Satyajit Chakrabarti
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Satyajit Chakrabarti has a total of 7 co-authors. Here are the top co-authors by number of shared publications:
- Bikash Sadhukhan
Department of Computer Science and Engineering, Techno International New Town, Kolkata, India
2 shared publications - Nabanita Das
Department of Computer Science and Engineering, Techno International New Town, Kolkata, India
2 shared publications - Susmit Shekhar Bhakta
Department of Computer Science and Engineering, Techno International New Town, Kolkata, India
2 shared publications - Dipankar Das
The Heritage Academy
1 shared publication - Rituparna Pal
K. K. Das College
1 shared publication - Samik Datta
Department of Computer Science and Engineering, University of Engineering and Management, Kolkata, India
1 shared publication
Latest Publications
- Open Access
- 7 March 2024
- Published by Springer Nature in Social Network Analysis and Mining
- Vol. 14 (1) , 1
Correction: Integrating EEMD and ensemble CNN with X (Twitter) sentiment for enhanced stock price predictions
- 7 March 2024
- Published by Springer Nature in Social Network Analysis and Mining
- Vol. 14 (1) , 1
Open AccessCorrection: Integrating EEMD and ensemble CNN with X (Twitter) sentiment for enhanced stock price predictions
- 24 January 2024
- Published by Springer Nature in Social Network Analysis and Mining
- Vol. 14 (1) , 1-18
Integrating EEMD and ensemble CNN with X (Twitter) sentiment for enhanced stock price predictions
- 24 January 2024
- Published by Springer Nature in Social Network Analysis and Mining
- Vol. 14 (1) , 1-18
Integrating EEMD and ensemble CNN with X (Twitter) sentiment for enhanced stock price predictions
- Open Access
- 8 September 2023
- Published by Universiti Putra Malaysia in Pertanika Journal of Science and Technology
- Vol. 31 (6) , 3179-3198
An Extreme Learning Machine Approach for Forecasting the Wholesale Price Index of Food Products in India
Precise food price forecasting is crucial for any country, and searching for appropriate approach(s) from an assortment of available strategies toward this objective is an open problem. The current Indian Wholesale Price Index (WPI) series contains sixty individual food items in the 'manufacture of food product' category. This work considered the monthly data from April 2011 to June 2022, i.e., one hundred thirty-five months' data of these sixty WPIs. The researchers extracted the linearity, curvature, and autocorrelation features for each WPI. The curvature and linearity-based grouping of these WPIs revealed that the WPIs are heterogeneous. This work proposed an extreme learning machine (ELM) approach for forecasting these WPIs. The present work employed the following twenty-two time-series forecasting techniques: six standard methods (Auto ARIMA, TSLM, SES, DES, TES, and Auto ETS), five neural networks (Auto FFNN, Auto GRNN, Auto MLP, Auto ELM, and proposed ELM), and eleven state-of-art techniques (two ARIMA-ETS based ensembles, an ARIMA-THETAF-TBATS based ensemble, one MLP, and seven LSTM-based models) to identify the best forecasting approach for these WPIs. For the majority of WPIs, the offered ELM attained suitable performance in the case of fifteen months of out-of-sample forecasting. Nearly eighty-seven percent of cases achieved high accuracy (MAPE ≤ ten) and outshined others. Upon accuracy comparison, both forecast-MAPE and forecast-RMSE, between the proposed ELM and others, this paper observed that the proposed ELM's performance is more favorable. This paper's findings imply that the proposed ELM is a promising prospect to offer accurate forecasts of these sixty WPIs.
