Recognizing induced emotions of movie audiences: are induced and perceived emotions the same?

Leimin Tian, Michal Muszynski, Catherine Lai, Johanna D. Moore, Theodoras Kostoulas, Patrizia Lombardo, Thierry Pun, Guillaume Chanel

Research output: Chapter in Book/Report/Conference proceedingConference PaperResearch

Abstract

Predicting the emotional response of movie audiences to affective movie content is a challenging task in affective computing. Previous work has focused on using audiovisual movie content to predict movie induced emotions. However, the relationship between the audience's perceptions of the affective movie content (perceived emotions) and the emotions evoked in the audience (induced emotions) remains unexplored. In this work, we address the relationship between perceived and induced emotions in movies, and identify features and modelling approaches effective for predicting movie induced emotions. First, we extend the LIRIS-ACCEDE database by annotating perceived emotions in a crowd-sourced manner, and find that perceived and induced emotions are not always consistent. Second, we show that dialogue events and aesthetic highlights are effective predictors of movie induced emotions. In addition to movie based features, we also study physiological and behavioural measurements of audiences. Our experiments show that induced emotion recognition can benefit from including temporal context and from including multimodal information. Our study bridges the gap between affective content analysis and induced emotion prediction.

Original languageEnglish
Title of host publicationThe 7th International Conference on Affective Computing and Intelligent Interaction (ACII 2017)
Subtitle of host publicationSan Antonio, Texas October 23-26, 2017
EditorsHayley Hung, Emily Mower Provost, Mohammad Soleymani
Place of PublicationPiscataway NJ USA
PublisherIEEE, Institute of Electrical and Electronics Engineers
Pages28-35
Number of pages8
ISBN (Electronic)9781538605639
ISBN (Print)9781538605646
DOIs
Publication statusPublished - 2017
Externally publishedYes
EventInternational Conference on Affective Computing and Intelligent Interaction 2017 - San Antonio, United States of America
Duration: 23 Oct 201726 Oct 2017
Conference number: 7th
http://acii2017.org/Home

Conference

ConferenceInternational Conference on Affective Computing and Intelligent Interaction 2017
Abbreviated titleACII 2017
CountryUnited States of America
CitySan Antonio
Period23/10/1726/10/17
Internet address

Cite this

Tian, L., Muszynski, M., Lai, C., Moore, J. D., Kostoulas, T., Lombardo, P., ... Chanel, G. (2017). Recognizing induced emotions of movie audiences: are induced and perceived emotions the same? In H. Hung, E. Mower Provost, & M. Soleymani (Eds.), The 7th International Conference on Affective Computing and Intelligent Interaction (ACII 2017): San Antonio, Texas October 23-26, 2017 (pp. 28-35). Piscataway NJ USA: IEEE, Institute of Electrical and Electronics Engineers. https://doi.org/10.1109/ACII.2017.8273575
Tian, Leimin ; Muszynski, Michal ; Lai, Catherine ; Moore, Johanna D. ; Kostoulas, Theodoras ; Lombardo, Patrizia ; Pun, Thierry ; Chanel, Guillaume. / Recognizing induced emotions of movie audiences : are induced and perceived emotions the same?. The 7th International Conference on Affective Computing and Intelligent Interaction (ACII 2017): San Antonio, Texas October 23-26, 2017. editor / Hayley Hung ; Emily Mower Provost ; Mohammad Soleymani. Piscataway NJ USA : IEEE, Institute of Electrical and Electronics Engineers, 2017. pp. 28-35
@inproceedings{8ec4633c7f0f4424bae55a1254998d38,
title = "Recognizing induced emotions of movie audiences: are induced and perceived emotions the same?",
abstract = "Predicting the emotional response of movie audiences to affective movie content is a challenging task in affective computing. Previous work has focused on using audiovisual movie content to predict movie induced emotions. However, the relationship between the audience's perceptions of the affective movie content (perceived emotions) and the emotions evoked in the audience (induced emotions) remains unexplored. In this work, we address the relationship between perceived and induced emotions in movies, and identify features and modelling approaches effective for predicting movie induced emotions. First, we extend the LIRIS-ACCEDE database by annotating perceived emotions in a crowd-sourced manner, and find that perceived and induced emotions are not always consistent. Second, we show that dialogue events and aesthetic highlights are effective predictors of movie induced emotions. In addition to movie based features, we also study physiological and behavioural measurements of audiences. Our experiments show that induced emotion recognition can benefit from including temporal context and from including multimodal information. Our study bridges the gap between affective content analysis and induced emotion prediction.",
author = "Leimin Tian and Michal Muszynski and Catherine Lai and Moore, {Johanna D.} and Theodoras Kostoulas and Patrizia Lombardo and Thierry Pun and Guillaume Chanel",
year = "2017",
doi = "10.1109/ACII.2017.8273575",
language = "English",
isbn = "9781538605646",
pages = "28--35",
editor = "Hung, {Hayley } and {Mower Provost}, {Emily } and Soleymani, {Mohammad }",
booktitle = "The 7th International Conference on Affective Computing and Intelligent Interaction (ACII 2017)",
publisher = "IEEE, Institute of Electrical and Electronics Engineers",
address = "United States of America",

