CogAware: Cognition-Aware framework for sentiment analysis with textual representations

Abstract

Sentiment analysis has become an important research area in artificial intelligence. Recently, the integration of sentiment analysis with cognitive neuroscience in natural language processing (NLP) tasks has attracted widespread attention. Cognitive signals and textual signals (i.e. word embeddings) both contain distinctive information for sentiment analysis tasks. However, most previous studies cannot effectively capture the specific features and cross-domain features while integrating cognitive signals acquired from brain activity and textual signals obtained from natural language processing (NLP). To address this issue, we propose CogAware, which learns to obtain a deep representation that combines purified specific features with cross-domain features from textual and cognitive signals. CogAware employs four private encoders to extract specific or cross-domain features from textual and cognitive signals alternately. It also employs feature reinforcement and orthogonality regularization to separate specific and cross-domain features from each modality. Moreover, a shared encoder and a modality discriminator are used to further capture cross-domain features from different modalities. Our designed architecture utilizes cognitive signals and word embeddings during model training, yet relies solely on word embeddings for model inference. Experiments on a public dataset show that CogAware achieves new state-of-the-art performance on the sentiment analysis task compared with other existing models. The source code of CogAware is available at: https://github.com/zhejiangzhuque/CogAware.