Research activity information

• Sep. 2024 The Japanese Association of Educational Psychology, Kido Award, Development of a short form of the Children’se Emotion Vocabulary Scale, using item response theory analysis

  Mai Hamana, Kyosuke Bunji

  Official journal

  共同研究・競争的資金等の業績IDIRI


• May 2020 日本計算機統計学会, 奨励賞

  分寺杏介

  本学会の欧文誌に公刊された Bunji & Okada (2019) は，反応時間もモデルに組み込んだ項目反応理論の優れた論文であり，本学会シンポジウムでも優れた口頭発表をしている (分寺・岡田，2017，2018)。その他，Behaviorresearch methods，日本テスト学会誌や，行動計量学の諸誌に，テストデータの計算機統計学の優れた論文を公刊しており，今後の研究が奨励されます。 Bunji, K., & Okada, K. (2019). Item response and response time model for personality assessment via linear ballistic accumulation. Japanese Journal of Statistics and Data Science, 2, 263–297. 分寺杏介，岡田謙介 (2018) Thurstonian IRT におけるパラメータの不変性について．日本計算機統計学会第32回シンポジ ウム． 分寺杏介，岡田議介 (2017) 反応時を利用する新たな項目反応モデ ルの提案 ― Linear Ballistic Accumulation を用いた効率的な推定法 ―．日本計算機統計学会第31回シンポジウム．

  Japan society


• Dec. 2017 日本テスト学会, 日本テスト学会大会発表賞, 出題領域と解答時間を考慮した項目選択アルゴリズムの性能評価

  登藤直弥, 分寺杏介, 尾崎幸謙

  Japan society


• Nov. 2017 日本計算機統計学会, 学生研究発表賞, 反応時間を利用する新たな項目反応モデルの提案 －Linear Ballistic Accumulation を用いた効率的な推定法－

  分寺杏介

  Japan society

• “Stumbling” in Responses to Psychological Scales and Support from Clinical Psychologists

  Ayako Baba, Kyosuke Bunji, Aya Fukushima

  This study defines “stumbling in response (hereinafter called "stumbling”)” as the difficulty in giving a valid response about their condition to a certain situation, psychological scale, or item. This study explored the presence, situation, and clinical psychologists’ support for clients’ stumbling in clinical situations from the perspective of clinical psychologists. An open-ended web-based survey of clinical psychologists showed that 99 out of 103 valid respondents noticed stumbling. Qualitative analysis revealed various situations causing stumbling, the diversity of clients’ expressions, clinical psychologists’ support, and different characteristics of stumbling in the collected responses. Quantitative analysis of co-occurrence frequencies and rates showed that the situation was related to stumbling, and that stumbling was related to support. These results are expected to facilitate the development of appropriate methods for stumbling prevention and support.

  The Japanese Psychological Association, Jan. 2025, 心理学研究, 96(1) (1), 48 - 54, Japanese, Domestic magazine

  [Refereed]

  Scientific journal


• Does the context effect exist in the multiple alternative forced-choice personality measurement?

  Kyosuke Bunji, Kensuke Okada

  A fundamental assumption in item response theory (IRT) models for multiple-alternative forced-choice (MAFC) personality measurement is that the utility of each statement (choice option) remains independent and invariant, irrespective of factors like the context effect. However, investigations on the confounding impact of the context effect on MAFC personality measurements are scarce. This study examined the impact of context effect on the utility and estimation of the parameters of each statement of the MAFC personality measurement. Thereon, a parameter estimation was conducted using the Thurstonian IRT model, assuming the presence or absence of context effects. Parameter estimates and Bayesian posterior distributions were compared from the perspective of the correlation of trait scores, an information criterion, explained variance, 95\% credible interval, the Bayes factor, and the overlap rate of the posterior distributions. The study's results suggest that the context effect can be considered small enough to be practically negligible.

  Sep. 2024, PsyArXiV (preprint), English


• An overview of research topics and recent developments in computer-based testing

  Kyosuke Bunji

  This paper selectively reviews the outline and current developments on theoretical aspects of computer-based testing (CBT) in various fields. Six major research topics were introduced in detail: score comparability between PBT and CBT, adaptive testing, innovative item types, frauds and their countermeasures in online testing, utilizing log data, and reasonable accommodation. In addition, following the previous predictions on the development of CBTs and the literature review, the future direction of research on CBTs was discussed from three perspectives: validity, test anxiety, and automation.

