Eintrag weiter verarbeiten
Contextual and active learning-based affect-sensing from virtual drama improvisation
Gespeichert in:
Zeitschriftentitel: | ACM Transactions on Speech and Language Processing |
---|---|
Personen und Körperschaften: | |
In: | ACM Transactions on Speech and Language Processing, 9, 2013, 4, S. 1-25 |
Format: | E-Article |
Sprache: | Englisch |
veröffentlicht: |
Association for Computing Machinery (ACM)
|
Schlagwörter: |
author_facet |
Zhang, Li Zhang, Li |
---|---|
author |
Zhang, Li |
spellingShingle |
Zhang, Li ACM Transactions on Speech and Language Processing Contextual and active learning-based affect-sensing from virtual drama improvisation Computational Mathematics Computer Science (miscellaneous) |
author_sort |
zhang, li |
spelling |
Zhang, Li 1550-4875 1550-4883 Association for Computing Machinery (ACM) Computational Mathematics Computer Science (miscellaneous) http://dx.doi.org/10.1145/2407736.2407738 <jats:p>Affect interpretation from open-ended drama improvisation is a challenging task. This article describes experiments in using latent semantic analysis to identify discussion themes and potential target audiences for those improvisational inputs without strong affect indicators. A context-based affect-detection is also implemented using a supervised neural network with the consideration of emotional contexts of most intended audiences, sentence types, and interpersonal relationships. In order to go beyond the constraints of predefined scenarios and improve the system's robustness, min-margin-based active learning is implemented. This active learning algorithm also shows great potential in dealing with imbalanced affect classifications. Evaluation results indicated that the context-based affect detection achieved an averaged precision of 0.826 and an averaged recall of 0.813 for affect detection of the test inputs from the Crohn's disease scenario using three emotion labels: positive, negative, and neutral, and an averaged precision of 0.868 and an average recall of 0.876 for the test inputs from the school bullying scenario. Moreover, experimental evaluation on a benchmark data set for active learning demonstrated that active learning was able to greatly reduce human annotation efforts for the training of affect detection, and also showed promising robustness in dealing with open-ended example inputs beyond the improvisation of the chosen scenarios.</jats:p> Contextual and active learning-based affect-sensing from virtual drama improvisation ACM Transactions on Speech and Language Processing |
doi_str_mv |
10.1145/2407736.2407738 |
facet_avail |
Online |
finc_class_facet |
Mathematik Informatik |
format |
ElectronicArticle |
fullrecord |
blob:ai-49-aHR0cDovL2R4LmRvaS5vcmcvMTAuMTE0NS8yNDA3NzM2LjI0MDc3Mzg |
id |
ai-49-aHR0cDovL2R4LmRvaS5vcmcvMTAuMTE0NS8yNDA3NzM2LjI0MDc3Mzg |
institution |
DE-Zi4 DE-15 DE-105 DE-14 DE-Ch1 |
imprint |
Association for Computing Machinery (ACM), 2013 |
imprint_str_mv |
Association for Computing Machinery (ACM), 2013 |
issn |
1550-4875 1550-4883 |
issn_str_mv |
1550-4875 1550-4883 |
language |
English |
mega_collection |
Association for Computing Machinery (ACM) (CrossRef) |
match_str |
zhang2013contextualandactivelearningbasedaffectsensingfromvirtualdramaimprovisation |
publishDateSort |
2013 |
publisher |
Association for Computing Machinery (ACM) |
recordtype |
ai |
record_format |
ai |
series |
ACM Transactions on Speech and Language Processing |
source_id |
49 |
title |
Contextual and active learning-based affect-sensing from virtual drama improvisation |
title_unstemmed |
Contextual and active learning-based affect-sensing from virtual drama improvisation |
title_full |
Contextual and active learning-based affect-sensing from virtual drama improvisation |
title_fullStr |
Contextual and active learning-based affect-sensing from virtual drama improvisation |
title_full_unstemmed |
Contextual and active learning-based affect-sensing from virtual drama improvisation |
title_short |
Contextual and active learning-based affect-sensing from virtual drama improvisation |
title_sort |
contextual and active learning-based affect-sensing from virtual drama improvisation |
topic |
Computational Mathematics Computer Science (miscellaneous) |
url |
http://dx.doi.org/10.1145/2407736.2407738 |
publishDate |
2013 |
physical |
1-25 |
description |
