Shinji Tateishi - Academia.edu (original) (raw)
Uploads
Papers by Shinji Tateishi
This paper proposes an academic success prediction modeling approach that can be used for student... more This paper proposes an academic success prediction modeling approach that can be used for student advising, in which a multi-objective evolutionary computation approach is applied that automatically selects important explanatory variables suitable to predict academic success and construct multiple predictive models based on machine learning. Numerical experiments using actual student data suggest that it is possible to construct predictive models in considering the trade-off of prediction performance and model interpretability.
序章 研究の狙いと方法… 小方直幸 1 第1章 学部の概要とプログラムの特性… 串本剛 7 第2章 山口大学国際総合科学部… 小方直幸 17 第3章 福井大学国際地域学部… 小方直幸 29 第4... more 序章 研究の狙いと方法… 小方直幸 1 第1章 学部の概要とプログラムの特性… 串本剛 7 第2章 山口大学国際総合科学部… 小方直幸 17 第3章 福井大学国際地域学部… 小方直幸 29 第4章 長崎大学多文化社会学部… 小方直幸 41 第5章 学生の諸経験等に関する3学部の特性… 立石慎治 53 第6章 教員の認識… 立石慎治 63 結章 学士課程教育における総合的アプローチの意義… 小方直幸 73
Daigaku ronshu: Research in higher education, Mar 1, 2020
International journal of institutional research and management, 2021
In this paper, we propose a new method of constructing machine learning models for predicting aca... more In this paper, we propose a new method of constructing machine learning models for predicting academic success. In this method, a multi-objective genetic algorithm is deployed to select explanatory variables for the predictive model as an approach that takes into account both elements of predictive performance and interpretability. By using two evaluation functions, i.e., prediction performance and the number of explanatory variables, our method can find the Pareto-optimal solution set that reflects these trade-offs. The numerical simulation results show that our method can obtain a model set that takes into account the trade-off between the accuracy and complexity of the predictive model, although there are differences in behavior depending on the academic success indices to be predicted.
The aim of this paper is to analyze the structure of decision-making of students for transfer in ... more The aim of this paper is to analyze the structure of decision-making of students for transfer in short-cycle higher education based on the "Survey on high school students' progression" conducted by Center for Research on University Management and Policy, Tokyo University. After the descriptive analysis, binominal logistic regression model was used for analyzing the structure of decision-making of students for transfer at both time of high school and colleges. The primary results include: 1) Parents' expectation regulates their children's choice. 2) Academic record in junior high school and learning behavior in college affect students' choice. Further analysis of actual result of transfer to university and development of framework of student survey that focuses on another type of minority students remain as future issues
The purpose of this book is to clarify the renewed undergraduate education in the humanities and ... more The purpose of this book is to clarify the renewed undergraduate education in the humanities and social sciences in the national university sector, from the viewpoint of organization, curriculum, and the impact on students’ learning. Three case-studies are selected on the basis of their name, academic field, type of reorganization, and date of formation: the School of Global Humanities and Social Science at Nagasaki University, the Faculty of Global Sciences at Yamaguchi University, and the School of Global and Community Studies at University of Fukui. First, the context of reorganization of each school and faculty, and the characteristics and structure of the curriculum are analyzed. Next the students’ learning behaviors and the impact of curriculum are analyzed based on a student survey, through comparison with the national student survey and between the three case-study organizations. Furthermore, the results from the student survey are reverified through a faculty survey. The re...
2020 9th International Congress on Advanced Applied Informatics (IIAI-AAI), 2020
This paper proposes an academic success prediction modeling approach that can be used for student... more This paper proposes an academic success prediction modeling approach that can be used for student advising, in which a multi-objective evolutionary computation approach is applied that automatically selects important explanatory variables suitable to predict academic success and construct multiple predictive models based on machine learning. Numerical experiments using actual student data suggest that it is possible to construct predictive models in considering the trade-off of prediction performance and model interpretability.
序章 研究の狙いと方法… 小方直幸 1 第1章 学部の概要とプログラムの特性… 串本剛 7 第2章 山口大学国際総合科学部… 小方直幸 17 第3章 福井大学国際地域学部… 小方直幸 29 第4... more 序章 研究の狙いと方法… 小方直幸 1 第1章 学部の概要とプログラムの特性… 串本剛 7 第2章 山口大学国際総合科学部… 小方直幸 17 第3章 福井大学国際地域学部… 小方直幸 29 第4章 長崎大学多文化社会学部… 小方直幸 41 第5章 学生の諸経験等に関する3学部の特性… 立石慎治 53 第6章 教員の認識… 立石慎治 63 結章 学士課程教育における総合的アプローチの意義… 小方直幸 73
International Journal of Institutional Research and Management, 2021
In this paper, we propose a new method of constructing machine learning models for predicting aca... more In this paper, we propose a new method of constructing machine learning models for predicting academic success. In this method, a multi-objective genetic algorithm is deployed to select explanatory variables for the predictive model as an approach that takes into account both elements of predictive performance and interpretability. By using two evaluation functions, i.e., prediction performance and the number of explanatory variables, our method can find the Pareto-optimal solution set that reflects these trade-offs. The numerical simulation results show that our method can obtain a model set that takes into account the trade-off between the accuracy and complexity of the predictive model, although there are differences in behavior depending on the academic success indices to be predicted.
