     More details

  • AI賞 - LOD チャレンジ2024

    2024.12  

    井下敬翔

     More details

  • Best Paper Award - the 10th IEEE International Conference on Data Science and Systems (IEEE DSS)

    2024.12  

    Keito Inoshita, Xiaokang Zhou, Akira Kawai

     More details

  • 奨励賞 - 人と仕事の未来研究所第1回懸賞論文

    2024.11  

    井下敬翔

     More details

  • Best Paper Award - the 2024 IEEE International Conference on Internet of Things and Intelligence System (IEEE IoTaIS)

    2024.11  

    Keito Inoshita

     More details

  • Best Paper Award - the 14th IEEE International Conference on Big Data and Cloud Computing (IEEE BDCloud)

    2024.10  

    Keito Inoshita, Xiaokang Zhou

     More details

  • 3位 - The IEEE R10 Ethics and Enterprise Risk Management committee Student Contest

    2024.9  

    Keito inoshita

     More details

  • Best Paper Award - International Conference on Information Technology, Computer, and Electrical Engineering (ICITACEE 2024)

    2024.8  

    Keito Inoshita

     More details

  • 関西大学給付奨学金

    2025.6  

     More details

  • 審査員特別賞-武蔵大学ビジネスプランコンテスト

    2025.2  

     More details

  • 学長賞-滋賀大学

    2025.2  

     More details

  • KINTO未来ファンド賞

    2025.1  

    井下敬翔

     More details

  • 優秀賞 - 第2回西播磨ビジネスコンテスト

    2024.12  

    井下敬翔

     More details

  • 入賞 - 「大学生」空き家活用アイデアコンテスト

    2024.11  

    井下敬翔

     More details

  • 優秀賞 - 夢をつくるプロジェクト2024

    2024.11  

    井下敬翔

     More details

  • 「しま」のビジネスチャレンジ賞 - ながさき「しま」のビジネスチャレンジ

    2024.11  

    井下敬翔

     More details

  • スポーツ庁長官賞 - スポーツ・健康まちづくりデザイン学生コンペティション2024

    2024.11  

    井下敬翔

     More details

  • 環境大臣賞 - APEV: 「モビリティで2030を創る」国際ワークショップ

    2024.11  

    井下敬翔, HAL名古屋メンバー

     More details

  • エシカル・データ賞 - 岡山ガス ビジネスプランコンテスト2024

    2024.11  

    井下敬翔

     More details

  • 採択 - 学生 ACTION CAMP 2024

    2024.10  

    井下敬翔

     More details

  • 優秀賞 - Panda杯全日本青年作文コンクール2024

    2024.10  

    井下敬翔

     More details

  • 優秀賞 - 関西大学ビジネスプラン・コンペティション(KUBIC)

    2024.10  

    井下敬翔

     More details

  • 最優秀賞 - NEC Analytics Challenge Cup for Business Idea 2024

    2024.10  

    井下敬翔 曽我美結

     More details

  • 敢闘賞 - 第9回芝浦ビジネスモデルコンペティション

    2024.9  

    井下敬翔

     More details

  • 入賞 - 第5回創生アイデアコンテストA部門

    2024.9  

    井下敬翔

     More details

  • 最優秀賞&テーマ賞 - Electric Sheepアイデアコンテスト2024

    2024.9  

    井下敬翔

     More details

  • 採択 - 水地域イノベーション財団 2024年度支援事業ビジネスプランコンテスト

    2024.9  

    井下敬翔

     More details

  • 優秀賞 - 第2回高速道路DXアイデアコンテストアイデア部門

    2024.6  

    井下敬翔

     More details

  • 滋賀大学データサイエンス研究科奨学金

    2024.3  

    井下敬翔

     More details

▼display all

Research Projects

  • 職場環境におけるマルチモーダルLLMを用いた感情シミュレーション&ゲーミングによる意思決定支援と組織学習の強化

    2025.4 - 2026.3

    公益財団法人 科学技術融合振興財団  調査研究補助金 

    井下敬翔

      More details

    Authorship:Principal investigator 

    researchmap

Other

  • 保持資格

     More details

    統計検定準1級,
    基本情報技術者,
    宅地建物取引士,
    データサイエンス発展

    researchmap

  • 修了証-AI経営講座(AI Business Insights 2025)

     More details

Social Activities

  • スポーツによる健康、まちづくりについて玉野市へプレゼン

    Role(s): Appearance, Informant

    スポーツ庁  スポーツ•健康まちづくりデザイン学生コンペティション  2025.2

     More details

    Type:Lecture

    researchmap

Academic Activities

  • Reviewer (日本認知科学会)

    Role(s): Peer review

     More details

  • Reviewer (Natural Language Processing for Digital Humanities)

    Role(s): Peer review

     More details

  • Reviewer (IEEE Transactions on Affective Computing)

    Role(s): Peer review

     More details