Estimation of Interpersonal Relationships in Movies

Yuta OHWATARI; Takahiro KAWAMURA; Yuichi SEI; Yasuyuki TAHARA; Akihiko OHSUGA

doi:10.1587/transinf.2015MUP0015

Estimation of Interpersonal Relationships in Movies

Yuta OHWATARI, Takahiro KAWAMURA, Yuichi SEI, Yasuyuki TAHARA, Akihiko OHSUGA

Full Text Views

0

Cite this

Summary :

In many movies, social conditions and awareness of the issues of the times are depicted in any form. Even if fantasy and science fiction are works far from reality, the character relationship does mirror the real world. Therefore, we try to understand social conditions of the real world by analyzing the movie. As a way to analyze the movies, we propose a method of estimating interpersonal relationships of the characters, using a machine learning technique called Markov Logic Network (MLN) from movie script databases on the Web. The MLN is a probabilistic logic network that can describe the relationships between characters, which are not necessarily satisfied on every line. In experiments, we confirmed that our proposed method can estimate favors between the characters in a movie with F-measure of 58.7%. Finally, by comparing the relationships with social indicators, we discussed the relevance of the movies to the real world.

Publication: IEICE TRANSACTIONS on Information Vol.E99-D No.1 pp.128-137

Publication Date: 2016/01/01

Publicized: 2015/11/05

Online ISSN: 1745-1361

DOI: 10.1587/transinf.2015MUP0015

Type of Manuscript: Special Section PAPER (Special Section on Enriched Multimedia---Creation of a New Society through Value-added Multimedia Content---)

Category

Authors

Yuta OHWATARI
  The University of Electro-Communications
Takahiro KAWAMURA
  The University of Electro-Communications
Yuichi SEI
  The University of Electro-Communications
Yasuyuki TAHARA
  The University of Electro-Communications
Akihiko OHSUGA
  The University of Electro-Communications

Keyword

Markov Logic Network, semantic analysis, Open Movie Database, perception/cognitive metrics

Cite this

Copy

Yuta OHWATARI, Takahiro KAWAMURA, Yuichi SEI, Yasuyuki TAHARA, Akihiko OHSUGA, "Estimation of Interpersonal Relationships in Movies" in IEICE TRANSACTIONS on Information, vol. E99-D, no. 1, pp. 128-137, January 2016, doi: 10.1587/transinf.2015MUP0015.
Abstract: In many movies, social conditions and awareness of the issues of the times are depicted in any form. Even if fantasy and science fiction are works far from reality, the character relationship does mirror the real world. Therefore, we try to understand social conditions of the real world by analyzing the movie. As a way to analyze the movies, we propose a method of estimating interpersonal relationships of the characters, using a machine learning technique called Markov Logic Network (MLN) from movie script databases on the Web. The MLN is a probabilistic logic network that can describe the relationships between characters, which are not necessarily satisfied on every line. In experiments, we confirmed that our proposed method can estimate favors between the characters in a movie with F-measure of 58.7%. Finally, by comparing the relationships with social indicators, we discussed the relevance of the movies to the real world.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2015MUP0015/_p

Copy

@ARTICLE{e99-d_1_128,
author={Yuta OHWATARI, Takahiro KAWAMURA, Yuichi SEI, Yasuyuki TAHARA, Akihiko OHSUGA, },
journal={IEICE TRANSACTIONS on Information},
title={Estimation of Interpersonal Relationships in Movies},
year={2016},
volume={E99-D},
number={1},
pages={128-137},
abstract={In many movies, social conditions and awareness of the issues of the times are depicted in any form. Even if fantasy and science fiction are works far from reality, the character relationship does mirror the real world. Therefore, we try to understand social conditions of the real world by analyzing the movie. As a way to analyze the movies, we propose a method of estimating interpersonal relationships of the characters, using a machine learning technique called Markov Logic Network (MLN) from movie script databases on the Web. The MLN is a probabilistic logic network that can describe the relationships between characters, which are not necessarily satisfied on every line. In experiments, we confirmed that our proposed method can estimate favors between the characters in a movie with F-measure of 58.7%. Finally, by comparing the relationships with social indicators, we discussed the relevance of the movies to the real world.},
keywords={},
doi={10.1587/transinf.2015MUP0015},
ISSN={1745-1361},
month={January},}

Copy

TY - JOUR
TI - Estimation of Interpersonal Relationships in Movies
T2 - IEICE TRANSACTIONS on Information
SP - 128
EP - 137
AU - Yuta OHWATARI
AU - Takahiro KAWAMURA
AU - Yuichi SEI
AU - Yasuyuki TAHARA
AU - Akihiko OHSUGA
PY - 2016
DO - 10.1587/transinf.2015MUP0015
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E99-D
IS - 1
JA - IEICE TRANSACTIONS on Information
Y1 - January 2016
AB - In many movies, social conditions and awareness of the issues of the times are depicted in any form. Even if fantasy and science fiction are works far from reality, the character relationship does mirror the real world. Therefore, we try to understand social conditions of the real world by analyzing the movie. As a way to analyze the movies, we propose a method of estimating interpersonal relationships of the characters, using a machine learning technique called Markov Logic Network (MLN) from movie script databases on the Web. The MLN is a probabilistic logic network that can describe the relationships between characters, which are not necessarily satisfied on every line. In experiments, we confirmed that our proposed method can estimate favors between the characters in a movie with F-measure of 58.7%. Finally, by comparing the relationships with social indicators, we discussed the relevance of the movies to the real world.
ER -