LADA: A label-aware framework for cross-domain sentiment classification.

Abstract

Existing domain adaptation approaches that address the cross-domain sentiment analysis task can be concluded into two main lines: (i) aligning the distributions across different domains using various distance metrics. (ii) leveraging the generative-adversarial mechanism. Both methods aim to generate domain-invariant features. However, a shared challenge is evident: solely minimizing the distance of features X between the source and target domains results in a deficiency in establishing the relationship between features and labels. Moreover, the generative-adversarial approach is constrained by the inherent drawback of the generative adversarial mechanism, where the generator may generate irrelevant features as long as it can deceive the discriminator. In response to the aforementioned challenges, we introduce a Label-Aware Domain Adaptation (LADA) framework. LADA utilizes the joint probability distribution to preserve the relationship between features and labels. LADA achieves domain-invariant feature generation with label information by aligning the joint feature distributions of the source and target domains. Comprehensive experiments validate the cross-domain effectiveness of LADA, demonstrating state-of-the-art performance in the benchmark tests of sentiment analysis.