Multi-Attention Network for Aspect Sentiment Analysis

Han, Huiyu; Li, Xiaoge; Zhi, Shuting; Wang, Haoyue

doi:10.1145/3316615.3316673

Cited by 11 publications

(5 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For aspect phrases, different words contribute to the aspect expression differently. Attention mechanism that phrase is an important part of the model is able to focus on, so as to promote the accuracy of sentiment classification [11]. In general, our model achieves better results on datasets of four different domains and two different languages than other models.…”

Section: -Class Sentimental Classificationmentioning

confidence: 87%

“…This phenomenon poses a threat to the simple location weight calculation. In this paper, citing the punctuation-based algorithm proposed by Han [11] to be calculated.…”

Section: Figure 2 the Relative Distances Between Words And Aspect Tamentioning

confidence: 99%

“…The above deficiencies, a model named LSTM-MATT-AC [11] is proposed, which introduce Multiple attention combining mechanisms (MATT) and aspect context module(AC). Where multi-attention mechanism consists of three parts: content attention, location attention, and class attention.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Multi-Layer Attention Approach for Aspect based Sentiment Analysis

Ai¹,

Li²,

Hu³

et al. 2020

Computer Science &Amp; Information Technology (CS &Amp; IT)

Self Cite

View full text Add to dashboard Cite

Based on the aspect-level sentiment analysis is typical of fine-grained emotional classification that assigns sentiment polarity for each of the aspects in a review. For better handle the emotion classification task, this paper put forward a new model which apply Long Short-Term Memory network combine multiple attention with aspect context. Where multiple attention mechanism (i.e., location attention, content attention and class attention) refers to takes the factors of context location, content semantics and class balancing into consideration. Therefore, the proposed model can adaptively integrate location and semantic information between the aspect targets and their contexts into sentimental features, and overcome the model data variance introduced by the imbalanced training dataset. In addition, the aspect context is encoded on both sides of the aspect target, so as to enhance the ability of the model to capture semantic information. The Multi-Attention mechanism (MATT) and Aspect Context (AC) allow our model to perform better when facing reviews with more complicated structures. The result of this experiment indicate that the accuracy of the new model is up to 80.6% and 75.1% for two datasets in SemEval-2014 Task 4 respectively, While the accuracy of the data set on twitter 71.1%, and 81.6% for the Chinese automotive-domain dataset. Compared with some previous models for sentiment analysis, our model shows a higher accuracy.

show abstract

Section: -Class Sentimental Classificationmentioning

confidence: 87%

“…This phenomenon poses a threat to the simple location weight calculation. In this paper, citing the punctuation-based algorithm proposed by Han [11] to be calculated.…”

Section: Figure 2 the Relative Distances Between Words And Aspect Tamentioning

confidence: 99%

See 1 more Smart Citation

Multi-Layer Attention Approach for Aspect based Sentiment Analysis

Ai¹,

Li²,

Hu³

et al. 2020

Computer Science &Amp; Information Technology (CS &Amp; IT)

Self Cite

View full text Add to dashboard Cite

show abstract

“…Kumar et al [45] proposed a soft attention-based LSTM with CNN for sarcasm detection. Han et al [46] proposed a Multi-Attention Network (MAN) model which adopts several attention networks, the model solve the problem of the RNN-based model can't extract the potential correlation between relatively distant sentiment words and aspect words in complex statements, and the proposed model could achieve consistently superior results on three datasets. Gao et al [47] propose a collaborative extraction hierarchical attention network, this proposed method achieves better performance than the methods which only use aspect features to extract sentiment feature for aspect-level sentiment classification on SemEval competition data set.…”

Section: Related Workmentioning

confidence: 99%

Text Sentiment Orientation Analysis Based on Multi-Channel CNN and Bidirectional GRU With Attention Mechanism

et al. 2020

View full text Add to dashboard Cite

Convolutional Neural Network(CNN) and Recurrent Neural Network(RNN) have been widely used in the field of text sentiment analysis and have achieved good results. However, there is an anteroposterior dependency between texts, although CNN can extract local information between consecutive words of a sentence, it ignores the contextual semantic information between words. Bidirectional GRU can make up for the shortcomings that CNN can't extract contextual semantic information of long text, but it can't extract the local features of the text as well as CNN. Therefore, we propose a multi-channel model that combines the CNN and the bidirectional gated recurrent unit network with attention mechanism (MC-AttCNN-AttBiGRU). The model can pay attention to the words that are important to the sentiment polarity classification in the sentence through the attention mechanism and combine the advantages of CNN to extract local features of text and bidirectional GRU to extract contextual semantic information of long text, which improves the text feature extraction ability of the model. The experimental results on the IMDB dataset and Yelp 2015 dataset show that the proposed model can extract more rich text features than other baseline models, and can achieve better results than other baseline models. INDEX TERMS Convolutional Neural Network, Bidirectional gated recurrent unit network, attention mechanism, text sentiment orientation analysis.

show abstract

“…Subsequent studies indicate that the introduction of attention mechanisms can help solve this problem [9], [16]. A complex statement may contain multiple aspect words.…”

Section: Related Workmentioning

confidence: 99%

CE-HEAT: An Aspect-Level Sentiment Classification Approach With Collaborative Extraction Hierarchical Attention Network

Gao

Liu

et al. 2019

IEEE Access

View full text Add to dashboard Cite

Aspect-level sentiment classification is a fine-grained sentiment analysis task. It aims to predict the sentiment of a review in different aspects. Recently many works exploit the hierarchical attention network to capture the aspect-specific sentiment information. However, the prior work only attends to use the aspect terms to capture the aspect-specific sentiment information in the text. It may cause the mismatch of sentiment for the aspect-specific when the aspect words are extracted incorrectly. Since the number of aspect words is much more than that sentiment words, some uncommon aspect terms are more difficult to be extracted than uncommon sentiment terms. To solve this problem, we propose a collaborative extraction hierarchical attention network. It consists of two hierarchical attention units, i.e.. One unit extracts the sentiment features by the sentiment attention layer and uses the sentiment features to capture the specific aspect-related sentiment aspect information by the aspect attention layer. The other extracts the aspect features by the aspect attention layer and uses the aspect features to help capture the aspect-specific sentiment information by the sentiment attention layer. Moreover, we use the SemEval competition data set to verify our approach. The experiment shows that our approach achieves better performance than the methods which only use aspect features to extract sentiment feature for aspect-level sentiment classification. INDEX TERMS Sentiment analysis, aspect-level sentiment classification, collaborative extraction hierarchical attention network.

show abstract

Multi-Attention Network for Aspect Sentiment Analysis

Cited by 11 publications

References 5 publications

Multi-Layer Attention Approach for Aspect based Sentiment Analysis

Multi-Layer Attention Approach for Aspect based Sentiment Analysis

Text Sentiment Orientation Analysis Based on Multi-Channel CNN and Bidirectional GRU With Attention Mechanism

CE-HEAT: An Aspect-Level Sentiment Classification Approach With Collaborative Extraction Hierarchical Attention Network

Contact Info

Product

Resources

About