Advanced search
Publication Cover
Applied Artificial Intelligence
An International Journal
Volume 36, 2022 - Issue 1
Submit an article Journal homepage
2,689
Views
5
CrossRef citations to date
0
Altmetric
Research Article

Deep Sentiments Analysis for Roman Urdu Dataset Using Faster Recurrent Convolutional Neural Network Model

Arfan Ali Nagraa Department of Computer Science, Garrison University, Lahore, PakistanCorrespondence[email protected]
,
Khalid Alissab Networks and Communications Department, College of Computer Science and Information Technology, Imam Abdulrahman Bin Faisal University, Dammam, Saudi Arabia
,
Taher M. Ghazalc Center for Cyber Security, Faculty of Information Science and Technology, Universiti Kebangsaan Malaysia (UKM), Bangi, Selangor, Malaysia;d School of Information Technology, Skyline University College, University City Sharjah, Sharjah, UAE
,
Saigeeta Kukunurue Faculty of Management, Swiss Business School, Ras Al Khaima, UAE
,
Muhammad Mugees Asifa Department of Computer Science, Garrison University, Lahore, Pakistan
&
Muhammad Fawadf Riphah School of Computing and Innovation, Faculty of Computing, Riphah International University, Lahore, Pakistan
Article: 2123094 | Received 19 May 2022, Accepted 02 Sep 2022, Published online: 26 Sep 2022

Figures & data

Figure 1. Tokenization example.

Figure 1. Tokenization example.

Figure 2. Lower casing example.

Figure 2. Lower casing example.

Figure 3. Stop word example.

Figure 3. Stop word example.

Figure 4. RNN (recurrent neural network) Model.

Figure 4. RNN (recurrent neural network) Model.

Figure 5. Architecture diagram of faster RCNN.

Figure 5. Architecture diagram of faster RCNN.

Figure 6. Positive class example.

Figure 6. Positive class example.

Figure 7. Negative class example.

Figure 7. Negative class example.

Figure 8. Neutral class example.

Figure 8. Neutral class example.

Table 1. Result obtained from previous related work.

Table 2. Result obtained from previous work at the linguistic level.

Table 3. Corpus Statistics.

Table 4. Faster RCNN model initial parameters.

Table 5. Special symbols description used for evaluation.

Table 6. Comparative analysis of faster RCNN model for binary and tertiary classification experiment.

Table 7. Comparative analysis of faster RCNN model with RCNN, rule-based approach and N-gram model for binary and tertiary classification.

Figure 9. Assessment of Accuracy, Precision, Recall, and F1 score by binary classification for all models using RUSA-19 Corpus.

Figure 9. Assessment of Accuracy, Precision, Recall, and F1 score by binary classification for all models using RUSA-19 Corpus.

Figure 10. Assessment of accuracy, precision, recall, and F1 score by tertiary classification for all models using RUSA-19 Corpus.

Figure 10. Assessment of accuracy, precision, recall, and F1 score by tertiary classification for all models using RUSA-19 Corpus.

Figure 11. Comparison of precision, recall, and F1 score of binary classification for 2 to 5-gram.

Figure 11. Comparison of precision, recall, and F1 score of binary classification for 2 to 5-gram.

Figure 12. Comparison of Precision, recall, and F1 score of tertiary classification for 2 to 5-gram.

Figure 12. Comparison of Precision, recall, and F1 score of tertiary classification for 2 to 5-gram.

Figure 13. Faster RCNN training accuracy for binary and tertiary classification.

Figure 13. Faster RCNN training accuracy for binary and tertiary classification.

Table 8. Comparative analysis of faster RCNN model in term of speed.

Related research

People also read lists articles that other readers of this article have read.

Recommended articles lists articles that we recommend and is powered by our AI driven recommendation engine.

Cited by lists all citing articles based on Crossref citations.
Articles with the Crossref icon will open in a new tab.