<jats:p>Affect interpretation from open-ended drama improvisation is a challenging task. This article describes experiments in using latent semantic analysis to identify discussion themes and potential target audiences for those improvisational inputs without strong affect indicators. A context-based affect-detection is also implemented using a supervised neural network with the consideration of emotional contexts of most intended audiences, sentence types, and interpersonal relationships. In order to go beyond the constraints of predefined scenarios and improve the system's robustness, min-margin-based active learning is implemented. This active learning algorithm also shows great potential in dealing with imbalanced affect classifications. Evaluation results indicated that the context-based affect detection achieved an averaged precision of 0.826 and an averaged recall of 0.813 for affect detection of the test inputs from the Crohn's disease scenario using three emotion labels: positive, negative, and neutral, and an averaged precision of 0.868 and an average recall of 0.876 for the test inputs from the school bullying scenario. Moreover, experimental evaluation on a benchmark data set for active learning demonstrated that active learning was able to greatly reduce human annotation efforts for the training of affect detection, and also showed promising robustness in dealing with open-ended example inputs beyond the improvisation of the chosen scenarios.</jats:p> |
container_issue |
4 |
container_start_page |
1 |
container_title |
ACM Transactions on Speech and Language Processing |
container_volume |
9 |
format_de105 |
Article, E-Article |
format_de14 |
Article, E-Article |
format_de15 |
Article, E-Article |
format_de520 |
Article, E-Article |
format_de540 |
Article, E-Article |
format_dech1 |
Article, E-Article |
format_ded117 |
Article, E-Article |
format_degla1 |
E-Article |
format_del152 |
Buch |
format_del189 |
Article, E-Article |
format_dezi4 |
Article |
format_dezwi2 |
Article, E-Article |
format_finc |
Article, E-Article |
format_nrw |
Article, E-Article |
_version_ |
1792332206991998977 |
geogr_code |
not assigned |
last_indexed |
2024-03-01T13:52:43.289Z |
geogr_code_person |
not assigned |
openURL |
url_ver=Z39.88-2004&ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fvufind.svn.sourceforge.net%3Agenerator&rft.title=Contextual+and+active+learning-based+affect-sensing+from+virtual+drama+improvisation&rft.date=2013-01-01&genre=article&issn=1550-4883&volume=9&issue=4&spage=1&epage=25&pages=1-25&jtitle=ACM+Transactions+on+Speech+and+Language+Processing&atitle=Contextual+and+active+learning-based+affect-sensing+from+virtual+drama+improvisation&aulast=Zhang&aufirst=Li&rft_id=info%3Adoi%2F10.1145%2F2407736.2407738&rft.language%5B0%5D=eng |
SOLR | |
_version_ | 1792332206991998977 |
author | Zhang, Li |
author_facet | Zhang, Li, Zhang, Li |
author_sort | zhang, li |
container_issue | 4 |
container_start_page | 1 |
container_title | ACM Transactions on Speech and Language Processing |
container_volume | 9 |
description | <jats:p>Affect interpretation from open-ended drama improvisation is a challenging task. This article describes experiments in using latent semantic analysis to identify discussion themes and potential target audiences for those improvisational inputs without strong affect indicators. A context-based affect-detection is also implemented using a supervised neural network with the consideration of emotional contexts of most intended audiences, sentence types, and interpersonal relationships. In order to go beyond the constraints of predefined scenarios and improve the system's robustness, min-margin-based active learning is implemented. This active learning algorithm also shows great potential in dealing with imbalanced affect classifications. Evaluation results indicated that the context-based affect detection achieved an averaged precision of 0.826 and an averaged recall of 0.813 for affect detection of the test inputs from the Crohn's disease scenario using three emotion labels: positive, negative, and neutral, and an averaged precision of 0.868 and an average recall of 0.876 for the test inputs from the school bullying scenario. Moreover, experimental evaluation on a benchmark data set for active learning demonstrated that active learning was able to greatly reduce human annotation efforts for the training of affect detection, and also showed promising robustness in dealing with open-ended example inputs beyond the improvisation of the chosen scenarios.</jats:p> |