  The Japan Association for Research on Testing, Jun. 2023, Japanese Journal for Research on Testing, 19(1) (1), 191 - 225, Japanese, Domestic magazine

  [Refereed]

  Scientific journal


• Prediction of mental health problem using annual student health survey: Machine learning approach

  Ayako Baba, Kyosuke Bunji

  Background: One of the reasons why students go to counseling is being called on based on self-reported health survey results. However, there is no concordant standard for such calls. Objective: This study aims to develop a machine learning (ML) model to predict students’ mental health problems in 1 year and the following year using the health survey’s content and answering time (response time, response time stamp, and answer date). Methods: Data were obtained from the responses of 3561 (62.58%) of 5690 undergraduate students from University A in Japan (a national university) who completed the health survey in 2020 and 2021. We performed 2 analyses; in analysis 1, a mental health problem in 2020 was predicted from demographics, answers for the health survey, and answering time in the same year, and in analysis 2, a mental health problem in 2021 was predicted from the same input variables as in analysis 1. We compared the results from different ML models, such as logistic regression, elastic net, random forest, XGBoost, and LightGBM. The results with and without answering time conditions were compared using the adopted model. Results: On the basis of the comparison of the models, we adopted the LightGBM model. In this model, both analyses and conditions achieved adequate performance (eg, Matthews correlation coefficient [MCC] of with answering time condition in analysis 1 was 0.970 and MCC of without answering time condition in analysis 1 was 0.976; MCC of with answering time condition in analysis 2 was 0.986 and that of without answering time condition in analysis 2 was 0.971). In both analyses and in both conditions, the response to the questions about campus life (eg, anxiety and future) had the highest impact (Gain 0.131-0.216; Shapley additive explanations 0.018-0.028). Shapley additive explanations of 5 to 6 input variables from questions about campus life were included in the top 10. In contrast to our expectation, the inclusion of answering time–related variables did not exhibit substantial improvement in the prediction of students’ mental health problems. However, certain variables generated based on the answering time are apparently helpful in improving the prediction and affecting the prediction probability. Conclusions: These results demonstrate the possibility of predicting mental health across years using health survey data. Demographic and behavioral data, including answering time, were effective as well as self-rating items. This model demonstrates the possibility of synergistically using the characteristics of health surveys and advantages of ML. These findings can improve health survey items and calling criteria.

  JMIR Publications Inc., May 2023, JMIR Mental Health, 10, Article e42420, English, International magazine

  [Refereed]

  Scientific journal


• Development of a short form of the Children’s Emotion Vocabulary Scale, using item response theory analysis

  Mai Hamana, Kyosuke Bunji

  Acquisition of emotion words plays an important role in the socialization or the development of children's emotional experience. This study aimed to develop emotion words vocabulary scales for preschooler and young elementary school children by applying the model of Item Response Theory (IRT). In study 1, data was collected from 1136 mothers with 3 to 9-year-old children. Based on the data, short form of the emotion vocabulary scale was constructed. Study 2 and 3 reports the pattern of correlation relationships of the emotion vocabulary scale with several relevant variables. The results showed that emotion vocabulary was associated with language ability and social emotional competence in children; thus the validity evidence of the scale was confirmed.

  The Japanese Association of Educational Psychology, Mar. 2023, The Japanese Journal of Educational Psychology, 71(1) (1), 51 - 61, Japanese, Domestic magazine

  [Refereed]

  Scientific journal


• An estimation method in the paired-comparison format questionnaires that measure two latent traits

  Seito Nonoda, Kyosuke Bunji, Kensuke Okada

  Paired-comparison format questionnaires that measures two latent traits suffer from the problem of unidentifiability in the Thurstonian item response model. This study proposes a new method that enables us to identify this model. Specifically, we pro- pose to use every item twice in the questionnaire. In simulation studies, our proposed method recovered the respondent parameters at least as well as the control method, which required analysts to fix some of the parameters to their true values. In the real data analysis, the proposed method was applied to data obtained by two types of psychological scales, one of which contained only positively keyed items, whereas the other contained both positively and negatively keyed items. Item parameters and trait scores estimated using the former data resulted in large posterior standard deviations. In contrast, those estimated with the latter data exhibited better estimation proper- ties. Although it generally does not allow for precise measurement, we show that the proposed method is applicable to empirical analysis. It achieved progress, in that, it negates the need for the unrealistic assumption of fixing parameters to their true values.

  The Behaviormetric Society, Sep. 2021, The Japanese journal of behaviormetrics, 48(2) (2), 53 - 68, Japanese, Domestic magazine

  [Refereed]

  Scientific journal


• Linear ballistic accumulator item response theory model for multidimensional multiple-alternative forced-choice measurement of personality

  Kyosuke Bunji, Kensuke Okada

  There has been a growing interest in psychological measurements that use the multiple-alternative forced-choice (MAFC) response format for its resistance to response biases. Although several models have been proposed for the data obtained from such measurements, none have succeeded in incorporating the response time information. Given that currently, many psychological measurements are performed via computers, it would be beneficial to develop a joint model involving an MAFC item response and response time. The present study proposes the first model that combines a cognitive process model that underlies the observed response time and the forced-choice item response model. Specifically, the proposed model is based on the linear ballistic accumulator model of response time, which is substantially extended by reformulating its parameters so as to incorporate the MAFC item responses. The model parameters are estimated by the Markov chain Monte Carlo (MCMC) algorithm. A simulation study confirmed that the proposed approach could appropriately recover the parameters. Two empirical applications are reported to demonstrate the use of the proposed model and compare it with existing models. The results showed that the proposed model could be a useful tool for jointly modeling the MAFC item responses and response times.

