Abstract: Sentiment analysis is an important natural language processing (NLP) task due to a wide range of applications. Most existing sentiment analysis techniques are limited to the analysis carried out at the aggregate level, merely providing negative, neutral, and positive sentiments. The latest deep learning-based methods have been leveraged to provide more than 3 sentiment classes. However, such learning-based methods are still black-box based methods rather than explainable language processing methods. To address this gap, this research proposes a new explainable fine-grained multi-class sentiment analysis method, namely MiMuSA, which mimics the human language understanding processes. The proposed method involves a multi-level modular structure designed to mimic human’s language understanding processes, e.g., ambivalence handling process, sentiment strength handling process, etc. Specifically, multiple knowledge bases including basic knowledge base, negation and special knowledge base, sarcasm rule and adversative knowledge base, and sentiment strength knowledge base are built to support the sentiment understanding process.
Biography: Zhaoxia WANG is an Associate Professor of Computer Science (Practice) in the School of Computing and Information Systems of Singapore Management University (SMU). Prior to joining SMU, she was with the Institute of High Performance Computing (IHPC) under Agency for Science, Technology and Research (A*STAR), Singapore, rising to the position of Senior Scientist and Programme Manager. She has held various positions in a few academic institutions, including Visiting Scholar at the University of Birmingham, UK, Adjunct Professor at Tianjin University, Adjunct Faculty at National University of Singapore, and Adjunct Professor at Nanjing University of Information Science and Technology. Her research interests include natural language processing, machine learning, sentiment analysis, time series analysis, complex system analysis, image processing, knowledge graph, knowledge representation, causal reasoning, and intelligent robots. She is Associate Editor of Complex & Intelligent Systems, IEEE Transactions on Affective Computing, and IEEE Transactions on Emerging Topics in Computational Intelligence.
Address:Zhaoxia WANG, Ph.D. School of Computing and Information Systems (SCIS) Singapore Management University 80 Stamford Road, Singapore 178902
Tel: +65 6826 1347
Email: zxwang@smu.edu.sg.