Computational models of aesthetic appreciation for literary and visual arts

2017 Fiscal Year Final Research Report

• Project/Area Number: 15K12045
• Research Category: Grant-in-Aid for Challenging Exploratory Research
• Allocation Type: Multi-year Fund
• Research Field: Cognitive science
• Research Institution: The University of Electro-Communications
• Principal Investigator: Utsumi Akira 電気通信大学, 大学院情報理工学研究科, 教授 (30251664)
• Project Period (FY): 2015-04-01 – 2018-03-31
• Keywords: 審美的判断 / ベクトル空間モデル / 視覚芸術 / 言語芸術

Outline of Final Research Achievements

In this project, we attempted to develop computational models for aesthetic appreciation and judgment for Western paintings as visual arts and metaphors as literary arts. For visual arts, we collected a large dateset of human aesthetic judgments and found that some factors for aesthetic judgment can be predicted by vector representations of painting images. For literary arts, we proposed a computational method for generating metaphors using a vector space model and demonstrated that the proposed method can generate more fresh (or innovative) metaphors than the original ones used in literary works.

Free Research Field

認知科学