How intense are you? Predicting intensities of emotions and sentiments using stacked ensemble [application notes]
Emotions and sentiments are subjective in nature. They differ on a case-to-case basis. However,-predicting only the emotion and sentiment does not always convey complete information. The degree or level of emotions and sentiments often plays a crucial role in understanding the exact feeling within a...
| Main Authors: | , , |
|---|---|
| Other Authors: | |
| Format: | Journal Article |
| Language: | English |
| Published: |
2021
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/154430 |
| _version_ | 1811696729930596352 |
|---|---|
| author | Akhtar, M. S. Ekbal, A. Cambria, Erik |
| author2 | School of Computer Science and Engineering |
| author_facet | School of Computer Science and Engineering Akhtar, M. S. Ekbal, A. Cambria, Erik |
| author_sort | Akhtar, M. S. |
| collection | NTU |
| description | Emotions and sentiments are subjective in nature. They differ on a case-to-case basis. However,-predicting only the emotion and sentiment does not always convey complete information. The degree or level of emotions and sentiments often plays a crucial role in understanding the exact feeling within a single class (e.g., 'good' versus 'awesome'). In this paper, we propose a stacked ensemble method for predicting the degree of intensity for emotion and sentiment by combining the outputs obtained from several deep learning and classical feature-based models using a multi-layer perceptron network. We develop three deep learning models based on convolutional neural network, long short-term memory and gated recurrent unit and one classical supervised model based on support vector regression. We evaluate our proposed technique for two problems, i.e., emotion analysis in the generic domain and sentiment analysis in the financial domain. The proposed model shows impressive results for both the problems. Comparisons show that our proposed model achieves improved performance over the existing state-of-theart systems. |
| first_indexed | 2024-10-01T07:44:00Z |
| format | Journal Article |
| id | ntu-10356/154430 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T07:44:00Z |
| publishDate | 2021 |
| record_format | dspace |
| spelling | ntu-10356/1544302021-12-22T07:31:52Z How intense are you? Predicting intensities of emotions and sentiments using stacked ensemble [application notes] Akhtar, M. S. Ekbal, A. Cambria, Erik School of Computer Science and Engineering Engineering::Computer science and engineering Sentiment Analysis Emotion Recognition Emotions and sentiments are subjective in nature. They differ on a case-to-case basis. However,-predicting only the emotion and sentiment does not always convey complete information. The degree or level of emotions and sentiments often plays a crucial role in understanding the exact feeling within a single class (e.g., 'good' versus 'awesome'). In this paper, we propose a stacked ensemble method for predicting the degree of intensity for emotion and sentiment by combining the outputs obtained from several deep learning and classical feature-based models using a multi-layer perceptron network. We develop three deep learning models based on convolutional neural network, long short-term memory and gated recurrent unit and one classical supervised model based on support vector regression. We evaluate our proposed technique for two problems, i.e., emotion analysis in the generic domain and sentiment analysis in the financial domain. The proposed model shows impressive results for both the problems. Comparisons show that our proposed model achieves improved performance over the existing state-of-theart systems. Asif Ekbal acknowledges the Young Faculty Research Fellowship (YFRF), supported by Visvesvaraya PhD scheme for Electronics and IT, Ministry of Electronics and Information Technology (MeitY), Government of India, being implemented by Digital India Corporation (formerly Media Lab Asia). 2021-12-22T07:31:52Z 2021-12-22T07:31:52Z 2020 Journal Article Akhtar, M. S., Ekbal, A. & Cambria, E. (2020). How intense are you? Predicting intensities of emotions and sentiments using stacked ensemble [application notes]. IEEE Computational Intelligence Magazine, 15(1), 64-75. https://dx.doi.org/10.1109/MCI.2019.2954667 1556-603X https://hdl.handle.net/10356/154430 10.1109/MCI.2019.2954667 2-s2.0-85078338836 1 15 64 75 en IEEE Computational Intelligence Magazine © 2020 IEEE. All rights reserved. |
| spellingShingle | Engineering::Computer science and engineering Sentiment Analysis Emotion Recognition Akhtar, M. S. Ekbal, A. Cambria, Erik How intense are you? Predicting intensities of emotions and sentiments using stacked ensemble [application notes] |
| title | How intense are you? Predicting intensities of emotions and sentiments using stacked ensemble [application notes] |
| title_full | How intense are you? Predicting intensities of emotions and sentiments using stacked ensemble [application notes] |
| title_fullStr | How intense are you? Predicting intensities of emotions and sentiments using stacked ensemble [application notes] |
| title_full_unstemmed | How intense are you? Predicting intensities of emotions and sentiments using stacked ensemble [application notes] |
| title_short | How intense are you? Predicting intensities of emotions and sentiments using stacked ensemble [application notes] |
| title_sort | how intense are you predicting intensities of emotions and sentiments using stacked ensemble application notes |
| topic | Engineering::Computer science and engineering Sentiment Analysis Emotion Recognition |
| url | https://hdl.handle.net/10356/154430 |
| work_keys_str_mv | AT akhtarms howintenseareyoupredictingintensitiesofemotionsandsentimentsusingstackedensembleapplicationnotes AT ekbala howintenseareyoupredictingintensitiesofemotionsandsentimentsusingstackedensembleapplicationnotes AT cambriaerik howintenseareyoupredictingintensitiesofemotionsandsentimentsusingstackedensembleapplicationnotes |