Get 20M+ Full-Text Papers For Less Than $1.50/day. Start a 14-Day Trial for You or Your Team.

Learn More →

TRG-DAtt: The Target Relational Graph and Double Attention Network Based Sentiment Analysis and Prediction for Supporting Decision Making

TRG-DAtt: The Target Relational Graph and Double Attention Network Based Sentiment Analysis and... The management of public opinion and the use of big data monitoring to accurately judge and verify all kinds of information are valuable aspects in the enterprise management decision-making process. The sentiment analysis of reviews is a key decision-making tool for e-commerce development. Most existing review sentiment analysis methods involve sequential modeling but do not focus on the semantic relationships. However, Chinese semantics are different from English semantics in terms of the sentence structure. Irrelevant contextual words may be incorrectly identified as cues for sentiment prediction. The influence of the target words in reviews must be considered. Thus, this paper proposes the TRG-DAtt model for sentiment analysis based on target relational graph (TRG) and double attention network (DAtt) to analyze the emotional information to support decision making. First, dependency tree-based TRG is introduced to independently and fully mine the semantic relationships. We redefine and constrain the dependency and use it as the edges to connect the target and context words. Second, we design dependency graph attention network (DGAT) and interactive attention network (IAT) to form the DAtt and obtain the emotional features of the target words and reviews. DGAT models the dependency of the TRG by aggregating the semantic information. Next, the target emotional enhancement features obtained by the DGAT are input to the IAT. The influence of each target word on the review can be obtained through the interaction. Finally, the target emotional enhancement features are weighted by the impact factor to generate the review's emotional features. In this study, extensive experiments were conducted on the car and Meituan review data sets, which contain consumer reviews on cars and stores, respectively. The results demonstrate that the proposed model outperforms the existing models. http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png ACM Transactions on Management Information Systems (TMIS) Association for Computing Machinery

TRG-DAtt: The Target Relational Graph and Double Attention Network Based Sentiment Analysis and Prediction for Supporting Decision Making

Download PDF
25 pages

Loading next page...
 
/lp/association-for-computing-machinery/trg-datt-the-target-relational-graph-and-double-attention-network-I80xREzF5K

References

References for this paper are not available at this time. We will be adding them shortly, thank you for your patience.

Publisher
Association for Computing Machinery
Copyright
Copyright © 2021 Association for Computing Machinery.
ISSN
2158-656X
eISSN
2158-6578
DOI
10.1145/3462442
Publisher site
See Article on Publisher Site

Abstract

The management of public opinion and the use of big data monitoring to accurately judge and verify all kinds of information are valuable aspects in the enterprise management decision-making process. The sentiment analysis of reviews is a key decision-making tool for e-commerce development. Most existing review sentiment analysis methods involve sequential modeling but do not focus on the semantic relationships. However, Chinese semantics are different from English semantics in terms of the sentence structure. Irrelevant contextual words may be incorrectly identified as cues for sentiment prediction. The influence of the target words in reviews must be considered. Thus, this paper proposes the TRG-DAtt model for sentiment analysis based on target relational graph (TRG) and double attention network (DAtt) to analyze the emotional information to support decision making. First, dependency tree-based TRG is introduced to independently and fully mine the semantic relationships. We redefine and constrain the dependency and use it as the edges to connect the target and context words. Second, we design dependency graph attention network (DGAT) and interactive attention network (IAT) to form the DAtt and obtain the emotional features of the target words and reviews. DGAT models the dependency of the TRG by aggregating the semantic information. Next, the target emotional enhancement features obtained by the DGAT are input to the IAT. The influence of each target word on the review can be obtained through the interaction. Finally, the target emotional enhancement features are weighted by the impact factor to generate the review's emotional features. In this study, extensive experiments were conducted on the car and Meituan review data sets, which contain consumer reviews on cars and stores, respectively. The results demonstrate that the proposed model outperforms the existing models.

