TDAM: a Topic-Dependent Attention Model for Sentiment Analysis

@article{Pergola2019TDAMAT,
  title={TDAM: a Topic-Dependent Attention Model for Sentiment Analysis},
  author={Gabriele Pergola and Lin Gui and Yulan He},
  journal={Inf. Process. Manag.},
  year={2019},
  volume={56}
}

Figures and Tables from this paper

TAN-NTM: Topic Attention Networks for Neural Topic Modeling

A novel attention mechanism which factors in topic-word distribution to enable the model to attend on relevant words that convey topic related cues is proposed, which results in ~9-15 percentage improvement over score of existing SOTA topic models in NPMI coherence on several benchmark datasets.

Hierarchical Interaction Networks with Rethinking Mechanism for Document-level Sentiment Analysis

A Hierarchical Interaction Networks (HIN) is proposed to explore bidirectional interactions between the summary and document at multiple granularities and learn subject-oriented document representations for sentiment classification and a Sentiment-based Rethinking mechanism (SR) is designed.

Attention Mechanism with Gated Recurrent Unit Using Convolutional Neural Network for Aspect Level Opinion Mining

A novel approach using an attention mechanism with a gated recurrent unit and a convolutional neural network for aspect level opinion mining with different input vector representations is proposed.

Self-Attention Networks and Adaptive Support Vector Machine for aspect-level sentiment classification

The two-stage novel architecture named Self Attention Networks and Adaptive SVM (SAN-ASVM) for aspect-level sentiment classification is proposed, designed to substitute the SoftMax function to perform sentiment classification, which can effectively make multi-classifications in high-dimensional space.

Topic sentiment analysis using words embeddings dependency in edge social system

A novel topic sentiment joint model with word embeddings dependency based on recurrent neural network that fully extends the semantic information and redefines the topic sentiment‐word distribution and achieves better topic detection and sentiment analysis.

Online Latent Dirichlet Allocation Model Based on Sentiment Polarity Time Series

The topic evolution method that integrates the sentimental information of topic words proposed in this paper is better than the traditional model.

References

SHOWING 1-10 OF 43 REFERENCES

Interactive Attention Networks for Aspect-Level Sentiment Classification

It is argued that both targets and contexts deserve special treatment and need to be learned their own representations via interactive learning and proposed the interactive attention networks (IAN) to interactively learn attentions in the contexts and targets.

Aspect-based sentiment analysis with alternating coattention networks

Neural Sentiment Classification with User and Product Attention

A hierarchical neural network is proposed to incorporate global user and product information into sentiment classification and achieves significant and consistent improvements compared to all state-of-theart methods.

Personalized Microblog Sentiment Classification via Multi-Task Learning

This approach can capture the individual personality and at the same time leverage the common sentiment knowledge shared by all users, and improve microblog sentiment classification accuracy effectively and efficiently.

TopicRNN: A Recurrent Neural Network with Long-Range Semantic Dependency

In this paper, we propose TopicRNN, a recurrent neural network (RNN)-based language model designed to directly capture the global semantic meaning relating words in a document via latent topics.

Document Modeling with Gated Recurrent Neural Network for Sentiment Classification

A neural network model is introduced to learn vector-based document representation in a unified, bottom-up fashion and dramatically outperforms standard recurrent neural network in document modeling for sentiment classification.

Personalized Microblog Sentiment Classification via Adversarial Cross-lingual Multi-task Learning

A novel user-attention-based Convolutional Neural Network model with adversarial cross-lingual learning framework, in which with the help of user properties as bridge between languages, can extract language-specific features and language-independent features to enrich the user post representation so as to alleviate the data insufficiency problem.

Combining Deep Learning and Topic Modeling for Review Understanding in Context-Aware Recommendation

The proposed model is named LSTM-Topic matrix factorization (LTMF) which integrates both L STM and Topic Modeling for review understanding and shows the better ability on making topic clustering than traditional topic model based method.

Hierarchical Attention Networks for Document Classification

Experiments conducted on six large scale text classification tasks demonstrate that the proposed architecture outperform previous methods by a substantial margin.