  Society of Multivariate Experimental Psychology, Mar. 2021, Multivariate Behavioral Research, 57(4) (4), 658 - 678, English, International magazine

  [Refereed]

  Scientific journal


• Bayesian statistical modeling for modern personality measurement

  Kyosuke Bunji, Kensuke Okada

  コンピュータ上で行う心理特性の測定には，回答に要した時間も収集できることや，回答バイアスの影響を受けにくい比較判断型項目を自然に実装ができることといった利点がある。従来の紙の調査票をそのままコンピュータに載せるのではなく，こうした特徴を活用して妥当性の高い測定を行えると望ましい。本稿ではこれを実現するための，ベイズ統計的アプローチに基づく項目反応理論モデルの拡張による私たちの研究を紹介する。

  一般社団法人社会調査協会, Sep. 2020, Advances in Social Research, 25, 22 - 30, Japanese, Domestic magazine

  [Invited]

  Scientific journal


• Joint modeling of the two-alternative multidimensional forced-choice personality measurement and its response time by a Thurstonian D-diffusion item response model

  Kyosuke Bunji, Kensuke Okada

  The two-alternative multidimensional forced-choice measurement of personality has attracted researchers’ attention for its tolerance to response bias. Moreover, the response time can be collected along with the item response when personality measurement is conducted with computers. In view of this situation, the objective of this study is to propose a Thurstonian D-diffusion item response theory (IRT) model, which combines two key existing frameworks: the Thurstonian IRT model for forced-choice measurement and the D-diffusion IRT model for the response time in personality measurement. The proposed model reflects the psychological theories behind the data-generating mechanism of the item response and response time. A simulation study reveals that the proposed model can successfully recover the parameters and factor structure in typical application settings. A real data application reveals that the proposed model estimates similar but still different parameter values compared to the original Thurstonian IRT model, and this difference can be explained by the response time information. In addition, the proposed model successfully reflects the distance–difficulty relationship between the response time and the latent relative respondent position.

  Psychonomic Society, Jun. 2020, Behavior Research Methods, 52(3) (3), 1091 - 1107, English, International magazine

  [Refereed]

  Scientific journal


• Increase of reliability by incorporating response time into the paired-comparison psychological measurement

  Kensuke Okada, Kyosuke Bunji

  Much scholarly attention is focused on psychological measurement through the paired-comparison format, which is considered to be tolerant to systematic response bias. The Thurstonian D-diffusion item response theory model was recently proposed to incorporate response-time information in this context. Because reliability is a fundamental measurement property, this study used the above model to conduct a preliminary investigation into the extent of the reliability increase achieved when incorporating response-time information into paired-comparison psychological measurement. Under some realistic conditions, our simulation revealed a practically relevant (but not very large) degree of increase. The same type of increase was also found during our analysis of a real psychological dataset containing measurements for the Big Five traits. As such, this study produced evidence supporting the collection and utilization of response time when conducting paired-comparison psychological measurement.

  The Behaviormetric Society, Apr. 2020, Behaviormetrika, 48(1) (1), 169 - 177, English, International magazine

  [Refereed]

  Scientific journal


• New item response models for multi-alternative forced choice questionnaire data with response time

  Kyosuke Bunji

  The University of Tokyo, Mar. 2020, 博士学位論文（東京大学教育学研究科）, English

  Doctoral thesis


• Comparison of item selection algorithm in computerized adaptive testing with a time limit

  Kyosuke Bunji

  This study compared several item selection algorithms in a situation where a time limit exists in terms of estimation accuracy and item bank security. Simulation results show the following: (1) adjusting item information using the expected response time will improve both the estimation accuracy and the item bank security; (2) when item discrimination and expected response time are positively correlated, the mean numbers of the answered items decrease particularly in the algorithms which determine the next item according to the information; (3) under the condition in (2), algorithms that suppress the inflation of overlap rate demonstrate better estimation accuracy and; (4) the root-mean-square error and test information show slightly different results between algorithms.