The purpose of this article is to propose a new framework for analyzing undergraduate education i... more The purpose of this article is to propose a new framework for analyzing undergraduate education in nontraditional faculties through consideration of the interrelationship between disciplines, faculty arrangement and curriculum. In contrast to traditional faculties, non-traditional faculties are grounded on competencies that they try to inculcate in their students, rather than introducing students to a single discipline. The emergence of these new non-traditional faculties demands a new perspective to understand the construction of undergraduate education. This article takes three non-traditional faculties of humanities and social sciences in three national universities as case studies. All of them were reorganized after 2014, and differ enough to warrant a comparative study. Case studies were conducted in two ways. First, the faculty arrangement and curriculum of each case were analyzed quantitatively based on their official application forms for reorganization. In terms of faculty ...
Kyōiku shakaigaku kenkyū, Jun 30, 2019
はじめに 小林 功英 i 第1章 大学における災害ボランティア活動の教育効果を検討するために 白川 優治・小林 功英・立石 慎治 1 第2章 分析の枠組 小林 功英・白川 優治・村澤 昌崇・立石... more はじめに 小林 功英 i 第1章 大学における災害ボランティア活動の教育効果を検討するために 白川 優治・小林 功英・立石 慎治 1 第2章 分析の枠組 小林 功英・白川 優治・村澤 昌崇・立石 慎治 15 第3章 災害ボランティア経験者の素描 : ボランティアに至るまで 村澤 昌崇 19 第4章 災害ボランティア経験の実態 白川 優治・小林 功英 27 第5章 災害ボランティア経験が持つ大学生へのインパクト 小林 功英 37 第6章 大学や周囲の人との関係性 立石 慎治 44 第7章 インタビューを通してみるボランティア経験の受け止められ方 小林 功英・白川 優治・村澤 昌崇・立石 慎治 58 第8章 今後の展望 : 機関インタビューの結果を通じて 小林 功英・白川 優治・立石 慎治 75 おわりに 小林 功英 84 付録 : アンケート調査項
The Journal of Educational Sociology, 2019
This paper proposes an academic success prediction modeling approach that can be used for student... more This paper proposes an academic success prediction modeling approach that can be used for student advising, in which a multi-objective evolutionary computation approach is applied that automatically selects important explanatory variables suitable to predict academic success and construct multiple predictive models based on machine learning. Numerical experiments using actual student data suggest that it is possible to construct predictive models in considering the trade-off of prediction performance and model interpretability.
序章 研究の狙いと方法… 小方直幸 1 第1章 学部の概要とプログラムの特性… 串本剛 7 第2章 山口大学国際総合科学部… 小方直幸 17 第3章 福井大学国際地域学部… 小方直幸 29 第4... more 序章 研究の狙いと方法… 小方直幸 1 第1章 学部の概要とプログラムの特性… 串本剛 7 第2章 山口大学国際総合科学部… 小方直幸 17 第3章 福井大学国際地域学部… 小方直幸 29 第4章 長崎大学多文化社会学部… 小方直幸 41 第5章 学生の諸経験等に関する3学部の特性… 立石慎治 53 第6章 教員の認識… 立石慎治 63 結章 学士課程教育における総合的アプローチの意義… 小方直幸 73
Daigaku ronshu: Research in higher education, Mar 1, 2020
International journal of institutional research and management, 2021
In this paper, we propose a new method of constructing machine learning models for predicting aca... more In this paper, we propose a new method of constructing machine learning models for predicting academic success. In this method, a multi-objective genetic algorithm is deployed to select explanatory variables for the predictive model as an approach that takes into account both elements of predictive performance and interpretability. By using two evaluation functions, i.e., prediction performance and the number of explanatory variables, our method can find the Pareto-optimal solution set that reflects these trade-offs. The numerical simulation results show that our method can obtain a model set that takes into account the trade-off between the accuracy and complexity of the predictive model, although there are differences in behavior depending on the academic success indices to be predicted.
