Projects per year
Abstract
In this study, sentiment classification and emotion distribution learning across domains are both formulated as a semi-supervised domain adaptation problem, which utilizes a small amount of labeled documents in the target domain for model training. By introducing a shared matrix that captures the stable association between document clusters and word clusters, non-negative matrix tri-factorization (NMTF) is robust to the labeled target domain data and has shown remarkable performance in cross-domain text classification. However, the existing NMTF-based models ignore the incompatible relationship of sentiment polarities and the relatedness among emotions. Besides, their applications on large-scale datasets are limited by the high computation complexity. To address these issues, we propose a semi-supervised NMTF framework for sentiment classification and emotion distribution learning across domains. Based on a many-to-many mapping between document clusters and sentiment polarities (or emotions), we first incorporate the prior information of label dependency to improve the model performance. Then, we develop a parallel algorithm based on message passing interface (MPI) to further enhance the model scalability. Extensive experiments on real-world datasets validate the effectiveness of our method.
Original language | English |
---|---|
Article number | 74 |
Number of pages | 30 |
Journal | ACM Transactions on Knowledge Discovery from Data |
Volume | 17 |
Issue number | 5 |
Early online date | 18 Nov 2022 |
DOIs | |
Publication status | Published - Jun 2023 |
Bibliographical note
Publisher Copyright:© 2023 Association for Computing Machinery.
Keywords
- emotion distribution learning
- label dependency
- non-negative matrix tri-factorization
- Semi-supervised learning
- sentiment classification
Fingerprint
Dive into the research topics of 'Semi-supervised Sentiment Classification and Emotion Distribution Learning Across Domains'. Together they form a unique fingerprint.Projects
- 3 Finished
-
Data Augmentation Techniques for Contrastive Sentence Representation Learning
XIE, H. (PI), LI, Z. (CoI) & WONG, T. L. (CoI)
1/08/22 → 31/07/24
Project: Grant Research
-
Modeling Bitcoin Transaction Network via Structural Identity Representation
XIE, H. (PI) & DAI, H. H. (CoI)
1/07/22 → 30/06/23
Project: Grant Research
-
Cluster-level Social Emotion Classification Across Domains
XIE, H. (PI)
1/03/22 → 28/02/23
Project: Grant Research