Sentiment Analysis of Electronic Social Media Based on Deep Learning

Derbentsev, Vasily; Bezkorovainyi, Vitalii; Matviychuk, Andriy; Pomazun, Oksana; Hrabariev, Andrii; Hostryk, Alexey

doi:10.5220/0011932300003432

Cited by 2 publications

(5 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There are five processes in data preprocessing, namely data cleaning, case folding, stop words, stemming, and tokenizing. Data cleaning is the process of cleaning data by removing non-alphabets, various tags, URLs, punctuation, spaces, and other markup elements [13]. Case folding is the process of converting uppercase letters in the input data into lowercase letters.…”

Section: Data Pre-processingmentioning

confidence: 99%

“…BI-LSTM is a model that combines two independent LSTMs, one with normal time order and one with reverse time order, allowing the input to be processed simultaneously. At each time step, the outputs of both LSTMs are concatenated [13], [17]. In many sequence processing tasks, it is important to analyze information from both the future and the past of a point in the sequence [13], [18], [19].…”

Section: Bi-directional Long Short-term Memory (Bi-lstm)mentioning

confidence: 99%

“…At each time step, the outputs of both LSTMs are concatenated [13], [17]. In many sequence processing tasks, it is important to analyze information from both the future and the past of a point in the sequence [13], [18], [19]. Unlike standard RNNs that only use the previous context, Bi-LSTM is specifically designed to learn long-term dependencies from both sides, and it has been proven to outperform other neural network architectures in phoneme per frame recognition [13], [17], [19].…”

Section: Bi-directional Long Short-term Memory (Bi-lstm)mentioning

confidence: 99%

“…In many sequence processing tasks, it is important to analyze information from both the future and the past of a point in the sequence [13], [18], [19]. Unlike standard RNNs that only use the previous context, Bi-LSTM is specifically designed to learn long-term dependencies from both sides, and it has been proven to outperform other neural network architectures in phoneme per frame recognition [13], [17], [19]. Several hyperparameters were modified in the Bi-LSTM, including the use of 64 data per batch for 10 epochs, 64 units, and dropout.…”

Section: Bi-directional Long Short-term Memory (Bi-lstm)mentioning

confidence: 99%

See 3 more Smart Citations

Detecting Hoax Content on Social Media Using Bi-LSTM and RNN

Aji,

Setiawan

2023

bits

View full text Add to dashboard Cite

Online media, such as websites and applications, have become a communication tool available on the internet. Social media is a part of online media that can be used to spread news, opinions, or even hoaxes, such as through Twitter. Although hoaxes are difficult to eliminate, several systems have been built using deep learning approaches that can process text and images to detect the truthfulness of news. In this study, four systems were built using four deep learning methods, namely Bi-directional Long Short-Term Memory (Bi-LSTM), Recurrent Neural Network (RNN), hybrid RNN-Bi-LSTM, and hybrid Bi-LSTM-RNN. Feature extraction was performed using Term Frequency - Inverse Document Frequency (TF-IDF) and feature expansion was performed using Global Vectors (GloVe). The data used has been adjusted according to the keyword of fake news on mainstream news portals. This study attempted several scenarios to compare the various methods that have been built, with the aim of finding the best method that provides the highest accuracy. The results showed that the Bi-LSTM method had the highest accuracy of 96.48%, while the hybrid Bi-LSTM-RNN method ranked second with an accuracy of 96.36%, followed by the RNN method with an accuracy of 95.49%, and the hybrid RNN-Bi-LSTM method with an accuracy of 95.34%.

show abstract

Section: Data Pre-processingmentioning

confidence: 99%

Section: Bi-directional Long Short-term Memory (Bi-lstm)mentioning

confidence: 99%

Section: Bi-directional Long Short-term Memory (Bi-lstm)mentioning

confidence: 99%

Section: Bi-directional Long Short-term Memory (Bi-lstm)mentioning

confidence: 99%

See 2 more Smart Citations

Detecting Hoax Content on Social Media Using Bi-LSTM and RNN

Aji,

Setiawan

2023

bits

View full text Add to dashboard Cite

show abstract

“…The paper "A comparative study of deep learning models for sentiment analysis of social media texts" by Vasily D. Derbentsev, Vitalii S. Bezkorovainyi, Andriy V. Matviychuk, Oksana M. Pomazun, Andrii V. Hrabariev, and Alexey M. Hostryk [48] presents a comparative study of deep learning models for sentiment analysis of social media texts.…”

Section: Articles Overviewmentioning

confidence: 99%

Advances in machine learning for the innovation economy: in the shadow of war

Danylchuk,

Semerikov

2023

View full text Add to dashboard Cite

This preface introduces the selected and revised papers presented at the 10th International Conference on Monitoring, Modeling & Management of Emergent Economy (M3E2 2022), held online in Ukraine, on November 17-18, 2022. The conference aimed to bring together researchers, practitioners, and students from various fields to exchange ideas, share experiences, and discuss challenges and opportunities in applying computational intelligence and data science for the innovation economy. The innovation economy is a term that describes the emerging paradigm of economic development that is driven by knowledge, creativity, and innovation. It requires new approaches and methods for solving complex problems, discovering new opportunities, and creating value in various domains of science, business,and society. Computational intelligence and data science are two key disciplines that can provide such approaches and methods by exploiting the power of data, algorithms, models, and systems to enable intelligent decision making, learning, adaptation, optimization, and discovery. The papers in this proceedings cover a wide range of topics related to computational intelligence and data science for the innovation economy. They include theoretical foundations, novel techniques, and innovative applications. The papers were selected and revised based on the feedback from the program committe members and reviewers who ensured their high quality. We would like to thank all the authors who submitted their papers to M3E2 2022. We also appreciate the keynote speakers who shared their insights and visions on the current trends and future directions of computational intelligence and data science for the innovation economy. We acknowledge the support of our sponsors, partners, and organizers who made this conference possible despite the challenging circumstances caused by the ongoing war in Ukraine. Finally, we thank all the participants who attended the conference online and contributed to its success.

show abstract

Sentiment Analysis of Electronic Social Media Based on Deep Learning

Cited by 2 publications

References 0 publications

Detecting Hoax Content on Social Media Using Bi-LSTM and RNN

Detecting Hoax Content on Social Media Using Bi-LSTM and RNN

Advances in machine learning for the innovation economy: in the shadow of war

Contact Info

Product

Resources

About