An Attention-Based Multi-Representational Fusion Method for Social-Media-Based Text Classification
Open Access
- 29 March 2022
- journal article
- research article
- Published by MDPI AG in Information
- Vol. 13 (4) , 171
Abstract
There exist various text-classification tasks using user-generated contents (UGC) on social media in the big data era. In view of advantages and disadvantages of feature-engineering-based machine-learning models and deep-learning models, we argue that fusing handcrafted-text representation via feature engineering and data-driven deep-text representations extracted by performing deep-learning methods is conducive to enhancing text-classification capability. Given the characteristics of different deep neural networks, their complementary effect needs to be investigated. Moreover, contributions of these representations need to be adaptively learned when it comes to addressing different tasks or predicting different samples. Therefore, in this paper, we propose a novel fused deep-neural-network architecture with a hierarchical attention mechanism for text classification with social media data. Specifically, in the context that handcraft features are available, we employ the attention mechanism to adaptively fuse totally data-driven-text representation and handcrafted representation. For the generation of the data-driven-text representation, we propose a data-driven encoder that fuses text representations derived from three deep-learning methods with the attention mechanism, to adaptively select discriminative representation and explore their complementary effect. To verify the effectiveness of our approach, we performed two text-classification tasks, i.e., identifying adverse drug reaction (ADR)-relevant tweets from social media and identifying comparative-relevant reviews from an E-commerce platform. Experimental results demonstrate that our approach outperforms other baselines.Keywords
Funding Information
- National Natural Science Foundation of China (71701142)
- China Postdoctoral Science Foundation (2018M640346)
- Tianjin philosophy and social science planning project (TJKS19XSX-015)
This publication has 27 references indexed in Scilit:
- ABCDM: An Attention-based Bidirectional CNN-RNN Deep Model for sentiment analysisFuture Generation Computer Systems, 2021
- User generated content for exploring factors affecting intention to use travel and food delivery servicesInternational Journal of Hospitality Management, 2021
- Feature engineering vs. deep learning for paper section identification: Toward applications in Chinese medical literatureInformation Processing & Management, 2020
- Identifying malicious social media contents using multi-view Context-Aware active learningFuture Generation Computer Systems, 2019
- Bidirectional LSTM with attention mechanism and convolutional layer for text classificationNeurocomputing, 2019
- Collecting event‐related tweets from twitter streamJournal of the Association for Information Science and Technology, 2018
- Analysis of user-generated content from online social communities to characterise and predict depression degreeJournal of Information Science, 2017
- Filtering big data from social media – Building an early warning system for adverse drug reactionsJournal of Biomedical Informatics, 2015
- Portable automatic text classification for adverse drug reaction detection via multi-corpus trainingJournal of Biomedical Informatics, 2015
- Long Short-Term MemoryNeural Computation, 1997