  The Japan Association for Research on Testing, Jun. 2019, Japanese Journal for Research on Testing, 15(1) (1), 1 - 20, Japanese, Domestic magazine

  [Refereed]

  Scientific journal


• Item response and response time model for personality assessment via linear ballistic accumulation

  Kyosuke Bunji, Kensuke Okada

  On the basis of a combination of linear ballistic accumulation (LBA) and item response theory (IRT), this paper proposes a new class of item response models, namely LBA IRT, which incorporates the observed response time (RT) by means of LBA. Our main objective is to develop a simple yet effective alternative to the diffusion IRT model, which is one of best-known RT-incorporating IRT models that explicitly models the underlying psychological process of the elicited item response. Through a simulation study, we show that the proposed model enables us to obtain the corresponding parameter estimates compared with the diffusion IRT model while achieving a much faster convergence speed. Furthermore, the application of the proposed model to real personality measurement data indicates that it fits the data better than the diffusion IRT model in terms of its predictive performance. Thus, the proposed model exhibits good performance and promising modeling capabilities in terms of capturing the cognitive and psychometric processes underlying the observed data.

  Japanese Federation of Statistical Science Associations, Apr. 2019, Japanese Journal of Statistics and Data Science, 2(1) (1), 263 - 297, English, International magazine

  [Refereed]

  Scientific journal


• Evaluating reading support systems through reading skill test

  Teiko Arai, Kyosuke Bunji, Naoya Todo, Noriko H. Arai, Takuya Matsuzaki

  We propose a computer-based testing environment, Reading Skill Test, to measure the effects of various types of systematic reading support systems. We prove its validity, reliability and one-dimensionality using 31,000 subjects. The effects of furigana system on the 5th to 8th grade students are analyzed using this environment. Furigana is a widely used Japanese reading support system that has been believed to be beneficial especially for pupils. Despite our expectation, we have to conclude that furigana failed to improve pupils' reading significantly, and discuss why it did so.

  Jul. 2018, Proceedings of the 40th Annual Cognitive Science Society Meeting (CogSci 2018), 100 - 105, English

  [Refereed]

  International conference proceedings


• Complexities of text from the points of view of lexical and syntactic characteristics:Quantitative analysis of linguistic features of primary school textbooks

  Arai Teiko, Bunji Kyosuke, Ishihara Yuki, Matsuzaki Takuya, Kageura Kyo

  This paper analyses linguistic features of primary school textbooks for the penultimate and final grades (grades five and six) and junior high school textbooks for the first and second grades (grades one and two), in order to reveal factors affecting the so-called "primary-secondary" learning gap. We chose science textbooks and analysed their complexities from the points of view of lexical and syntactic characteristics. The analysis revealed that there is a clear gap in syntactic complexities of sentences between primary and secondary school textbooks. The analysis showed that the factors constitute the gap between primary and secondary school textbooks.

  The Mathematical Linguistic Society of Japan, Sep. 2017, Mathematical Linguistics, 31(2) (2), 144 - 159, Japanese, Domestic magazine

  [Refereed]

  Scientific journal


• Reading skill test to diagnose basic language skills in comparison to machines

  Noriko H. Arai, Naoya Todo, Teiko Arai, Kyosuke Bunji, Shingo Sugawara, Miwa Inuzuka, Takuya Matsuzaki, Koken Ozaki

  CORE A

  2017, Proceedings of the 39th Annual Cognitive Science Society Meeting (CogSci 2017), 1556 - 1561, English, International magazine

  [Refereed]

  International conference proceedings


• Modeling inter-item variance of item response theory : Application to essay rating

  Kyosuke Bunji

  This study proposes a graded response model including a new parameter, which represents rater effects affecting inter-item variance. The validity of this model was shown by parameter restoration simulation, in which artificial item response data were generated and calibrated under 12 conditions each. Another simulation study, which compares estimation accuracy of θ in the presented model and original graded response model, was conducted. Results indicated the proposed model can remove the rater effect. Using a rating experiment that induced the halo effect, it was shown that the new parameter wir can be regarded as a halo effect.

  The Behaviormetric Society, Sep. 2016, The Japanese journal of behaviormetrics, 43(2) (2), 181 - 195, Japanese, Domestic magazine

  [Refereed]

  Scientific journal

• Book Review: Matrix-Based Introduction to Multivariate Data Analysis: Second edition

  Kyosuke Bunji

  Jun. 2021, Japanese Journal for Research on Testing, 17(1) (1), 128 - 129, Japanese

  Book review


• Emotion Vocabulary Development in Early Childhood : Based on Item Response Theory

  Mai Hamana, Kyosuke Bunji

  最終版はこちら↓ 浜名真以, 分寺杏介 (2023). 項目反応理論を用いた幼児および小学校低学年用短縮版感情語彙尺度の開発. 教育心理学研究. 71(1). 51-61. https://doi.org/10.5926/jjep.71.51

  明治安田こころの健康財団, 2018, Research-aid paper of the Yasuda Life Welfare Foundation, 54, 105 - 114, Japanese, Domestic magazine

