Multimodal Approach for Automatic Emotion Recognition Applied to the Tension Levels Study in TV Newscasts
This article addresses a multimodal approach to automatic emotion recognition in participants of TV newscasts (presenters, reporters, commentators and others) able to assist the tension levels study in narratives of events in this television genre. The methodology applies state-of-the-art computatio...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Associação Brasileira de Pesquisadores em Jornalismo
2015-12-01
|
| Series: | Brazilian Journalism Research |
| Subjects: | |
| Online Access: | https://bjr.sbpjor.org.br/bjr/article/view/850 |
| _version_ | 1819142176621199360 |
|---|---|
| author | Moisés Henrique Ramos Pereira Flávio Luis Cardeal Pádua Giani David Silva |
| author_facet | Moisés Henrique Ramos Pereira Flávio Luis Cardeal Pádua Giani David Silva |
| author_sort | Moisés Henrique Ramos Pereira |
| collection | DOAJ |
| description | This article addresses a multimodal approach to automatic emotion recognition in participants of TV newscasts (presenters, reporters, commentators and others) able to assist the tension levels study in narratives of events in this television genre. The methodology applies state-of-the-art computational methods to process and analyze facial expressions, as well as speech signals. The proposed approach contributes to semiodiscoursive study of TV newscasts and their enunciative praxis, assisting, for example, the identification of the communication strategy of these programs. To evaluate the effectiveness of the proposed approach was applied it in a video related to a report displayed on a Brazilian TV newscast great popularity in the state of Minas Gerais. The experimental results are promising on the recognition of emotions on the facial expressions of tele journalists and are in accordance with the distribution of audiovisual indicators extracted over a TV newscast, demonstrating the potential of the approach to support the TV journalistic discourse analysis.This article addresses a multimodal approach to automatic emotion recognition in participants of TV newscasts (presenters, reporters, commentators and others) able to assist the tension levels study in narratives of events in this television genre. The methodology applies state-of-the-art computational methods to process and analyze facial expressions, as well as speech signals. The proposed approach contributes to semiodiscoursive study of TV newscasts and their enunciative praxis, assisting, for example, the identification of the communication strategy of these programs. To evaluate the effectiveness of the proposed approach was applied it in a video related to a report displayed on a Brazilian TV newscast great popularity in the state of Minas Gerais. The experimental results are promising on the recognition of emotions on the facial expressions of tele journalists and are in accordance with the distribution of audiovisual indicators extracted over a TV newscast, demonstrating the potential of the approach to support the TV journalistic discourse analysis. |
| first_indexed | 2024-12-22T12:06:11Z |
| format | Article |
| id | doaj.art-1b923e1e669b471ea81e2016c9c8fc70 |
| institution | Directory Open Access Journal |
| issn | 1808-4079 1981-9854 |
| language | English |
| last_indexed | 2024-12-22T12:06:11Z |
| publishDate | 2015-12-01 |
| publisher | Associação Brasileira de Pesquisadores em Jornalismo |
| record_format | Article |
| series | Brazilian Journalism Research |
| spelling | doaj.art-1b923e1e669b471ea81e2016c9c8fc702022-12-21T18:26:25ZengAssociação Brasileira de Pesquisadores em JornalismoBrazilian Journalism Research1808-40791981-98542015-12-0111214616710.25200/BJR.v11n2.2015.850598Multimodal Approach for Automatic Emotion Recognition Applied to the Tension Levels Study in TV NewscastsMoisés Henrique Ramos Pereira0Flávio Luis Cardeal Pádua1Giani David Silva2Centro Federal de Educação Tecnológica de Minas GeraisCentro Federal de Educação Tecnológica de Minas GeraisCentro Federal de Educação Tecnológica de Minas GeraisThis article addresses a multimodal approach to automatic emotion recognition in participants of TV newscasts (presenters, reporters, commentators and others) able to assist the tension levels study in narratives of events in this television genre. The methodology applies state-of-the-art computational methods to process and analyze facial expressions, as well as speech signals. The proposed approach contributes to semiodiscoursive study of TV newscasts and their enunciative praxis, assisting, for example, the identification of the communication strategy of these programs. To evaluate the effectiveness of the proposed approach was applied it in a video related to a report displayed on a Brazilian TV newscast great popularity in the state of Minas Gerais. The experimental results are promising on the recognition of emotions on the facial expressions of tele journalists and are in accordance with the distribution of audiovisual indicators extracted over a TV newscast, demonstrating the potential of the approach to support the TV journalistic discourse analysis.This article addresses a multimodal approach to automatic emotion recognition in participants of TV newscasts (presenters, reporters, commentators and others) able to assist the tension levels study in narratives of events in this television genre. The methodology applies state-of-the-art computational methods to process and analyze facial expressions, as well as speech signals. The proposed approach contributes to semiodiscoursive study of TV newscasts and their enunciative praxis, assisting, for example, the identification of the communication strategy of these programs. To evaluate the effectiveness of the proposed approach was applied it in a video related to a report displayed on a Brazilian TV newscast great popularity in the state of Minas Gerais. The experimental results are promising on the recognition of emotions on the facial expressions of tele journalists and are in accordance with the distribution of audiovisual indicators extracted over a TV newscast, demonstrating the potential of the approach to support the TV journalistic discourse analysis.https://bjr.sbpjor.org.br/bjr/article/view/850TV NewscastsTension LevelsEmotion Recognition. SpeechFacial Expressions |
| spellingShingle | Moisés Henrique Ramos Pereira Flávio Luis Cardeal Pádua Giani David Silva Multimodal Approach for Automatic Emotion Recognition Applied to the Tension Levels Study in TV Newscasts Brazilian Journalism Research TV Newscasts Tension Levels Emotion Recognition. Speech Facial Expressions |
| title | Multimodal Approach for Automatic Emotion Recognition Applied to the Tension Levels Study in TV Newscasts |
| title_full | Multimodal Approach for Automatic Emotion Recognition Applied to the Tension Levels Study in TV Newscasts |
| title_fullStr | Multimodal Approach for Automatic Emotion Recognition Applied to the Tension Levels Study in TV Newscasts |
| title_full_unstemmed | Multimodal Approach for Automatic Emotion Recognition Applied to the Tension Levels Study in TV Newscasts |
| title_short | Multimodal Approach for Automatic Emotion Recognition Applied to the Tension Levels Study in TV Newscasts |
| title_sort | multimodal approach for automatic emotion recognition applied to the tension levels study in tv newscasts |
| topic | TV Newscasts Tension Levels Emotion Recognition. Speech Facial Expressions |
| url | https://bjr.sbpjor.org.br/bjr/article/view/850 |
| work_keys_str_mv | AT moiseshenriqueramospereira multimodalapproachforautomaticemotionrecognitionappliedtothetensionlevelsstudyintvnewscasts AT flavioluiscardealpadua multimodalapproachforautomaticemotionrecognitionappliedtothetensionlevelsstudyintvnewscasts AT gianidavidsilva multimodalapproachforautomaticemotionrecognitionappliedtothetensionlevelsstudyintvnewscasts |