Estimating Subjective Argument Quality Aspects From Social Signals in Argumentative Dialogue Systems
Information about a subjective user opinion towards an argument is crucial for argumentative systems in order to present appropriate content and adapt their behaviour to the individual user. However, requesting explicit feedback regarding the discussed arguments is often impractical and can hinder t...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2021-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9321384/ |
| id |
doaj-b72df32913d34dc3a28e5f04af734f9b |
|---|---|
| record_format |
Article |
| spelling |
doaj-b72df32913d34dc3a28e5f04af734f9b2021-04-05T17:37:12ZengIEEEIEEE Access2169-35362021-01-019116101162110.1109/ACCESS.2021.30515269321384Estimating Subjective Argument Quality Aspects From Social Signals in Argumentative Dialogue SystemsNiklas Rach0https://orcid.org/0000-0001-9737-8584Yuki Matsuda1https://orcid.org/0000-0002-3135-4915Stefan Ultes2https://orcid.org/0000-0003-2667-3126Wolfgang Minker3Keiichi Yasumoto4Institute of Communications Engineering, Ulm University, Ulm, GermanyGraduate School of Science and Technology, Nara Institute of Science and Technology, Ikoma, JapanMercedes-Benz Research and Development, Sindelfingen, GermanyInstitute of Communications Engineering, Ulm University, Ulm, GermanyGraduate School of Science and Technology, Nara Institute of Science and Technology, Ikoma, JapanInformation about a subjective user opinion towards an argument is crucial for argumentative systems in order to present appropriate content and adapt their behaviour to the individual user. However, requesting explicit feedback regarding the discussed arguments is often impractical and can hinder the interaction. To address this issue, we investigate the automatic recognition of user opinions towards arguments that are presented by means of a virtual avatar from social signals. We focus on two different user opinion categories (convincing and interesting) and two different types of social signals (facial expressions and eye movement). The recognition is addressed as a supervised learning problem and realized using the argument search evaluation data discussed in previous work. The overall performance is compared to a human annotation on a subset of the collected data. The results show that the machine learning performance is similar to human performance in both recognition tasks.https://ieeexplore.ieee.org/document/9321384/Computational argumentationargument quality estimationargumentative dialogue systemssocial signal extractionmachine learning |
| collection |
DOAJ |
| language |
English |
| format |
Article |
| sources |
DOAJ |
| author |
Niklas Rach Yuki Matsuda Stefan Ultes Wolfgang Minker Keiichi Yasumoto |
| spellingShingle |
Niklas Rach Yuki Matsuda Stefan Ultes Wolfgang Minker Keiichi Yasumoto Estimating Subjective Argument Quality Aspects From Social Signals in Argumentative Dialogue Systems IEEE Access Computational argumentation argument quality estimation argumentative dialogue systems social signal extraction machine learning |
| author_facet |
Niklas Rach Yuki Matsuda Stefan Ultes Wolfgang Minker Keiichi Yasumoto |
| author_sort |
Niklas Rach |
| title |
Estimating Subjective Argument Quality Aspects From Social Signals in Argumentative Dialogue Systems |
| title_short |
Estimating Subjective Argument Quality Aspects From Social Signals in Argumentative Dialogue Systems |
| title_full |
Estimating Subjective Argument Quality Aspects From Social Signals in Argumentative Dialogue Systems |
| title_fullStr |
Estimating Subjective Argument Quality Aspects From Social Signals in Argumentative Dialogue Systems |
| title_full_unstemmed |
Estimating Subjective Argument Quality Aspects From Social Signals in Argumentative Dialogue Systems |
| title_sort |
estimating subjective argument quality aspects from social signals in argumentative dialogue systems |
| publisher |
IEEE |
| series |
IEEE Access |
| issn |
2169-3536 |
| publishDate |
2021-01-01 |
| description |
Information about a subjective user opinion towards an argument is crucial for argumentative systems in order to present appropriate content and adapt their behaviour to the individual user. However, requesting explicit feedback regarding the discussed arguments is often impractical and can hinder the interaction. To address this issue, we investigate the automatic recognition of user opinions towards arguments that are presented by means of a virtual avatar from social signals. We focus on two different user opinion categories (convincing and interesting) and two different types of social signals (facial expressions and eye movement). The recognition is addressed as a supervised learning problem and realized using the argument search evaluation data discussed in previous work. The overall performance is compared to a human annotation on a subset of the collected data. The results show that the machine learning performance is similar to human performance in both recognition tasks. |
| topic |
Computational argumentation argument quality estimation argumentative dialogue systems social signal extraction machine learning |
| url |
https://ieeexplore.ieee.org/document/9321384/ |
| work_keys_str_mv |
AT niklasrach estimatingsubjectiveargumentqualityaspectsfromsocialsignalsinargumentativedialoguesystems AT yukimatsuda estimatingsubjectiveargumentqualityaspectsfromsocialsignalsinargumentativedialoguesystems AT stefanultes estimatingsubjectiveargumentqualityaspectsfromsocialsignalsinargumentativedialoguesystems AT wolfgangminker estimatingsubjectiveargumentqualityaspectsfromsocialsignalsinargumentativedialoguesystems AT keiichiyasumoto estimatingsubjectiveargumentqualityaspectsfromsocialsignalsinargumentativedialoguesystems |
| _version_ |
1721539206352732160 |