Fuzzy commonsense reasoning for multimodal sentiment analysis
The majority of user-generated content posted online is in the form of text, images and videos but also physiological signals in games. AffectiveSpace is a vector space of affective commonsense available for English text but not for other languages nor other modalities such as electrocardiogram sign...
| Main Authors: | , , , |
|---|---|
| Other Authors: | |
| Format: | Journal Article |
| Language: | English |
| Published: |
2021
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/151519 |
| _version_ | 1826115796156284928 |
|---|---|
| author | Chaturvedi, Iti Satapathy, Ranjan Cavallari, Sandro Cambria, Erik |
| author2 | School of Computer Science and Engineering |
| author_facet | School of Computer Science and Engineering Chaturvedi, Iti Satapathy, Ranjan Cavallari, Sandro Cambria, Erik |
| author_sort | Chaturvedi, Iti |
| collection | NTU |
| description | The majority of user-generated content posted online is in the form of text, images and videos but also physiological signals in games. AffectiveSpace is a vector space of affective commonsense available for English text but not for other languages nor other modalities such as electrocardiogram signals. We overcome this limitation by using deep learning to extract features from each modality and then projecting them to a common AffectiveSpace that has been clustered into different emotions. Because, in the real world, individuals tend to have partial or mixed sentiments about an opinion target, we use a fuzzy logic classifier to predict the degree of a particular emotion in AffectiveSpace. The combined model of deep convolutional neural networks and fuzzy logic is termed Convolutional Fuzzy Sentiment Classifier. Lastly, because the computational complexity of a fuzzy classifier is exponential with respect to the number of features, we project features to a four dimensional emotion space in order to speed up the classification performance. |
| first_indexed | 2024-10-01T04:01:01Z |
| format | Journal Article |
| id | ntu-10356/151519 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T04:01:01Z |
| publishDate | 2021 |
| record_format | dspace |
| spelling | ntu-10356/1515192021-06-29T07:48:14Z Fuzzy commonsense reasoning for multimodal sentiment analysis Chaturvedi, Iti Satapathy, Ranjan Cavallari, Sandro Cambria, Erik School of Computer Science and Engineering Engineering::Computer science and engineering Sentiment Prediction Fuzzy Logic The majority of user-generated content posted online is in the form of text, images and videos but also physiological signals in games. AffectiveSpace is a vector space of affective commonsense available for English text but not for other languages nor other modalities such as electrocardiogram signals. We overcome this limitation by using deep learning to extract features from each modality and then projecting them to a common AffectiveSpace that has been clustered into different emotions. Because, in the real world, individuals tend to have partial or mixed sentiments about an opinion target, we use a fuzzy logic classifier to predict the degree of a particular emotion in AffectiveSpace. The combined model of deep convolutional neural networks and fuzzy logic is termed Convolutional Fuzzy Sentiment Classifier. Lastly, because the computational complexity of a fuzzy classifier is exponential with respect to the number of features, we project features to a four dimensional emotion space in order to speed up the classification performance. Nanyang Technological University This work is partially supported by the Data Science and Artificial Intelligence Center (DSAIR) at the Nanyang Technological University. 2021-06-29T07:48:14Z 2021-06-29T07:48:14Z 2019 Journal Article Chaturvedi, I., Satapathy, R., Cavallari, S. & Cambria, E. (2019). Fuzzy commonsense reasoning for multimodal sentiment analysis. Pattern Recognition Letters, 125, 264-270. https://dx.doi.org/10.1016/j.patrec.2019.04.024 0167-8655 0000-0003-4602-2080 https://hdl.handle.net/10356/151519 10.1016/j.patrec.2019.04.024 2-s2.0-85065463296 125 264 270 en Pattern Recognition Letters © 2019 Published by Elsevier B.V. All rights reserved. |
| spellingShingle | Engineering::Computer science and engineering Sentiment Prediction Fuzzy Logic Chaturvedi, Iti Satapathy, Ranjan Cavallari, Sandro Cambria, Erik Fuzzy commonsense reasoning for multimodal sentiment analysis |
| title | Fuzzy commonsense reasoning for multimodal sentiment analysis |
| title_full | Fuzzy commonsense reasoning for multimodal sentiment analysis |
| title_fullStr | Fuzzy commonsense reasoning for multimodal sentiment analysis |
| title_full_unstemmed | Fuzzy commonsense reasoning for multimodal sentiment analysis |
| title_short | Fuzzy commonsense reasoning for multimodal sentiment analysis |
| title_sort | fuzzy commonsense reasoning for multimodal sentiment analysis |
| topic | Engineering::Computer science and engineering Sentiment Prediction Fuzzy Logic |
| url | https://hdl.handle.net/10356/151519 |
| work_keys_str_mv | AT chaturvediiti fuzzycommonsensereasoningformultimodalsentimentanalysis AT satapathyranjan fuzzycommonsensereasoningformultimodalsentimentanalysis AT cavallarisandro fuzzycommonsensereasoningformultimodalsentimentanalysis AT cambriaerik fuzzycommonsensereasoningformultimodalsentimentanalysis |