GP-GCN: Global features of orthogonal projection and local dependency fused graph convolutional networks for aspect-level sentiment classification

Wei, Subo; Zhu, Guangli; Sun, Zhengyan; Li, Xiaoqing; Weng, Tien‐Hsiung

doi:10.1080/09540091.2022.2080183

Cited by 13 publications

(2 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Also, TrigNet architecture which consists of a tripartite graph network and a BERT-based graph initializer was proposed by Yang et al [39] aims to structural psycholinguistic knowledge from LIWC for personality detection. In [40], the authors designed a system to capture the dependency information hidden in the psycholinguistic features combined with syntactic information of documents to predict personality prediction. Also, in [41] the authors proposed HG-PerCon, which leverages representations of users upon their historical and psychological knowledge for cross-view contrastive learning.…”

Section: B) Related Workmentioning

confidence: 99%

TranSentGAT: A Sentiment-Based Lexical Psycholinguistic Graph Attention Network for Personality Prediction

Bajestani,

Khalilzadeh,

Azarnoosh

et al. 2024

IEEE Access

View full text Add to dashboard Cite

Extended use of social media, lead to personality detection from online content shared by users.While it has numerous applications in different areas such as recommendation systems, most of existing studies focus on superficial, statistical, and explicit user contents, ignoring the knowledge hidden in semantic features. In this study, we proposed a method to explore psycholinguistic knowledge hidden in deep levels of users data for the task of personality prediction. We proposed a method utilizing fine-tuned domain-specific BERT model to extract features from a sentence, and enriched the outputs by leveraging emotional information to highlight the important words. Furthermore, by conducting a double-way-attention mechanism we reflected the information from highlighted words into the whole knowledge extracted from inputs. Then, created a graph by considering extracted embeddings from last step as node features and developing a dynamic and task-realted learning approach to specify edges to connect different pairs of nodes based on a neural network, and leveraged graph attention network to predict personality traits. Finally, experimental results confirmed the effectiveness of our proposed model with 80.63% of accuracy, compared to other stateof-the-art studies for the essays dataset. Also, several ablations are conducted to illustrate and verify the impact of different sections and parameteres of the proposed architecture.

show abstract

Section: B) Related Workmentioning

confidence: 99%

TranSentGAT: A Sentiment-Based Lexical Psycholinguistic Graph Attention Network for Personality Prediction

Bajestani,

Khalilzadeh,

Azarnoosh

et al. 2024

IEEE Access

View full text Add to dashboard Cite

show abstract

“…There are three subtasks, including sentiment extraction (SE), for example, good, bad, like, etc. ; aspect-level sentiment classification (ASC), for example, positive, negative, and natural; and aspect term extraction (ATE), related to the diagnosis of the disease, which aims at associating each aspect with its respective polarity separately [5]. MABSA functionally operates at the intersection of information retrieval, natural language processing, and artificial intelligence.…”

Section: Introductionmentioning

confidence: 99%

Multi-Task Aspect-Based Sentiment: A Hybrid Sampling and Stance Detection Approach

Waheeb

2023

Applied Sciences

View full text Add to dashboard Cite

This paper discusses the challenges associated with a class imbalance in medical data and the limitations of current approaches, such as machine multi-task learning (MMTL), in addressing these challenges. The proposed solution involves a novel hybrid data sampling method that combines SMOTE, a meta-weigher with a meta-based self-training method (MMS), and one-sided selection (OSS) to balance the distribution of classes. The method also utilizes condensed nearest neighbors (CNN) to remove noisy majority examples and redundant examples. The proposed technique is twofold, involving the creation of artificial instances using SMOTE-OSS-CNN to oversample the under-represented class distribution and the use of MMS to train an instructor model that produces in-field knowledge for pseudo-labeled examples. The student model uses these pseudo-labels for supervised learning, and the student model and MMS meta-weigher are jointly trained to give each example subtask-specific weights to balance class labels and mitigate the noise effects caused by self-training. The proposed technique is evaluated on a discharge summary dataset against six state-of-the-art approaches, and the results demonstrate that it outperforms these approaches with complete labeled data and achieves results equivalent to state-of-the-art methods that require all labeled data using aspect-based sentiment analysis (ABSA).

show abstract

Causality extraction model based on two-stage GCN

et al. 2022

Self Cite

View full text Add to dashboard Cite

In the traditional methods, the low identification accuracy of cascade implicit causalities is caused by the lack of causal inference. To solve this problem, we propose a causality extraction model based on GCN to infer the causality of the text. It can analyze the cause-effect existing in the text and realize the deep extraction under semantic enhancement. First, the data are preprocessed, and BERT is used for pre-training. In the pre-training, the candidate entities are selected by entity links. The text encoding is used context semantics and embedding location coding. Then, the semantic dependency graph is used to obtain the relationship between entities. In addition, the nodes and edges obtained by the previous step are input into the first-stage GCN to extract the whole causality. Finally, the entity relation graph obtained by the first-stage GCN is introduced into the second-stage GCN for cascade inference. The causality of the cascade is inferred and extracted by a two-stage GCN. Experiments show that the model can find implicit causality more accurately generate new implicit causal entities on the original causality.

show abstract

GP-GCN: Global features of orthogonal projection and local dependency fused graph convolutional networks for aspect-level sentiment classification

Cited by 13 publications

References 45 publications

TranSentGAT: A Sentiment-Based Lexical Psycholinguistic Graph Attention Network for Personality Prediction

TranSentGAT: A Sentiment-Based Lexical Psycholinguistic Graph Attention Network for Personality Prediction

Multi-Task Aspect-Based Sentiment: A Hybrid Sampling and Stance Detection Approach

Causality extraction model based on two-stage GCN

Contact Info

Product

Resources

About