The aim of this paper is to analyze the structure of decision-making of students for transfer in ... more The aim of this paper is to analyze the structure of decision-making of students for transfer in short-cycle higher education based on the "Survey on high school students' progression" conducted by Center for Research on University Management and Policy, Tokyo University. After the descriptive analysis, binominal logistic regression model was used for analyzing the structure of decision-making of students for transfer at both time of high school and colleges. The primary results include: 1) Parents' expectation regulates their children's choice. 2) Academic record in junior high school and learning behavior in college affect students' choice. Further analysis of actual result of transfer to university and development of framework of student survey that focuses on another type of minority students remain as future issues
The purpose of this book is to clarify the renewed undergraduate education in the humanities and ... more The purpose of this book is to clarify the renewed undergraduate education in the humanities and social sciences in the national university sector, from the viewpoint of organization, curriculum, and the impact on students’ learning. Three case-studies are selected on the basis of their name, academic field, type of reorganization, and date of formation: the School of Global Humanities and Social Science at Nagasaki University, the Faculty of Global Sciences at Yamaguchi University, and the School of Global and Community Studies at University of Fukui. First, the context of reorganization of each school and faculty, and the characteristics and structure of the curriculum are analyzed. Next the students’ learning behaviors and the impact of curriculum are analyzed based on a student survey, through comparison with the national student survey and between the three case-study organizations. Furthermore, the results from the student survey are reverified through a faculty survey. The re...
2020 9th International Congress on Advanced Applied Informatics (IIAI-AAI), 2020
This paper proposes an academic success prediction modeling approach that can be used for student... more This paper proposes an academic success prediction modeling approach that can be used for student advising, in which a multi-objective evolutionary computation approach is applied that automatically selects important explanatory variables suitable to predict academic success and construct multiple predictive models based on machine learning. Numerical experiments using actual student data suggest that it is possible to construct predictive models in considering the trade-off of prediction performance and model interpretability.
序章 研究の狙いと方法… 小方直幸 1 第1章 学部の概要とプログラムの特性… 串本剛 7 第2章 山口大学国際総合科学部… 小方直幸 17 第3章 福井大学国際地域学部… 小方直幸 29 第4... more 序章 研究の狙いと方法… 小方直幸 1 第1章 学部の概要とプログラムの特性… 串本剛 7 第2章 山口大学国際総合科学部… 小方直幸 17 第3章 福井大学国際地域学部… 小方直幸 29 第4章 長崎大学多文化社会学部… 小方直幸 41 第5章 学生の諸経験等に関する3学部の特性… 立石慎治 53 第6章 教員の認識… 立石慎治 63 結章 学士課程教育における総合的アプローチの意義… 小方直幸 73
International Journal of Institutional Research and Management, 2021
In this paper, we propose a new method of constructing machine learning models for predicting aca... more In this paper, we propose a new method of constructing machine learning models for predicting academic success. In this method, a multi-objective genetic algorithm is deployed to select explanatory variables for the predictive model as an approach that takes into account both elements of predictive performance and interpretability. By using two evaluation functions, i.e., prediction performance and the number of explanatory variables, our method can find the Pareto-optimal solution set that reflects these trade-offs. The numerical simulation results show that our method can obtain a model set that takes into account the trade-off between the accuracy and complexity of the predictive model, although there are differences in behavior depending on the academic success indices to be predicted.
The purpose of this article is to propose a new framework for analyzing undergraduate education i... more The purpose of this article is to propose a new framework for analyzing undergraduate education in nontraditional faculties through consideration of the interrelationship between disciplines, faculty arrangement and curriculum. In contrast to traditional faculties, non-traditional faculties are grounded on competencies that they try to inculcate in their students, rather than introducing students to a single discipline. The emergence of these new non-traditional faculties demands a new perspective to understand the construction of undergraduate education. This article takes three non-traditional faculties of humanities and social sciences in three national universities as case studies. All of them were reorganized after 2014, and differ enough to warrant a comparative study. Case studies were conducted in two ways. First, the faculty arrangement and curriculum of each case were analyzed quantitatively based on their official application forms for reorganization. In terms of faculty ...
Kyōiku shakaigaku kenkyū, Jun 30, 2019
はじめに 小林 功英 i 第1章 大学における災害ボランティア活動の教育効果を検討するために 白川 優治・小林 功英・立石 慎治 1 第2章 分析の枠組 小林 功英・白川 優治・村澤 昌崇・立石... more はじめに 小林 功英 i 第1章 大学における災害ボランティア活動の教育効果を検討するために 白川 優治・小林 功英・立石 慎治 1 第2章 分析の枠組 小林 功英・白川 優治・村澤 昌崇・立石 慎治 15 第3章 災害ボランティア経験者の素描 : ボランティアに至るまで 村澤 昌崇 19 第4章 災害ボランティア経験の実態 白川 優治・小林 功英 27 第5章 災害ボランティア経験が持つ大学生へのインパクト 小林 功英 37 第6章 大学や周囲の人との関係性 立石 慎治 44 第7章 インタビューを通してみるボランティア経験の受け止められ方 小林 功英・白川 優治・村澤 昌崇・立石 慎治 58 第8章 今後の展望 : 機関インタビューの結果を通じて 小林 功英・白川 優治・立石 慎治 75 おわりに 小林 功英 84 付録 : アンケート調査項
The Journal of Educational Sociology, 2019