- 8 September 2023
- Published by Universiti Putra Malaysia in Pertanika Journal of Science and Technology
- Vol. 31 (6) , 3179-3198
Open AccessAn Extreme Learning Machine Approach for Forecasting the Wholesale Price Index of Food Products in India
Precise food price forecasting is crucial for any country, and searching for appropriate approach(s) from an assortment of available strategies toward this objective is an open problem. The current Indian Wholesale Price Index (WPI) series contains sixty individual food items in the 'manufacture of food product' category. This work considered the monthly data from April 2011 to June 2022, i.e., one hundred thirty-five months' data of these sixty WPIs. The researchers extracted the linearity, curvature, and autocorrelation features for each WPI. The curvature and linearity-based grouping of these WPIs revealed that the WPIs are heterogeneous. This work proposed an extreme learning machine (ELM) approach for forecasting these WPIs. The present work employed the following twenty-two time-series forecasting techniques: six standard methods (Auto ARIMA, TSLM, SES, DES, TES, and Auto ETS), five neural networks (Auto FFNN, Auto GRNN, Auto MLP, Auto ELM, and proposed ELM), and eleven state-of-art techniques (two ARIMA-ETS based ensembles, an ARIMA-THETAF-TBATS based ensemble, one MLP, and seven LSTM-based models) to identify the best forecasting approach for these WPIs. For the majority of WPIs, the offered ELM attained suitable performance in the case of fifteen months of out-of-sample forecasting. Nearly eighty-seven percent of cases achieved high accuracy (MAPE ≤ ten) and outshined others. Upon accuracy comparison, both forecast-MAPE and forecast-RMSE, between the proposed ELM and others, this paper observed that the proposed ELM's performance is more favorable. This paper's findings imply that the proposed ELM is a promising prospect to offer accurate forecasts of these sixty WPIs.
- 22 September 2022
- Published by Springer Nature
- p. 363-372
A Gamification Architecture for Online Learning Platform Using Neural Network
- 22 September 2022
- Published by Springer Nature
- p. 363-372
A Gamification Architecture for Online Learning Platform Using Neural Network
- 4 July 2022
- Published by Taylor & Francis in Theoretical Issues in Ergonomics Science
- Vol. 24 (4) , 429-460
Enhanced ensemble learning for aspect-based sentiment analysis on multiple application oriented datasets
The main goal of this article is to develop and propose a novel ABSA method using enhanced ensemble learning (EEL) with optimal feature selection. Initially, the data from multiple applications is gathered and subjected to the preprocessing by ‘stop word removal and punctuation removal, lower case conversion and stemming’. Then, the aspect extraction is done by separating ‘noun and adjective and verb and adverb combination’. From this, the ‘Vader sentiment intensity analyzer’ is used to capture the weighted polarity feature, and then, the word2vector and ‘term frequency-inverse document frequency’ are extracted as features. The optimal feature selection using best and worst fitness-based galactic swarm optimization (BWF-GSO) is used for selecting the most significant features. With these features, ensemble learning with different classifiers like ‘recurrent neural network, support vector machine and deep belief network’ performs for handling the sentiment analysis with parameter optimization. The suggested models are helpful and generate better than the existing outcomes, according to experimental data. Through the performance analysis, the accuracy of BWF-GSO-EEL was 1.16%, 1.58%, 2.01% and 1.37% better than FF-MVO-EEL, FF-EEL, MVO-EEL and PSO-EEL, respectively. Thus, the promising performance has been observed while comparing with other algorithms.
- 4 July 2022
- Published by Taylor & Francis in Theoretical Issues in Ergonomics Science
- Vol. 24 (4) , 429-460
Enhanced ensemble learning for aspect-based sentiment analysis on multiple application oriented datasets
The main goal of this article is to develop and propose a novel ABSA method using enhanced ensemble learning (EEL) with optimal feature selection. Initially, the data from multiple applications is gathered and subjected to the preprocessing by ‘stop word removal and punctuation removal, lower case conversion and stemming’. Then, the aspect extraction is done by separating ‘noun and adjective and verb and adverb combination’. From this, the ‘Vader sentiment intensity analyzer’ is used to capture the weighted polarity feature, and then, the word2vector and ‘term frequency-inverse document frequency’ are extracted as features. The optimal feature selection using best and worst fitness-based galactic swarm optimization (BWF-GSO) is used for selecting the most significant features. With these features, ensemble learning with different classifiers like ‘recurrent neural network, support vector machine and deep belief network’ performs for handling the sentiment analysis with parameter optimization. The suggested models are helpful and generate better than the existing outcomes, according to experimental data. Through the performance analysis, the accuracy of BWF-GSO-EEL was 1.16%, 1.58%, 2.01% and 1.37% better than FF-MVO-EEL, FF-EEL, MVO-EEL and PSO-EEL, respectively. Thus, the promising performance has been observed while comparing with other algorithms.
