研究業績リスト
ジャーナル論文 - rm_published_papers: International Conference Proceedings
公開済 11/2025
Proceedings of the 13th International Conference on Human-Agent Interaction (HAI'25)
ジャーナル論文 - rm_published_papers: International Conference Proceedings
公開済 11/2025
Proceedings of the 13th International Conference on Human-Agent Interaction (HAI'25)
ジャーナル論文 - rm_published_papers: International Conference Proceedings
公開済 11/2025
Proceedings of the 13th International Conference on Human-Agent Interaction (HAI'25)
ジャーナル論文 - rm_published_papers: Others
公開済 11/2025
Proceedings of the 13th International Conference on Human-Agent Interaction (HAI'25)
ジャーナル論文 - rm_published_papers: Scientific Journal
Computational analysis of individual differences in metaphor comprehension and cognitive abilities
公開済 10/2025
Thinking Skills and Creativity, 59, 101997 - 101997
ジャーナル論文 - rm_published_papers: Symposium
公開済 09/2025
日本認知科学会第42回大会発表論文集, 360 - 363
ジャーナル論文 - rm_published_papers: International Conference Proceedings
公開済 07/2025
Proceedings of the 47th Annual Meeting of the Cognitive Science Society (CogSci2025)
ジャーナル論文 - rm_published_papers: Scientific Journal
公開済 09/2024
Thinking Skills and Creativity, 53, 101606 - 101606
ジャーナル論文 - rm_published_papers: Scientific Journal
Performance evaluation of automated scoring for the descriptive similarity response task
公開済 14/03/2024
Scientific Reports, 14, 1
Abstract
We examined whether a machine-learning-based automated scoring system can mimic the human similarity task performance. We trained a bidirectional encoder representations from transformer-model based on the semantic similarity test (SST), which presented participants with a word pair and asked them to write about how the two concepts were similar. In Experiment 1, based on the fivefold cross validation, we showed the model trained on the combination of the responses (N = 1600) and classification criteria (which is the rubric of the SST; N = 616) scored the correct labels with 83% accuracy. In Experiment 2, using the test data obtained from different participants in different timing from Experiment 1, we showed the models trained on the responses alone and the combination of responses and classification criteria scored the correct labels in 80% accuracy. In addition, human–model scoring showed inter-rater reliability of 0.63, which was almost the same as that of human–human scoring (0.67 to 0.72). These results suggest that the machine learning model can reach human-level performance in scoring the Japanese version of the SST.
ジャーナル論文 - rm_published_papers: Scientific Journal
公開済 03/2024
人工知能, 39, 2, 163 - 170