In this study, we propose a method of constructing a domain-specific sentiment analysis knowledge graph (SAKG) to analyze online reviews. Sentiment knowledge is integrate...
Abstract:
Sentiment analysis of online reviews is an important task in natural language processing. It has received much attention not only in academia but also in industry. Data h...Show MoreMetadata
Abstract:
Sentiment analysis of online reviews is an important task in natural language processing. It has received much attention not only in academia but also in industry. Data have become an important source of competitive intelligence. Various pretraining models such as BERT and ERNIE have made great achievements in the task of natural language processing, but lack domain-specific knowledge. Knowledge graphs can enhance language representation. Furthermore, knowledge graphs have high entity / concept coverage and strong semantic expression ability. We propose a sentiment analysis knowledge graph (SAKG)-BERT model that combines sentiment analysis knowledge and the language representation model BERT. To improve the interpretability of the deep learning algorithm, we construct an SAKG in which triples are injected into sentences as domain knowledge. Our investigation reveals promising results in sentence completion and sentiment analysis tasks.
In this study, we propose a method of constructing a domain-specific sentiment analysis knowledge graph (SAKG) to analyze online reviews. Sentiment knowledge is integrate...
Published in: IEEE Access ( Volume: 9)
Funding Agency:
School of Information Management, Central China Normal University, Wuhan, China
Xiaoyan Yan received the master’s degree from Zhengzhou University, in 2009. She is currently pursuing the Ph.D. degree with the School of Information Management, Central China Normal University, China. Her research interest includes text classification, information retrieval, and data mining.
Xiaoyan Yan received the master’s degree from Zhengzhou University, in 2009. She is currently pursuing the Ph.D. degree with the School of Information Management, Central China Normal University, China. Her research interest includes text classification, information retrieval, and data mining.View more
National Engineering Research Center for E-Learning, Central China Normal University, Wuhan, China
Fanghong Jian received the Ph.D. degree from the National Engineering Research Center for E-learning, Central China Normal University, China, in 2020. Since 2016, he has been published several refereed papers in international conferences, such as SIGIR, ICTIR, and TREC. His research interest includes information retrieval, natural language processing, and deep learning applied to text data.
Fanghong Jian received the Ph.D. degree from the National Engineering Research Center for E-learning, Central China Normal University, China, in 2020. Since 2016, he has been published several refereed papers in international conferences, such as SIGIR, ICTIR, and TREC. His research interest includes information retrieval, natural language processing, and deep learning applied to text data.View more
National Engineering Research Center for E-Learning, Central China Normal University, Wuhan, China
Bo Sun is currently pursuing the Ph.D. degree with the National Engineering Research Center for E-learning, Central China Normal University, China. His research interest includes natural language processing, Q&A, and text classification.
Bo Sun is currently pursuing the Ph.D. degree with the National Engineering Research Center for E-learning, Central China Normal University, China. His research interest includes natural language processing, Q&A, and text classification.View more
Contents School of Information Management, Central China Normal University, Wuhan, China
Xiaoyan Yan received the master’s degree from Zhengzhou University, in 2009. She is currently pursuing the Ph.D. degree with the School of Information Management, Central China Normal University, China. Her research interest includes text classification, information retrieval, and data mining.
Xiaoyan Yan received the master’s degree from Zhengzhou University, in 2009. She is currently pursuing the Ph.D. degree with the School of Information Management, Central China Normal University, China. Her research interest includes text classification, information retrieval, and data mining.View more
National Engineering Research Center for E-Learning, Central China Normal University, Wuhan, China
Fanghong Jian received the Ph.D. degree from the National Engineering Research Center for E-learning, Central China Normal University, China, in 2020. Since 2016, he has been published several refereed papers in international conferences, such as SIGIR, ICTIR, and TREC. His research interest includes information retrieval, natural language processing, and deep learning applied to text data.
Fanghong Jian received the Ph.D. degree from the National Engineering Research Center for E-learning, Central China Normal University, China, in 2020. Since 2016, he has been published several refereed papers in international conferences, such as SIGIR, ICTIR, and TREC. His research interest includes information retrieval, natural language processing, and deep learning applied to text data.View more
National Engineering Research Center for E-Learning, Central China Normal University, Wuhan, China
Bo Sun is currently pursuing the Ph.D. degree with the National Engineering Research Center for E-learning, Central China Normal University, China. His research interest includes natural language processing, Q&A, and text classification.
Bo Sun is currently pursuing the Ph.D. degree with the National Engineering Research Center for E-learning, Central China Normal University, China. His research interest includes natural language processing, Q&A, and text classification.View more