MG-SIN: Multigraph Sparse Interaction Network for Multitask Stance Detection
- 13 November 2023
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks and Learning Systems
- Vol. 36 (2) , 3111-3125
Abstract
Stance detection on social media aims to identify if an individual is in support of or against a specific target. Most existing stance detection approaches primarily rely on modeling the contextual semantic information in sentences and neglect to explore the pragmatics dependency information of words, thus degrading performance. Although several single-task learning methods have been proposed to capture richer semantic representation information, they still suffer from semantic sparsity problems caused by short texts on social media. This article proposes a novel multigraph sparse interaction network (MG-SIN) by using multitask learning (MTL) to identify the stances and classify the sentiment polarities of tweets simultaneously. Our basic idea is to explore the pragmatics dependency relationship between tasks at the word level by constructing two types of heterogeneous graphs, including task-specific and task-related graphs (tr-graphs), to boost the learning of task-specific representations. A graph-aware module is proposed to adaptively facilitate information sharing between tasks via a novel sparse interaction mechanism among heterogeneous graphs. Through experiments on two real-world datasets, compared with the state-of-the-art baselines, the extensive results exhibit that MG-SIN achieves competitive improvements of up to 2.1% and 2.42% for the stance detection task, and 5.26% and 3.93% for the sentiment analysis task, respectively.Keywords
Funding Information
- National Natural Science Foundation of China (62076079, 61976051, U19A2067)
- Guangdong Major Project of Basic and Applied Basic Research (2019B030302002)
- Major Key Project of Peng Cheng Laboratory (PCL2022A03)
- Shenzhen Science and Technology Program (ZDSYS20210623091809029)
This publication has 35 references indexed in Scilit:
- ABCDM: An Attention-based Bidirectional CNN-RNN Deep Model for sentiment analysisFuture Generation Computer Systems, 2021
- An Integrated Multi-Task Model for Fake News DetectionIEEE Transactions on Knowledge and Data Engineering, 2021
- Short Text Sentiment Analysis Based on Multi-Channel CNN With Multi-Head Attention MechanismIEEE Access, 2021
- Co-LSTM: Convolutional LSTM model for sentiment analysis in social big dataInformation Processing & Management, 2021
- Improving sentiment analysis with multi-task learning of negationNatural Language Engineering, 2020
- Pretrained Embeddings for Stance Detection with Hierarchical Capsule Network on Social MediaACM Transactions on Information Systems, 2020
- Neural Stance Detection With Hierarchical Linguistic RepresentationsIEEE/ACM Transactions on Audio, Speech, and Language Processing, 2020
- Person Reidentification via Multi-Feature Fusion With Adaptive Graph LearningIEEE Transactions on Neural Networks and Learning Systems, 2019
- Stance detection via sentiment information and neural network modelFrontiers of Computer Science, 2018
- Dynamic Affinity Graph Construction for Spectral Clustering Using Multiple FeaturesIEEE Transactions on Neural Networks and Learning Systems, 2018