doi_str_mv | 10.1145/2407736.2407738 |
facet_avail | Online |
finc_class_facet | Mathematik, Informatik |
format | ElectronicArticle |
format_de105 | Article, E-Article |
format_de14 | Article, E-Article |
format_de15 | Article, E-Article |
format_de520 | Article, E-Article |
format_de540 | Article, E-Article |
format_dech1 | Article, E-Article |
format_ded117 | Article, E-Article |
format_degla1 | E-Article |
format_del152 | Buch |
format_del189 | Article, E-Article |
format_dezi4 | Article |
format_dezwi2 | Article, E-Article |
format_finc | Article, E-Article |
format_nrw | Article, E-Article |
geogr_code | not assigned |
geogr_code_person | not assigned |
id | ai-49-aHR0cDovL2R4LmRvaS5vcmcvMTAuMTE0NS8yNDA3NzM2LjI0MDc3Mzg |
imprint | Association for Computing Machinery (ACM), 2013 |
imprint_str_mv | Association for Computing Machinery (ACM), 2013 |
institution | DE-Zi4, DE-15, DE-105, DE-14, DE-Ch1 |
issn | 1550-4875, 1550-4883 |
issn_str_mv | 1550-4875, 1550-4883 |
language | English |
last_indexed | 2024-03-01T13:52:43.289Z |
match_str | zhang2013contextualandactivelearningbasedaffectsensingfromvirtualdramaimprovisation |
mega_collection | Association for Computing Machinery (ACM) (CrossRef) |
physical | 1-25 |
publishDate | 2013 |
publishDateSort | 2013 |
publisher | Association for Computing Machinery (ACM) |
record_format | ai |
recordtype | ai |
series | ACM Transactions on Speech and Language Processing |
source_id | 49 |
spelling | Zhang, Li 1550-4875 1550-4883 Association for Computing Machinery (ACM) Computational Mathematics Computer Science (miscellaneous) http://dx.doi.org/10.1145/2407736.2407738 <jats:p>Affect interpretation from open-ended drama improvisation is a challenging task. This article describes experiments in using latent semantic analysis to identify discussion themes and potential target audiences for those improvisational inputs without strong affect indicators. A context-based affect-detection is also implemented using a supervised neural network with the consideration of emotional contexts of most intended audiences, sentence types, and interpersonal relationships. In order to go beyond the constraints of predefined scenarios and improve the system's robustness, min-margin-based active learning is implemented. This active learning algorithm also shows great potential in dealing with imbalanced affect classifications. Evaluation results indicated that the context-based affect detection achieved an averaged precision of 0.826 and an averaged recall of 0.813 for affect detection of the test inputs from the Crohn's disease scenario using three emotion labels: positive, negative, and neutral, and an averaged precision of 0.868 and an average recall of 0.876 for the test inputs from the school bullying scenario. Moreover, experimental evaluation on a benchmark data set for active learning demonstrated that active learning was able to greatly reduce human annotation efforts for the training of affect detection, and also showed promising robustness in dealing with open-ended example inputs beyond the improvisation of the chosen scenarios.</jats:p> Contextual and active learning-based affect-sensing from virtual drama improvisation ACM Transactions on Speech and Language Processing |
spellingShingle | Zhang, Li, ACM Transactions on Speech and Language Processing, Contextual and active learning-based affect-sensing from virtual drama improvisation, Computational Mathematics, Computer Science (miscellaneous) |
title | Contextual and active learning-based affect-sensing from virtual drama improvisation |
title_full | Contextual and active learning-based affect-sensing from virtual drama improvisation |
title_fullStr | Contextual and active learning-based affect-sensing from virtual drama improvisation |
title_full_unstemmed | Contextual and active learning-based affect-sensing from virtual drama improvisation |
title_short | Contextual and active learning-based affect-sensing from virtual drama improvisation |
title_sort | contextual and active learning-based affect-sensing from virtual drama improvisation |
title_unstemmed | Contextual and active learning-based affect-sensing from virtual drama improvisation |
topic | Computational Mathematics, Computer Science (miscellaneous) |
url | http://dx.doi.org/10.1145/2407736.2407738 |