Towards Interpretability in Audio and Visual Affective Machine Learning: A Review
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916988494807040 |
|---|---|
| author | Johnson, David S. Hakobyan, Olya Drimalla, Hanna |
| author_facet | Johnson, David S. Hakobyan, Olya Drimalla, Hanna |
| contents | Machine learning is frequently used in affective computing, but presents challenges due the opacity of state-of-the-art machine learning methods. Because of the impact affective machine learning systems may have on an individual's life, it is important that models be made transparent to detect and mitigate biased decision making. In this regard, affective machine learning could benefit from the recent advancements in explainable artificial intelligence (XAI) research. We perform a structured literature review to examine the use of interpretability in the context of affective machine learning. We focus on studies using audio, visual, or audiovisual data for model training and identified 29 research articles. Our findings show an emergence of the use of interpretability methods in the last five years. However, their use is currently limited regarding the range of methods used, the depth of evaluations, and the consideration of use-cases. We outline the main gaps in the research and provide recommendations for researchers that aim to implement interpretable methods for affective machine learning. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2306_08933 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Towards Interpretability in Audio and Visual Affective Machine Learning: A Review Johnson, David S. Hakobyan, Olya Drimalla, Hanna Machine Learning Machine learning is frequently used in affective computing, but presents challenges due the opacity of state-of-the-art machine learning methods. Because of the impact affective machine learning systems may have on an individual's life, it is important that models be made transparent to detect and mitigate biased decision making. In this regard, affective machine learning could benefit from the recent advancements in explainable artificial intelligence (XAI) research. We perform a structured literature review to examine the use of interpretability in the context of affective machine learning. We focus on studies using audio, visual, or audiovisual data for model training and identified 29 research articles. Our findings show an emergence of the use of interpretability methods in the last five years. However, their use is currently limited regarding the range of methods used, the depth of evaluations, and the consideration of use-cases. We outline the main gaps in the research and provide recommendations for researchers that aim to implement interpretable methods for affective machine learning. |
| title | Towards Interpretability in Audio and Visual Affective Machine Learning: A Review |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2306.08933 |