- 16 April 2021
- Published by Springer Nature in Sādhanā
- Vol. 46 (2) , 1-23
Aspect based sentiment analysis for demonetization tweets by optimized recurrent neural network using fire fly-oriented multi-verse optimizer
In this paper, it is proposed to understand the opinion of the public regarding the policy of demonetization that is implemented recently in India through Aspect-based Sentiment Analysis (ABSA) that predicts the sentiment of specific aspects present in the text. The major aim is to identify the relevant contexts for various aspects. Most of the conventional techniques have adopted attention mechanisms and deep learning concepts that decrease the prediction accuracy and generate huge noise. Another major disadvantage with the attention mechanisms is that the sentiment related to few context words alters with various aspects, and hence it cannot be concluded from itself alone. This paper adopts the optimized deep learning concept for performing the ABSA for demonetization tweets. The proposed model involves various phases such as pre-processing, aspect extraction, polarity feature extraction, and sentiment classification. Initially, the different demonetization tweets collected from the Kaggle dataset are taken. Pre-processing is done with the help of four phases like stop words removal, punctuation removal, lower case conversion, and stemming from minimizing the data to its reduced format. This pre-processed data is further performed with aspect extraction to extract the opinion words. These extracted aspect words are converted to the features with the help of polarity score computation and Word2vec. The weight of the polarity scores is optimized using hybridization of two meta-heuristic algorithms like FireFly Algorithm (FF), and Multi-Verse Optimization (MVO), and the new algorithm is termed as Fire Fly-oriented Multi-Verse Optimizer (FF-MVO). Further, combined features are subjected to a deep learning algorithm called Recurrent Neural Network (RNN). As a modification to the existing RNN, the hidden neurons are optimized by the hybrid FF-MVO, FF-MVO-RNN classifies the positive and negative sentiments. Finally, the comparative analysis of different machine learning algorithms proves the competent performance of the proposed model.
- 16 April 2021
- Published by Springer Nature in Sādhanā
- Vol. 46 (2) , 1-23
Aspect based sentiment analysis for demonetization tweets by optimized recurrent neural network using fire fly-oriented multi-verse optimizer
In this paper, it is proposed to understand the opinion of the public regarding the policy of demonetization that is implemented recently in India through Aspect-based Sentiment Analysis (ABSA) that predicts the sentiment of specific aspects present in the text. The major aim is to identify the relevant contexts for various aspects. Most of the conventional techniques have adopted attention mechanisms and deep learning concepts that decrease the prediction accuracy and generate huge noise. Another major disadvantage with the attention mechanisms is that the sentiment related to few context words alters with various aspects, and hence it cannot be concluded from itself alone. This paper adopts the optimized deep learning concept for performing the ABSA for demonetization tweets. The proposed model involves various phases such as pre-processing, aspect extraction, polarity feature extraction, and sentiment classification. Initially, the different demonetization tweets collected from the Kaggle dataset are taken. Pre-processing is done with the help of four phases like stop words removal, punctuation removal, lower case conversion, and stemming from minimizing the data to its reduced format. This pre-processed data is further performed with aspect extraction to extract the opinion words. These extracted aspect words are converted to the features with the help of polarity score computation and Word2vec. The weight of the polarity scores is optimized using hybridization of two meta-heuristic algorithms like FireFly Algorithm (FF), and Multi-Verse Optimization (MVO), and the new algorithm is termed as Fire Fly-oriented Multi-Verse Optimizer (FF-MVO). Further, combined features are subjected to a deep learning algorithm called Recurrent Neural Network (RNN). As a modification to the existing RNN, the hidden neurons are optimized by the hybrid FF-MVO, FF-MVO-RNN classifies the positive and negative sentiments. Finally, the comparative analysis of different machine learning algorithms proves the competent performance of the proposed model.