High performing sentiment analysis based on fast Fourier transform over temporal intuitionistic fuzzy value

Nandi, Basanti Pal; Jain, Amita; Tayal, Devendra K.; Narang, Poonam Ahuja

doi:10.1007/s00500-021-06444-3

Cited by 5 publications

(3 citation statements)

References 46 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For sentimental classification to increase recall, Nandi et al [21] suggested a Fast Fourier Transform on Temporal Intuitionistic Fuzzy Set (FFT-TIFS). To produce good performance and accuracy for applications in large volumes of documents, the FFT-TIFS was used.…”

Section: Literature Reviewmentioning

confidence: 99%

See 1 more Smart Citation

Sentiment Analysis Using Improved Atom Search Optimizer With a Simulated Annealing and ReLU Based Gated Recurrent Unit

Jacob,

Viswanatham

2024

IEEE Access

View full text Add to dashboard Cite

Social media has become an indispensable part of our daily lives in recent times. On social media, users commonly express their thoughts and opinions by sharing a substantial number of reviews and feedback. Twitter is one of the social media platforms with the best growth, and it also serves as a news and business tool. This study proposed the ReLU based Gated Recurrent Unit (ReLU-GRU) for Twitter sentiment analysis to classify the emotions like fear, anger, joy, and sadness. Covid-19, Sentiment-140 and twitter emoji datasets are used in this research to conduct the analysis. First, a pre-processing step using tokenization, stemming, adding part of speech, and punctuation removal is carried out using the collected datasets. Then, using Bag of Words (BoW), Latent Dirichlet Analysis (LDA), Term Frequency, and Inverse Document Frequency (TF-IDF), the processed data is employed for feature extraction. The next stage is to choose the best features for accurate classification which is carried out by using the proposed Improved Atom Search Optimizer (ASO) and a Simulated Annealing (SA) method. Finally, in the classification stage, ReLU-GRU is proposed for classifying the chosen features into various classes. From the outcomes, it evidently shows that proposed ReLU-GRU has outperformed existing methods by obtaining 97.87% and 96.52% of accuracy on Covid-19 and Sentiment-140 datasets.INDEX TERMS Improved atom search optimizer, simulated annealing, ReLU based gated recurrent unit, sentiment analysis, twitter datasets.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

“…Lastly, the update gate is used to determine the hidden layer output at the current time step. Equation (19)(20)(21)(22) is a representation of the mathematical procedure used in the GRU.…”

Section: Figure 2 Structure Of Gated Recurrent Unitmentioning

confidence: 99%

Sentiment Analysis Using Improved Atom Search Optimizer With a Simulated Annealing and ReLU Based Gated Recurrent Unit

Jacob,

Viswanatham

2024

IEEE Access

View full text Add to dashboard Cite

show abstract

“…The analytical tools we describe require adequate computing power, but this allows the time of data processing to be shortened. The tools we use are comparable to others that have recently been developed and implemented [15], but our solution was already fully functional in 2018 and is constantly being improved.…”

Section: Introductionmentioning

confidence: 96%

Potential for the use of large unstructured data resources by public innovation support institutions

Cetera

Gogołek²,

Żołnierski

et al. 2022

J Big Data

View full text Add to dashboard Cite

Effective programming of research and development (R&D) support, adjusted to the actual potential of beneficiaries, requires the use of modern analytical tools. An efficient R&D support system requires up-to-date data on technological trends, ongoing (and planning) research, market needs and developing innovation. The most popular programming methods were based on the analysis of data with a 4 to 5-year time delay until recently. Having described the method of refining information from unstructured data, we explore how to make it possible not only to solve the issue of up-to-date data but to identify of the latest trends in R&D activities.The analytical tools we describe were already fully functional in 2018 and are constantly being improved. The article presents the potential of one tool that can be applied in public support institutions. Methods of identifying and diagnosing technology trends are presented within the case study of the electric car technology trend. The presented case study shows the effectiveness of the method we developed for identifying and diagnosing areas requiring support from public funds. Public institutions, including public institutions supporting R&D and innovation processes, can apply tools that allow an increase in the quality of public support programmes offered, but also beneficial for the quality of strategic resources management within the institution itself. The comparison of the predictions made by the described tools with the classifications made by experts, the former are more accurate and precise. Moreover, the results of the analyses performed by the presented model are not influenced by distorting factors—fads, trends, political pressures, or processes with an unidentified, non-substantive background. It should be emphasized that the accuracy of the whole model is 0.84. The described tools and methods are already directly applicable in many areas related to the support of R&D activity worldwide. The article presents a solution that effectively enables the management of more precise programmes supporting innovative activities used for the first time in Poland. It is also one of the first uses of these methods by public administration in the world. Our approach not only strengthens improved adjustment of the support offered for R&D activity, but also makes it possible to apply and improve management methods in public institutions.

show abstract

An Optimized Textual Document Categorization Based on Fast Fourier Transform

Singh

Kaur

Nandi

et al. 2023

Lecture Notes in Networks and Systems

View full text Add to dashboard Cite

High performing sentiment analysis based on fast Fourier transform over temporal intuitionistic fuzzy value

Cited by 5 publications

References 46 publications

Sentiment Analysis Using Improved Atom Search Optimizer With a Simulated Annealing and ReLU Based Gated Recurrent Unit

Sentiment Analysis Using Improved Atom Search Optimizer With a Simulated Annealing and ReLU Based Gated Recurrent Unit

Potential for the use of large unstructured data resources by public innovation support institutions

An Optimized Textual Document Categorization Based on Fast Fourier Transform

Contact Info

Product

Resources

About