Journal

ACM Transactions on Management Information Systems (TMIS) – Association for Computing Machinery

Published: Oct 28, 2021

Keywords: Sentiment analysis

References

  • A topic sentence-based instance transfer method for imbalanced sentiment classification of Chinese product reviews[J]
    [,
  • Emotion and decision making[J]
    [,
  • The interaction of affect and cognition: A neurobiological perspective[C]
    [,
  • Toward a more contextual, psychological, and dynamic model of emotional intelligence[M]
    [,
  • Brain, emotion and decision making: the paradigmatic example of regret[J]
    [,
  • A Bi-LSTM mention hypergraph model with encoding schema for mention extraction[J]
    [,
  • Chinese short text classification with mutual-attention convolutional neural networks[J]
    [,
  • Hierarchical convolutional attention networks using joint Chinese word embedding for text classification[C]
    [,
  • Post text processing of Chinese speech recognition based on bidirectional LSTM networks and CRF[J]
    [,
  • Targeted sentiment classification based on attentional encoding and graph convolutional networks[J]
    [,
  • Target-sensitive memory networks for aspect sentiment classification[C]
    [,
  • Targeted sentiment classification with attentional encoder network[C]
    [,
  • Multi-layer attention based CNN for target-dependent sentiment classification[J]
    [,
  • Natural language modeling with syntactic structure dependency[J]
    [,
  • Appraisal expression recognition with syntactic path for sentence sentiment classification[J]
    [,
  • Aspect-level sentiment analysis via convolution over dependency tree[C]
    [,
  • Improve relation extraction with dual attention-guided graph convolutional networks[J]
    [,
  • ALGA: Adaptive lexicon learning using genetic algorithm for sentiment analysis of microblogs[J]
    [,
  • Document-level sentiment classification: An empirical comparison between SVM and ANN[J]
    [,
  • Sentiment analysis of law enforcement performance using support vector machine and K-nearest neighbor[C]
    [,
  • SFV-CNN: Deep text sentiment classification with scenario feature representation[C]
    [,
  • Three-way enhanced convolutional neural networks for sentence-level sentiment classification[J]
    [,
  • Multi-task learning model based on multi-scale CNN and LSTM for sentiment classification[J]
    [,
  • Sentiment classification with adversarial learning and attention mechanism[J]
    [,
  • Graph-based dependency parsing with graph neural networks[C]
    [,
  • A recommendation approach based on product attribute reviews: Improved collaborative filtering considering the sentiment polarity[J]
    [,
  • An approach to alleviate the sparsity problem of hybrid collaborative filtering based recommendations: The product-attribute perspective from user reviews[J]
    [,
  • Hierarchical attention networks for document classification[C]
    [,
  • A hierarchical structured self-attentive model for extractive document summarization (HSSAS)[J]
    [,
  • Domain-specific meta-embedding with latent semantic structures[J]
    [,
  • A novel attention-based hybrid CNN-RNN architecture for sEMG-based gesture recognition[J]
    [,
  • Targeted aspect-based sentiment analysis via embedding commonsense knowledge into an attentive LSTM[C]
    [,
  • Effective LSTMs for target-dependent sentiment classification
    [,
  • A hierarchical recurrent approach to predict scene graphs from a visual attention, riented perspective[J]
    [,
  • ASRNN: A recurrent neural network with an attention model for sequence labeling[J]
    [,
  • Graph attention networks[J]
    [,
  • Modeling polypharmacy side effects with graph convolutional networks[J]
    [,
  • Graph attention spatial-temporal network with collaborative global-local learning for citywide mobile traffic prediction[J]
    [,
  • Attention is all you need[C]
    [,
  • Text sentiment orientation analysis based on multi-channel CNN and bidirectional GRU with attention mechanism[J]
    [,
  • Cross-modality interactive attention network for multispectral pedestrian detection[J]
    [,
  • Focal loss for dense object detection[J]
    [,
  • The reliability and validity of the adolescent physical activity recall questionnaire[J]
    [,
  • Deep Learning[M]
    [,
  • Attention-based BiGRU-CNN for Chinese question classification[J]
    [,
  • A hierarchical bidirectional GRU model with attention for EEG-based emotion classification[J]
    [,
  • Bert: Pre-training of deep bidirectional transformers for language understanding[J]
    [,
  • Aspect sentiment classification with document-level sentiment preference modeling[C]
    [,