Aspect-level sentiment classification based on attention-BiLSTM model and transfer learning

Xu, Guixian; Zhang, Zixin; Zhang, Ting; Sui, Yu; Meng, Yueting; Chen, Sijin

doi:10.1016/j.knosys.2022.108586

Cited by 35 publications

(4 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Model transfer is usually applied in multitask learning, by applying task data to multiple associated sub-tasks, and using shared modules to learn the association between tasks to obtain additional useful information. In specific applications, Xu [20] proposed a pre-training + multi-task learning model. By using the shared module BiLSTM to first train the document-level data set to obtain the pre-training weight, and reserve the weight as the initialization parameter of the shared part of the model, and secondly, enter the aspect-level data into the pre-trained model to train two task to eventually fine-tune these weights.…”

Section: B Transfer Learningmentioning

confidence: 99%

“…To be able to flexibly apply data knowledge in the document level, Chen [34] proposed a model based on transfer capsules. Different from the training method in [20], Chen adopts a multi-task learning method of heterogeneous datasets [22], directly puts rich document-level datasets and aspect-level datasets into the model at the same time, and dynamically optimizes the shared parameters. Finally, on the upper layer of the model, semantic capsules and dynamic routing are combined with the acquired transfer knowledge.…”

Section: B Transfer Learningmentioning

confidence: 99%

“…In the literature, several studies such as [20], [34]and others have utilized the concept of transfer learning to effectively transfer the sentiment knowledge obtained from the DSC task data to the ASC task by employing model transfer and parameter sharing. The former is known as the source task while the latter as the target task.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Aspect-Level Sentiment Classification Based on Auto-Adaptive Model Transfer

et al. 2023

View full text Add to dashboard Cite

Aspect-level sentiment classification (ASC) is a fine-grained sentiment analysis task that involves detecting the sentiment polarity of a specific opinion target in a given sentence. Despite the popularity of deep learning methods, the limited availability of ASC training data has resulted in the suboptimal performance of neural network models. To address this issue, researchers have proposed transferring resource-rich document-level sentiment knowledge to ASC tasks using model transfer and shared parameters. However, these methods have neglected the impact of differences in the training data for different tasks on the shared layer parameters. Therefore, this paper proposes a transfer method that automatically adapts to task and domain differences-Auto-adaptive Model Transfer (AAMT). This method considers adding specific disturbance variables on shared layer parameters to subdivide task differences to further obtain more accurate and effective transfer knowledge. In addition, on this basis, we introduce an attention mechanism to combine aspect and sentence features to better capture the sentiment vocabulary associated with a given target. A series of experiments on three public datasets show that our proposed method can solve the problem of insufficient training data for ASC and achieve good results.

show abstract

Section: B Transfer Learningmentioning

confidence: 99%

Section: B Transfer Learningmentioning

confidence: 99%

See 1 more Smart Citation

Aspect-Level Sentiment Classification Based on Auto-Adaptive Model Transfer

et al. 2023

View full text Add to dashboard Cite

show abstract

“…Guixian Xu et al [13] propose an aspect-level sentiment classification model based on Attention-Bidirectional Long Short-Term Memory (Attention-BiLSTM) model and transfer learning. The authors propose three models, including Pre-training (PRET), Multitask learning (MTL), and Pretraining and multitask learning (PRET+MTL), which transfer the knowledge obtained from document-level training of sentiment classification to aspect-level sentiment classification.…”

mentioning

confidence: 99%

Aspect-Based Sentiment Analysis of Twitter Influencers to Predict the Trend of Cryptocurrencies Based on Hybrid Deep Transfer Learning Models

Jahanbin,

Chahooki

2023

IEEE Access

View full text Add to dashboard Cite

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.INDEX TERMS Aspect Based sentiment analysis, Prediction trend price, Cryptocurrencies, Pre-trained networks, Hybrid deep learning models.

show abstract