  Others


• The present and prospects of academic achievement tests for measuring children's ability: Toward evidence-based education policy

  Yoshiki Ishikawa, Hirotake Ito, Aya Uemura, Shin Tabata, Risako Toyama, Kyosuke Bunji, Takahiro Hoshino, Ryo Matsuoka, Kazuhiro Yamaguchi

  本稿では、就学期の子どもの認知能力を計測する目的で行われている「学力テスト」のあり方を展望し、今後の教育政策をエビデンスに基づくものに転換していくために、どのような学力テストのあり方が望ましいかを論じる。まずは国内外で実施された学力テストの動向を振り返り、その後平成27年から開始された「埼玉県・学力学習状況調査」を1つのモデルケースとして取り上げる。本稿の後半では、平成27年から開始された「埼玉県・学力学習状況調査」のデータの簡単な記述統計と分析を紹介するとともに、これと同時に行われた埼玉県戸田市での教員調査の結果も踏まえ、今後の改善点についても論じる。

  独立行政法人経済産業研究所, Mar. 2017, RIETI Policy Discussion Paper, 17-P-010, Japanese

  Technical report

• Statistical models and scaling techniques for forced-choice psychological measurement

  Kensuke Okada, Kyosuke Bunji, Keishi Nomura, Yoshito Tan, Hiroshi Shimizu, Koji E Kosugi

  The 52nd Annual Meeting of the Behaviormetric Society, Sep. 2024, Japanese, 2024_BMS_bunji_okada.pdf, No password, The Behaviormetric Society, Osaka University of Economics, Osaka, Japan, Japan, Domestic conference

  Public symposium

  添付ファイルのURL


• A method for presenting multiple-alternative personality measurement items to reduce cognitive load

  Kyosuke Bunji, Takeshi Sugiyama

  The 52nd Annual Meeting of the Behaviormetric Society, Sep. 2024, Japanese, 2024_BMS_bunji_sugiyama.pdf, No password, The Behaviormetric Society, Osaka University of Economics, Osaka, Japan, Japan, Domestic conference

  Oral presentation

  添付ファイルのURL


• Capturing the "difficult-to-answer" feeling towards psychological scales: A quantitative approach assessing individual subjectivity

  Kyosuke Bunji, Ayako Baba, Aya Fukushima

  The 88th Annual Convention of the Japanese Psychological Association, Sep. 2024, Japanese, 2024_JPA_Bunji_Baba_Fukushima.pdf, No password, The Japanese Psychological Association, Kumamoto-jo Hall, Kumamoto, Japan, Japan, Domestic conference

  Poster presentation

  添付ファイルのURL


• An investigation of the context effect in the multidimensional forced-choice personality measurement

  Kyosuke Bunji, Kensuke Okada

  IMPS 2024, Jul. 2024, English, IMPS_2024_Tuesday_RB101_Bunji.pdf, No password, Psychometric Society, Prague University of Economics and Business (Prague, Czech), Czech Republic, International conference

  Oral presentation

  添付ファイルのURL


• Past, present, and future of computer based testing

  Kyosuke Bunji

  17th Commemorative Lecture of the Japan Association for Research on Testing, Mar. 2024, Japanese, テスト学会セミナー2024_bunji.pdf, Published, No password, The Japan Association for Research on Testing, Online, Japan, Domestic conference

  [Invited]

  Public discourse

  添付ファイルのURL


• Do psychological scales measure clients' minds?: Focusing on "stumbling" in responses and support from psychologists

  Ayako Baba, Kyosuke Bunji, Aya Fukushima

  The 87th Annual Convention of the Japanese Psychological Association, Sep. 2023, Japanese, 日本心理学会2023_2D-033-PD.pdf, Published, No password, The Japanese Psychological Association, Kobe International Conference Center, Hyogo, Japan, Japan, Domestic conference

  Poster presentation

  添付ファイルのURL


• An examination of order effects in paired comparison psychological measurement

  Kyosuke Bunji

  The 51st Annual Meeting of the Behaviormetric Society, Aug. 2023, Japanese, 行動計量2023_bunji.pdf, Published, No password, The Behaviormetric Society, Aoyama Gakuin University, Tokyo, Japan, Japan, Domestic conference

  Oral presentation

  添付ファイルのURL


• An examination of the stability of paired comparison psychological measurement under different response methods

  Kyosuke Bunji, Kensuke Okada

  The 37th Annual Meeting of Japanese Society of Computational Statistics, Jun. 2023, Japanese, Japanese Society of Computational Statistics, Tokachi Plaza, Hokkaido, Japan, Japan, Domestic conference

  Oral presentation


• A Bayesian statistical approach to examining the comparability of CBT and PBT scores

  Kyosuke Bunji

  The 50th Annual Meeting of the Behaviormetric Society, Aug. 2022, Japanese, the Behaviormetric Society, Okinawa Shichoson Jichikaikan, Okinawa, Japan, Japan, Domestic conference

