Assessment System of Presentation Slide Design Using Visual and Structural Features

Shengzhou YI; Junichiro MATSUGAMI; Toshihiko YAMASAKI

doi:10.1587/transinf.2021HCK0001

Assessment System of Presentation Slide Design Using Visual and Structural Features

Shengzhou YI, Junichiro MATSUGAMI, Toshihiko YAMASAKI

Full Text Views

0

Cite this

Summary :

Developing well-designed presentation slides is challenging for many people, especially novices. The ability to build high quality slideshows is becoming more important in society. In this study, a neural network was used to identify novice vs. well-designed presentation slides based on visual and structural features. For such a purpose, a dataset containing 1,080 slide pairs was newly constructed. One of each pair was created by a novice, and the other was the improved one by the same person according to the experts' advice. Ten checkpoints frequently pointed out by professional consultants were extracted and set as prediction targets. The intrinsic problem was that the label distribution was imbalanced, because only a part of the samples had corresponding design problems. Therefore, re-sampling methods for addressing class imbalance were applied to improve the accuracy of the proposed model. Furthermore, we combined the target task with an assistant task for transfer and multi-task learning, which helped the proposed model achieve better performance. After the optimal settings were used for each checkpoint, the average accuracy of the proposed model rose up to 81.79%. With the advice provided by our assessment system, the novices significantly improved their slide design.

Publication: IEICE TRANSACTIONS on Information Vol.E105-D No.3 pp.587-596

Publication Date: 2022/03/01

Publicized: 2021/12/01

Online ISSN: 1745-1361

DOI: 10.1587/transinf.2021HCK0001

Type of Manuscript: Special Section PAPER (Special Section on Human Communication IV)

Category

Authors

Shengzhou YI
  The University of Tokyo
Junichiro MATSUGAMI
  Rubato Co., Ltd.
Toshihiko YAMASAKI
  The University of Tokyo

Keyword

presentation slide, class imbalance, feature fusion, transfer learning, multi-task learning

Cite this

Copy

Shengzhou YI, Junichiro MATSUGAMI, Toshihiko YAMASAKI, "Assessment System of Presentation Slide Design Using Visual and Structural Features" in IEICE TRANSACTIONS on Information, vol. E105-D, no. 3, pp. 587-596, March 2022, doi: 10.1587/transinf.2021HCK0001.
Abstract: Developing well-designed presentation slides is challenging for many people, especially novices. The ability to build high quality slideshows is becoming more important in society. In this study, a neural network was used to identify novice vs. well-designed presentation slides based on visual and structural features. For such a purpose, a dataset containing 1,080 slide pairs was newly constructed. One of each pair was created by a novice, and the other was the improved one by the same person according to the experts' advice. Ten checkpoints frequently pointed out by professional consultants were extracted and set as prediction targets. The intrinsic problem was that the label distribution was imbalanced, because only a part of the samples had corresponding design problems. Therefore, re-sampling methods for addressing class imbalance were applied to improve the accuracy of the proposed model. Furthermore, we combined the target task with an assistant task for transfer and multi-task learning, which helped the proposed model achieve better performance. After the optimal settings were used for each checkpoint, the average accuracy of the proposed model rose up to 81.79%. With the advice provided by our assessment system, the novices significantly improved their slide design.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2021HCK0001/_p

Copy

@ARTICLE{e105-d_3_587,
author={Shengzhou YI, Junichiro MATSUGAMI, Toshihiko YAMASAKI, },
journal={IEICE TRANSACTIONS on Information},
title={Assessment System of Presentation Slide Design Using Visual and Structural Features},
year={2022},
volume={E105-D},
number={3},
pages={587-596},
abstract={Developing well-designed presentation slides is challenging for many people, especially novices. The ability to build high quality slideshows is becoming more important in society. In this study, a neural network was used to identify novice vs. well-designed presentation slides based on visual and structural features. For such a purpose, a dataset containing 1,080 slide pairs was newly constructed. One of each pair was created by a novice, and the other was the improved one by the same person according to the experts' advice. Ten checkpoints frequently pointed out by professional consultants were extracted and set as prediction targets. The intrinsic problem was that the label distribution was imbalanced, because only a part of the samples had corresponding design problems. Therefore, re-sampling methods for addressing class imbalance were applied to improve the accuracy of the proposed model. Furthermore, we combined the target task with an assistant task for transfer and multi-task learning, which helped the proposed model achieve better performance. After the optimal settings were used for each checkpoint, the average accuracy of the proposed model rose up to 81.79%. With the advice provided by our assessment system, the novices significantly improved their slide design.},
keywords={},
doi={10.1587/transinf.2021HCK0001},
ISSN={1745-1361},
month={March},}

Copy

TY - JOUR
TI - Assessment System of Presentation Slide Design Using Visual and Structural Features
T2 - IEICE TRANSACTIONS on Information
SP - 587
EP - 596
AU - Shengzhou YI
AU - Junichiro MATSUGAMI
AU - Toshihiko YAMASAKI
PY - 2022
DO - 10.1587/transinf.2021HCK0001
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E105-D
IS - 3
JA - IEICE TRANSACTIONS on Information
Y1 - March 2022
AB - Developing well-designed presentation slides is challenging for many people, especially novices. The ability to build high quality slideshows is becoming more important in society. In this study, a neural network was used to identify novice vs. well-designed presentation slides based on visual and structural features. For such a purpose, a dataset containing 1,080 slide pairs was newly constructed. One of each pair was created by a novice, and the other was the improved one by the same person according to the experts' advice. Ten checkpoints frequently pointed out by professional consultants were extracted and set as prediction targets. The intrinsic problem was that the label distribution was imbalanced, because only a part of the samples had corresponding design problems. Therefore, re-sampling methods for addressing class imbalance were applied to improve the accuracy of the proposed model. Furthermore, we combined the target task with an assistant task for transfer and multi-task learning, which helped the proposed model achieve better performance. After the optimal settings were used for each checkpoint, the average accuracy of the proposed model rose up to 81.79%. With the advice provided by our assessment system, the novices significantly improved their slide design.
ER -