Sentiment Analysis has recently been considered as the most active research field in the natural language processing (NLP) domain. Deep Learning is a subset of the large family of Machine Learning and becoming a growing trend due to its automatic learning capability with impressive consequences across different NLP tasks. Hence, a fusion-based Machine Learning framework has been attempted by merging the Traditional Machine Learning method with Deep Learning techniques to tackle the challenge of sentiment prediction for a massive amount of unstructured review dataset. The proposed architecture aims to utilize the Convolutional Neural Network (CNN) with a backpropagation algorithm to extract embedded feature vectors from the top hidden layer. Thereafter, these vectors augmented to an optimized feature set generated from binary particle swarm optimization (BPSO) method. Finally, a traditional SVM classifier is trained with these extended features set to determine the optimal hyper-plane for separating two classes of review datasets. The evaluation of this research work has been carried out on two benchmark movie review datasets IMDB, SST2. Experimental results with comparative studies based on performance accuracy and F-score value are reported to highlight the benefits of the developed frameworks.
Figure 1
Figure 2
Figure 3
Figure 4
Figure 5
Figure 6
This preprint is available for download as a PDF.
This is a list of supplementary files associated with this preprint. Click to download.
Loading...
Posted 05 Aug, 2020
On 13 Aug, 2020
On 03 Aug, 2020
On 03 Aug, 2020
On 03 Aug, 2020
Received 03 Aug, 2020
Received 03 Aug, 2020
Received 03 Aug, 2020
Received 02 Aug, 2020
On 30 Jul, 2020
Invitations sent on 30 Jul, 2020
On 30 Jul, 2020
On 29 Jul, 2020
On 29 Jul, 2020
On 20 Feb, 2020
Received 19 Feb, 2020
Received 17 Feb, 2020
On 14 Feb, 2020
Received 13 Feb, 2020
Received 13 Feb, 2020
On 13 Feb, 2020
On 13 Feb, 2020
Received 11 Feb, 2020
Received 11 Feb, 2020
On 10 Feb, 2020
On 10 Feb, 2020
On 09 Feb, 2020
Received 09 Feb, 2020
Invitations sent on 07 Feb, 2020
On 07 Feb, 2020
On 07 Feb, 2020
On 07 Feb, 2020
On 21 Jan, 2020
On 21 Jan, 2020
On 20 Jan, 2020
On 20 Jan, 2020
Posted 05 Aug, 2020
On 13 Aug, 2020
On 03 Aug, 2020
On 03 Aug, 2020
On 03 Aug, 2020
Received 03 Aug, 2020
Received 03 Aug, 2020
Received 03 Aug, 2020
Received 02 Aug, 2020
On 30 Jul, 2020
Invitations sent on 30 Jul, 2020
On 30 Jul, 2020
On 29 Jul, 2020
On 29 Jul, 2020
On 20 Feb, 2020
Received 19 Feb, 2020
Received 17 Feb, 2020
On 14 Feb, 2020
Received 13 Feb, 2020
Received 13 Feb, 2020
On 13 Feb, 2020
On 13 Feb, 2020
Received 11 Feb, 2020
Received 11 Feb, 2020
On 10 Feb, 2020
On 10 Feb, 2020
On 09 Feb, 2020
Received 09 Feb, 2020
Invitations sent on 07 Feb, 2020
On 07 Feb, 2020
On 07 Feb, 2020
On 07 Feb, 2020
On 21 Jan, 2020
On 21 Jan, 2020
On 20 Jan, 2020
On 20 Jan, 2020
Sentiment Analysis has recently been considered as the most active research field in the natural language processing (NLP) domain. Deep Learning is a subset of the large family of Machine Learning and becoming a growing trend due to its automatic learning capability with impressive consequences across different NLP tasks. Hence, a fusion-based Machine Learning framework has been attempted by merging the Traditional Machine Learning method with Deep Learning techniques to tackle the challenge of sentiment prediction for a massive amount of unstructured review dataset. The proposed architecture aims to utilize the Convolutional Neural Network (CNN) with a backpropagation algorithm to extract embedded feature vectors from the top hidden layer. Thereafter, these vectors augmented to an optimized feature set generated from binary particle swarm optimization (BPSO) method. Finally, a traditional SVM classifier is trained with these extended features set to determine the optimal hyper-plane for separating two classes of review datasets. The evaluation of this research work has been carried out on two benchmark movie review datasets IMDB, SST2. Experimental results with comparative studies based on performance accuracy and F-score value are reported to highlight the benefits of the developed frameworks.
Figure 1
Figure 2
Figure 3
Figure 4
Figure 5
Figure 6
This preprint is available for download as a PDF.
Loading...