  Oral presentation


• An examination of the influence of anchor item selection methods in equating with common item designs

  Kyosuke Bunji

  The 19th Annual Meeting of the Japan Association for Research on Testing, Sep. 2021, Japanese, Japan Association for Research on Testing, Online, Japan, Domestic conference

  Oral presentation


• Detection of mental health problem using annual student health survey data

  Ayako Baba, Kyosuke Bunji

  The 85th Annual Convention of the Japanese Psychological Association, Sep. 2021, Japanese, 日本心理学会, オンライン, Japan, Domestic conference

  Poster presentation


• An extension of the LBA-IRT model to multidimensional multiple-alternative forced-choice personality measurement with response times

  Kyosuke Bunji, Kensuke Okada

  MathPsych/ICCM 2020, Jul. 2020, English, Society for Mathematical Psychology, オンライン, International conference

  Oral presentation


• An LBA-IRT model for Likert data

  Kyosuke Bunji, Kensuke Okada

  The 33rd Symposium of Japanese Society of Computational Statistics, Nov. 2019, Japanese, 日本計算機統計学会, 青山学院大学青山キャンパス（東京都渋谷区）, Japan, Domestic conference

  Oral presentation


• Development of a Children’s Emotion Vocabulary Scale using item response theory

  Mai Hamana, Kyosuke Bunji

  The 83rd Annual Convention of the Japanese Psychological Association, Sep. 2019, Japanese, Japanese Psychological Association, Ritsumeikan University, Osaka, Japan, Domestic conference

  Poster presentation


• An item response model for multidimensional multiple-alternative forced-choice data using response time

  Kyosuke Bunji, Kensuke Okada

  The 47th Annual Meeting of the Behaviormetric Society, Sep. 2019, Japanese, The Behaviormetric Society, Osaka University, Osaka, Japan, Japan, Domestic conference

  Oral presentation


• Cognitive process model for ordered categorical response and response time data for questionnaires

  Kyosuke Bunji, Kensuke Okada

  MathPsych/ICCM 2019, Jul. 2019, English, Le Centre Sheraton (Montreal, QC), Canada, International conference

  Oral presentation


• Observed-score reliability and its approximate index in paired-comparison Thurstonian IRT

  Kensuke Okada, Kyosuke Bunji

  IMPS 2019, Jul. 2019, English, Psychometric Society, International conference

  Oral presentation


• On parameter invariance in Thurstonian IRT model

  Kyosuke Bunji, Kensuke Okada

  The 32th Symposium of Japanese Society of Computational Statistics, Nov. 2018, Japanese, Japanese Society of Computational Statistics, Shiga University, Shiga, Japan, Japan, Domestic conference

  Oral presentation


• Performance evaluation of item selection algorithms considering item domain and answer time

  Naoya Todo, Kyosuke Bunji, Koken Ozaki

  The 46th Annual Meeting of the Behaviormetric Society, Sep. 2018, Japanese, The Behaviormetric Society, Keio University, Tokyo, Japan, Japan, Domestic conference

  Oral presentation


• An extension of linear ballistic accumulator model for rank data

  Kyosuek Bunji

  The 46th Annual Meeting of the Behaviormetric Society, Sep. 2018, Japanese, The Behaviormetric Society, Keio University, Tokyo, Japan, Japan, Domestic conference

  Oral presentation


• Modeling Forced-choice Version of Questionnaires on the Big Five Factors for Reducing Response Biases

  Kyosuke Bunji, Kensuke Okada

  MathPsych/ICCM 2018, Jul. 2018, English, Society for Mathematical Psychology, University of Wisconsin–Madison (Madison, Wisconsin), United States, International conference

  Oral presentation


• Extending the diffusion-IRT model to forced-choice response time data

  Kyosuke Bunji, Kensuke Okada

  IMPS 2018, Jul. 2018, English, Psychometric Society, Columbia University (New York City, USA), United States, International conference

  Oral presentation


• A new item response model using response time: efficient estimation method via linear ballistic accumulation

  Kyosuek Bunji, Kensuke Okada

  The 31st Symposium of Japanese Society of Computational Statistics, Nov. 2017, Japanese, Japanese Society of Computational Statistics, Wakayama Medical University, Wakayama, Japan, Japan, Domestic conference

  Oral presentation


• A model for analyzing paired comparison data using response time

  Kyosuke Bunji

  The 45th Annual Meeting of the Behaviormetric Society, Aug. 2017, Japanese, The Behaviormetric Society, University of Shizuoka, Shizuoka, Japan, Japan, Domestic conference

  Oral presentation


• Performance evaluation of item selection algorithms considering item domain and answer time

