Abstract
Cross-domain sentiment classification could be attributed to two steps. The first step is used to extract the text representation, and the other is to reduce domain discrepancy. Existing methods mostly focus on learning the domain-invariant information, rarely consider using the domain-specific semantic information, which could help cross-domain sentiment classification; traditional adversarial-based models merely focus on aligning the global distribution ignore maximizing the class-specific decision boundaries. To solve these problems, we propose a context-aware semantic adaptation (CASA) network for cross-domain implicit sentiment classification (ISC). CASA can provide more semantic relationships and an accurate understanding of the emotion-changing process for ISC tasks lacking explicit emotion words. (1) To obtain inter- and intrasentence semantic associations, our model builds a context-aware heterogeneous graph (CAHG), which can aggregate the intrasentence dependency information and the intersentence node interaction information, followed by an attention mechanism that remains high-level domain-specific features. (2) Moreover, we conduct a new multigrain discriminator (MGD) to effectively reduce the interdomain distribution discrepancy and improve intradomain class discrimination. Experimental results demonstrate the effectiveness of different modules compared with existing models on the Chinese implicit emotion dataset and four public explicit datasets.
Highlights
Cross-domain sentiment classification could be attributed to two steps
We provide a visualization to demonstrate that context-aware heterogeneous graph (CAHG) can capture domain-specific information, and multigrain discriminator (MGD) can make features near decision boundaries more distinguishable
We propose MGD, which consists of a domain discriminator T and an emotional polarity discriminator D
Summary
Cross-domain sentiment classification could be attributed to two steps. The first step is used to extract the text representation, and the other is to reduce domain discrepancy. Existing methods mostly focus on learning the domain-invariant information, rarely consider using the domain-specific semantic information, which could help cross-domain sentiment classification; traditional adversarialbased models merely focus on aligning the global distribution ignore maximizing the class-specific decision boundaries. Sentiment analysis is considered one of the fundamental problems in natural language processing (NLP), and with social media developing rapidly, it is widely applied in real scenarios such as comment analysis, food safety monitoring, and public opinion mining Such tasks are usually defined as identifying the emotional polarity (e.g., positive, negative, or neutral) of a given text, sentence, or aspect. People use Example 2 (e.g., metaphor, sarcasm) In this sentence, no explicit emotional words are used and the individual’s emotional tendency is embedded in the semantic meaning of the text. Relevant models on Scientific Reports | (2021) 11:22038
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have