}

Tian, L, Muszynski, M, Lai, C, Moore, JD, Kostoulas, T, Lombardo, P, Pun, T & Chanel, G 2017, Recognizing induced emotions of movie audiences: are induced and perceived emotions the same? in H Hung, E Mower Provost & M Soleymani (eds), The 7th International Conference on Affective Computing and Intelligent Interaction (ACII 2017): San Antonio, Texas October 23-26, 2017. IEEE, Institute of Electrical and Electronics Engineers, Piscataway NJ USA, pp. 28-35, International Conference on Affective Computing and Intelligent Interaction 2017, San Antonio, United States of America, 23/10/17. https://doi.org/10.1109/ACII.2017.8273575

Recognizing induced emotions of movie audiences : are induced and perceived emotions the same? / Tian, Leimin; Muszynski, Michal; Lai, Catherine; Moore, Johanna D.; Kostoulas, Theodoras; Lombardo, Patrizia; Pun, Thierry; Chanel, Guillaume.

The 7th International Conference on Affective Computing and Intelligent Interaction (ACII 2017): San Antonio, Texas October 23-26, 2017. ed. / Hayley Hung; Emily Mower Provost; Mohammad Soleymani. Piscataway NJ USA : IEEE, Institute of Electrical and Electronics Engineers, 2017. p. 28-35.

Research output: Chapter in Book/Report/Conference proceedingConference PaperResearch

TY - GEN

T1 - Recognizing induced emotions of movie audiences

T2 - are induced and perceived emotions the same?

AU - Tian, Leimin

AU - Muszynski, Michal

AU - Lai, Catherine

AU - Moore, Johanna D.

AU - Kostoulas, Theodoras

AU - Lombardo, Patrizia

AU - Pun, Thierry

AU - Chanel, Guillaume

PY - 2017

Y1 - 2017

N2 - Predicting the emotional response of movie audiences to affective movie content is a challenging task in affective computing. Previous work has focused on using audiovisual movie content to predict movie induced emotions. However, the relationship between the audience's perceptions of the affective movie content (perceived emotions) and the emotions evoked in the audience (induced emotions) remains unexplored. In this work, we address the relationship between perceived and induced emotions in movies, and identify features and modelling approaches effective for predicting movie induced emotions. First, we extend the LIRIS-ACCEDE database by annotating perceived emotions in a crowd-sourced manner, and find that perceived and induced emotions are not always consistent. Second, we show that dialogue events and aesthetic highlights are effective predictors of movie induced emotions. In addition to movie based features, we also study physiological and behavioural measurements of audiences. Our experiments show that induced emotion recognition can benefit from including temporal context and from including multimodal information. Our study bridges the gap between affective content analysis and induced emotion prediction.

AB - Predicting the emotional response of movie audiences to affective movie content is a challenging task in affective computing. Previous work has focused on using audiovisual movie content to predict movie induced emotions. However, the relationship between the audience's perceptions of the affective movie content (perceived emotions) and the emotions evoked in the audience (induced emotions) remains unexplored. In this work, we address the relationship between perceived and induced emotions in movies, and identify features and modelling approaches effective for predicting movie induced emotions. First, we extend the LIRIS-ACCEDE database by annotating perceived emotions in a crowd-sourced manner, and find that perceived and induced emotions are not always consistent. Second, we show that dialogue events and aesthetic highlights are effective predictors of movie induced emotions. In addition to movie based features, we also study physiological and behavioural measurements of audiences. Our experiments show that induced emotion recognition can benefit from including temporal context and from including multimodal information. Our study bridges the gap between affective content analysis and induced emotion prediction.

UR - http://www.scopus.com/inward/record.url?scp=85041192587&partnerID=8YFLogxK

U2 - 10.1109/ACII.2017.8273575

DO - 10.1109/ACII.2017.8273575

M3 - Conference Paper

SN - 9781538605646

SP - 28

EP - 35

BT - The 7th International Conference on Affective Computing and Intelligent Interaction (ACII 2017)

A2 - Hung, Hayley

A2 - Mower Provost, Emily

A2 - Soleymani, Mohammad

PB - IEEE, Institute of Electrical and Electronics Engineers

CY - Piscataway NJ USA

ER -

Tian L, Muszynski M, Lai C, Moore JD, Kostoulas T, Lombardo P et al. Recognizing induced emotions of movie audiences: are induced and perceived emotions the same? In Hung H, Mower Provost E, Soleymani M, editors, The 7th International Conference on Affective Computing and Intelligent Interaction (ACII 2017): San Antonio, Texas October 23-26, 2017. Piscataway NJ USA: IEEE, Institute of Electrical and Electronics Engineers. 2017. p. 28-35 https://doi.org/10.1109/ACII.2017.8273575