Aspect-Based Sentiment Analysis of Twitter Influencers to Predict the Trend of Cryptocurrencies Based on Hybrid Deep Transfer Learning Models
With the expansion of social networks, sentiment analysis has become one of the hot topics in machine learning. However, in traditional sentiment analysis, the text is considered of a general nature and ignores the different aspects that may exist in the text. This paper presents a hybrid model of t...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2023-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10292644/ |
| _version_ | 1827769227471224832 |
|---|---|
| author | Kia Jahanbin Mohammad Ali Zare Chahooki |
| author_facet | Kia Jahanbin Mohammad Ali Zare Chahooki |
| author_sort | Kia Jahanbin |
| collection | DOAJ |
| description | With the expansion of social networks, sentiment analysis has become one of the hot topics in machine learning. However, in traditional sentiment analysis, the text is considered of a general nature and ignores the different aspects that may exist in the text. This paper presents a hybrid model of transfer deep learning methods for the aspect-oriented sentiment analysis of influencers’ tweets to predict the trend of cryptocurrencies. In the first model, different aspects of tweets are extracted using the Concept Latent Dirichlet Allocation (Concept-LDA). Then, by using the pre-trained RoBERTa network and combining it with the Bidirectional Gated Recurrent Unit (BiGRU) deep learning network and attention layer, sentiments of different aspects of tweets are determined. In the following, the price trend of seven cryptocurrencies, Bitcoin, Ethereum, Binance, Ripple, Dogecoin, Cardano, and Solana, is determined using the historical price and the polarity of tweets with BiGRU combined deep neural network and the attention layer. Also, we used the gridsearch method to select dropout hyper-parameters, learning rate, and the number of GRU units, and the Akaike Information Criterion (AIC) criterion confirmed the results of this proposed combination. The results show that the proposed model in the aspect-based sentiment analysis section has been able to achieve 5.94% accuracy and 9.9% improvement in the f1-score on the SemEval 2015 dataset and 2.61% improvement on the SemEval 2016 dataset in f1-score compared to the state-of-arts. Also, the results of predicting the price trend of cryptocurrencies show that the proposed model has correctly recognized the price trend in the next five days in 77% of cases according to the ROC-AUC criterion. |
| first_indexed | 2024-03-11T12:22:20Z |
| format | Article |
| id | doaj.art-fa9d38f94ce647f69e069931cea06978 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-03-11T12:22:20Z |
| publishDate | 2023-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-fa9d38f94ce647f69e069931cea069782023-11-07T00:01:21ZengIEEEIEEE Access2169-35362023-01-011112165612167010.1109/ACCESS.2023.332706010292644Aspect-Based Sentiment Analysis of Twitter Influencers to Predict the Trend of Cryptocurrencies Based on Hybrid Deep Transfer Learning ModelsKia Jahanbin0https://orcid.org/0000-0003-3330-5751Mohammad Ali Zare Chahooki1Department of Computer Engineering, Yazd University, Yazd, IranDepartment of Computer Engineering, Yazd University, Yazd, IranWith the expansion of social networks, sentiment analysis has become one of the hot topics in machine learning. However, in traditional sentiment analysis, the text is considered of a general nature and ignores the different aspects that may exist in the text. This paper presents a hybrid model of transfer deep learning methods for the aspect-oriented sentiment analysis of influencers’ tweets to predict the trend of cryptocurrencies. In the first model, different aspects of tweets are extracted using the Concept Latent Dirichlet Allocation (Concept-LDA). Then, by using the pre-trained RoBERTa network and combining it with the Bidirectional Gated Recurrent Unit (BiGRU) deep learning network and attention layer, sentiments of different aspects of tweets are determined. In the following, the price trend of seven cryptocurrencies, Bitcoin, Ethereum, Binance, Ripple, Dogecoin, Cardano, and Solana, is determined using the historical price and the polarity of tweets with BiGRU combined deep neural network and the attention layer. Also, we used the gridsearch method to select dropout hyper-parameters, learning rate, and the number of GRU units, and the Akaike Information Criterion (AIC) criterion confirmed the results of this proposed combination. The results show that the proposed model in the aspect-based sentiment analysis section has been able to achieve 5.94% accuracy and 9.9% improvement in the f1-score on the SemEval 2015 dataset and 2.61% improvement on the SemEval 2016 dataset in f1-score compared to the state-of-arts. Also, the results of predicting the price trend of cryptocurrencies show that the proposed model has correctly recognized the price trend in the next five days in 77% of cases according to the ROC-AUC criterion.https://ieeexplore.ieee.org/document/10292644/Aspect based sentiment analysisprediction trend pricecryptocurrenciespre-trained networkshybrid deep learning models |
| spellingShingle | Kia Jahanbin Mohammad Ali Zare Chahooki Aspect-Based Sentiment Analysis of Twitter Influencers to Predict the Trend of Cryptocurrencies Based on Hybrid Deep Transfer Learning Models IEEE Access Aspect based sentiment analysis prediction trend price cryptocurrencies pre-trained networks hybrid deep learning models |
| title | Aspect-Based Sentiment Analysis of Twitter Influencers to Predict the Trend of Cryptocurrencies Based on Hybrid Deep Transfer Learning Models |
| title_full | Aspect-Based Sentiment Analysis of Twitter Influencers to Predict the Trend of Cryptocurrencies Based on Hybrid Deep Transfer Learning Models |
| title_fullStr | Aspect-Based Sentiment Analysis of Twitter Influencers to Predict the Trend of Cryptocurrencies Based on Hybrid Deep Transfer Learning Models |
| title_full_unstemmed | Aspect-Based Sentiment Analysis of Twitter Influencers to Predict the Trend of Cryptocurrencies Based on Hybrid Deep Transfer Learning Models |
| title_short | Aspect-Based Sentiment Analysis of Twitter Influencers to Predict the Trend of Cryptocurrencies Based on Hybrid Deep Transfer Learning Models |
| title_sort | aspect based sentiment analysis of twitter influencers to predict the trend of cryptocurrencies based on hybrid deep transfer learning models |
| topic | Aspect based sentiment analysis prediction trend price cryptocurrencies pre-trained networks hybrid deep learning models |
| url | https://ieeexplore.ieee.org/document/10292644/ |
| work_keys_str_mv | AT kiajahanbin aspectbasedsentimentanalysisoftwitterinfluencerstopredictthetrendofcryptocurrenciesbasedonhybriddeeptransferlearningmodels AT mohammadalizarechahooki aspectbasedsentimentanalysisoftwitterinfluencerstopredictthetrendofcryptocurrenciesbasedonhybriddeeptransferlearningmodels |