Topic Driven Adaptive Network for cross-domain sentiment classification |
| |
| Institution: | 1. College of Management, Shenzhen University, Shenzhen, China, 518055;2. Greater Bay Area International Institute for Innovations, Shenzhen University, Shenzhen, China, 518055;3. Shenzhen University, Shenzhen, China, 518055;4. School of Logistics, Yunnan University of Finance and Economics, Kunming, 650221, China;1. Research Institute for Smart Cities, School of Architecture and Urban Planning, Shenzhen University and Shenzhen Key Laboratory of Spatial Smart Sensing and Services and MNR Technology Innovation Center of Territorial and Spatial Big Data and Guangdong–Hong Kong-Macau Joint Laboratory for Smart Cities, Shenzhen 518060, China;2. Logistics Information Centre, Beijing 100842, China;3. Department of Game Design, Faculty of Arts, Uppsala University, Sweden;1. School of Information Management, Central China Normal University, Wuhan, 430079, China;3. Center for Studies of Information Resources, Wuhan University, Wuhan, 430072, China;4. Institute of Medical Information, Chinese Academy of Medical Sciences & Peking Union Medical College, Beijing, 100020, China;5. School of Information Management, Wuhan University, Wuhan, 430072, China |
| |
| Abstract: | As a hot spot these years, cross-domain sentiment classification aims to learn a reliable classifier using labeled data from a source domain and evaluate the classifier on a target domain. In this vein, most approaches utilized domain adaptation that maps data from different domains into a common feature space. To further improve the model performance, several methods targeted to mine domain-specific information were proposed. However, most of them only utilized a limited part of domain-specific information. In this study, we first develop a method of extracting domain-specific words based on the topic information derived from topic models. Then, we propose a Topic Driven Adaptive Network (TDAN) for cross-domain sentiment classification. The network consists of two sub-networks: a semantics attention network and a domain-specific word attention network, the structures of which are based on transformers. These sub-networks take different forms of input and their outputs are fused as the feature vector. Experiments validate the effectiveness of our TDAN on sentiment classification across domains. Case studies also indicate that topic models have the potential to add value to cross-domain sentiment classification by discovering interpretable and low-dimensional subspaces. |
| |
| Keywords: | Sentiment analysis Transfer learning Topic model Transformer |
| 本文献已被 ScienceDirect 等数据库收录！ |
|