  Naoya Todo, Kyosuke Bunji, Koken Ozaki

  The 15th Annual Meeting of the Japan Association for Research on Testing, Aug. 2017, Japanese, The Japan Association for Research on Testing, Tohoku University, Miyagi, Japan, Japan, Domestic conference

  Oral presentation


• An exploratory study of the relationship between reading comprehension and reading, life, and study habits: using the Reading Skills Test

  Kyosuke Bunji, Noriko Arai

  The 15th Annual Meeting of the Japan Association for Research on Testing, Aug. 2017, Japanese, The Japan Association for Research on Testing, Tohoku Univeristy, Miyagi, Japan, Japan, Domestic conference

  Oral presentation


• New IRT Model Incorporating Response Time via Linear Ballistic Accumulation

  Kyosuke Bunji, Kensuke Okada

  MathPsych/ICCM 2017, Jul. 2017, English, The Society for Mathematical Psychology, University of Warwick (Coventry, United Kingdom), United Kingdom, International conference

  Poster presentation


• A quantitative analysis of text reading difficulty: A case study of elementary and junior high school science textbooks

  Teiko Arai, Kyosuke Bunji, Takuya Matsuzaki, Kyo Kageura

  IPSJ SIG Computers and the Humanities, May 2017, Japanese

  Poster presentation


• Reading Skills Test (RST): Its educational measurement properties and implications for educational practice

  Noriko Arai, Shingo Sugawara, Koken Ozaki, Miwa Inuzuka, Teiko Arai, Kyosuke Bunji, Hiroyuki Noguchi, Naoya Todo

  The 59th Annual Meeting of the Japanese Association for Educational Psychology, Oct. 2017, Japanese, The Japanese Association for Educational Psychology, Nagoya University, Aichi, Japan, Japan, Domestic conference

  Public symposium


• Factor structure in personality trait tests conducted in several countries

  Shino Sako, Yutaro Sakamoto, Shiho Imashiro, Kyosuke Bunji

  The 14th Annual Meeting of the Japan Association for Research on Testing, Sep. 2016, Japanese, The Japan Association for Research on Testing, The University of Electro-Communications, Tokyo, Japan, Japan, Domestic conference

  Oral presentation


• Proposal of a marginal model for linear combination of multiple traits on a multidimensional item response theory model

  Kyosuke Bunji, Takahiro Hoshino

  The 44th Annual Meeting of the Behaviormetric Society, Sep. 2016, Japanese, The Behaviormetric Society, Sapporo Gakuin University, Hokkaido, Japan, Japan, Domestic conference

  Oral presentation


• An item response model that incorporates rater bias affecting variance among raters and examinees

  Kyosuke Bunji

  The 43rd Annual Meeting of the Behaviormetric Society, Sep. 2015, Japanese, The Behaviormetric Society, Tokyo Metropolitan University, Tokyo, Japan, Japan, Domestic conference

  Poster presentation


• Impact of the question wording on social studies test: question setting considering the measuring intent of the examiner

  Kazuhiro Yasunaga, Kyosuke Bunji, Hiroyuki Ito, Yuji Mitobe

  The 57th Annual Meeting of the Japanese Association for Educational Psychology, Aug. 2015, Japanese, The Japanese Association for Educational Psychology, Japan, Domestic conference

  Poster presentation

• Japanese Society of Computational Statistics

  IRI


• The Japan Association for Research on Testing

  IRI


• The Behaviormetric Society

  IRI


• The Japanese Psychological Association

  IRI


• The Japanese Association of Education Psychology

  IRI

• Psychological Measurement with Response Bias-Robust Comparative Scales: Foundation Building and Development of Applications

  Kensuke Okada, Izumi Matsuda, Tetsuya Kawamoto, Kyosuke Bunji, Keishi Nomura

  Japan Society for the Promotion of Science, KAKENHI, Grants-in-Aid for Scientific Research (A), The University of Tokyo, Apr. 2025 - Mar. 2029, Coinvestigator


• Development of a Machine Learning Approach for Estimating Psychological Traits Using Diverse Paradata

  分寺 杏介

  Japan Society for the Promotion of Science, Grants-in-Aid for Scientific Research, Grant-in-Aid for Early-Career Scientists, Kobe University, Apr. 2024 - Mar. 2028, Principal investigator


• 非認知特性のスケーラブルな測定と利活用

  岡田 謙介, 分寺 杏介

  科学技術振興機構, AIP加速研究, Apr. 2025 - Mar. 2026, Coinvestigator

  本研究では、社会的望ましさバイアスの影響を抑えながら多数の対象者から効果的に非認知特性の測定を行うことができる、比較型測定に基づくテストの社会実装を行います。そのための技術開発と実証研究を進め、企業や教育の現場で実用化のためのケーススタディを行います。非認知特性の信頼性の高い測定を通じて、個人の特性に基づいた最適な人材配置やチーム構築、個別最適な指導を志向し、組織や社会の幸福度向上を目指します。


• Development of a method for detecting 'stumbling' in psychological scale responses using paradata in web surveys

  Kyosuke Bunji, Ayako Baba

  The Telecommunication Advancement Foundation, Grants for research, Kobe University, Apr. 2024 - Mar. 2026, Principal investigator

  Competitive research funding


• 情報セキュリティ教育ツールによる情報セキュリティ意識変容の調査に関する学術研究

  分寺 杏介

  LRM株式会社, 共同研究, Dec. 2024 - Nov. 2025, Principal investigator

  Industry academia cooperation


• Development of an adaptive multiple forced-choice psychological measurement using response time

  分寺 杏介

  Japan Society for the Promotion of Science, Grants-in-Aid for Scientific Research, Grant-in-Aid for Research Activity Start-up, Kobe University, 31 Aug. 2022 - 31 Mar. 2024, Principal investigator

  Competitive research funding


• Modeling the rater effect by considering cognitive processes within individuals

  Kyosuke Bunji

  Japan Society for the Promotion of Science, Grants-in-Aid for Scientific Research, Grant-in-Aid for JSPS Fellows, The University of Tokyo, 26 Apr. 2017 - 31 Mar. 2020, Principal investigator

  本研究の目的は，多様な評定者効果を統一的に表現する数理モデルを提案し，その性能を評価すること，また提案モデルを使用した実際の分析例を提示することであった． 本年度は前年度に引き続き，Linear Ballistic Accumulationモデル（LBA）に基づく項目反応モデルについての考察および，Thurstoneの比較判断の法則に基づくモデルの拡張に関する研究を中心に行った．本年度の研究としては，第一にLBA IRTモデルを多次元多肢選択項目に拡張するためのモデルの拡張を行った（業績4，論文投稿準備中）．Thurstoneの比較判断の法則を援用することにより，各選択肢の潜在的な効用を考慮したモデリングを行うことができると考えられる．また，LBAモデルをベースにすることで回答時間データを併せて用いることが可能となり，より豊かな情報を引き出すことが可能になると考えられる．将来的には，選択肢間での潜在的効用を促進・抑制しあう構造を取り入れることで，文脈効果を考慮したモデリングが可能になると期待される．第二にLBA IRTモデルをリッカート尺度などの順序データに適用するための拡張の研究を行った（業績5,6）．通常のLBA IRTモデルは二択の項目にしか適用できないため，一問あたりの情報量が限られてしまう．リッカート尺度は心理学に限らず様々な分野で広く用いられている手法であるため，本モデルの提案により，より一般的な場面においてもLBA IRTを適用することが可能となり，また二択の場合と比べてより情報量の多い分析が可能になると考えられる．

  Competitive research funding

• セキュリティ教育効果測定のためのテスト設計と性能評価〜信頼性・妥当性の観点から〜

  LRM株式会社

  Appearance, 第8回セキュリティ教育サミット, 20 Feb. 2025, General


• 指導助言者

  神戸大学附属中等教育学校

  Advisor, 2024年度授業研究会・公開授業, 08 Feb. 2025


• テストの未来：CBTからIBTヘ

  プロメトリック株式会社

  Contribution, 04 Jun. 2024

• Japanese Journal of Educational Psychology

  Japanese Journal of Educational Psychology

  Peer review etc


• Japanese Journal of Applied Statistics

  Japanese Journal of Applied Statistics

  Not contributing to international academic

  Peer review etc


• Journal of Information Processing

  Journal of Information Processing

  Not contributing to international academic

  Peer review etc


• Health Science Reports

  Health Science Reports

  International academic contribution

  Peer review etc


• The Japanese Journal of Psychology

  The Japanese Journal of Psychology

  Not contributing to international academic

  Peer review etc


• Proceedings of the Institute of Statistical Mathematics

  Proceedings of the Institute of Statistical Mathematics

  Not contributing to international academic

  Peer review etc


• Behaviormetrika

  Behaviormetrika

  International academic contribution

  Peer review etc


• The Japanese Journal of Behaviormetrics

  The Japanese Journal of Behaviormetrics

  Not contributing to international academic

  Peer review etc


• Educational and Psychological Measurement

  Educational and Psychological Measurement

  International academic contribution

  Peer review etc


• Behavior Research Methods

  Behavior Research Methods

  International academic contribution

  Peer review etc


• Japanese Journal for Research on Testing

  Japanese Journal for Research on Testing

  Not contributing to international academic

  Peer review etc


• Japanese Psychological Research

  Japanese Psychological Research

  International academic contribution

  Peer review etc

• 東京大学FFP（フューチャー・ファカルティ・プログラム）第９期修了

  Apr. 2017 - Jul. 2017