RecogNet-LSTM plus CNN: a hybrid network with attention mechanism for aspect categorization and sentiment classification

Sentiment analysis for user reviews has received substantial heed in recent years. There are many deep learning models for natural language processing (NLP) applications. Long-short term memory (LSTM) and Convolutional neural network (CNN) based models efficiently enhance sentiment accuracy. Aspect-level sentiment analysis involves aspect extraction, aspect categorization, and polarity classification. The aspect sentiments in the dataset are classified as positive, negative, and neutral, depending on the polarity score associated with the aspect emotions. Existing neural architectures combining LSTM and CNN employ only the implicit information from the dataset for sentiment classification. Alternatively, this paper highlights the integration of explicit knowledge from the external database (RecogNet) with the implicit information of the LSTM model to improvise the sentiment accuracy. Incorporating sentic and semantic clues from the RecogNet knowledge base to the LSTM increases aspect extraction and categorization efficiency. Furthermore, we implemented CNN with target and position attention mechanisms over the RecogNet-LSTM layer to further enhance the classification accuracy. Finally, the model evaluations are performed using five online datasets related to the restaurants, laptops, and locations. Among LSTM based hybrid models, our RecogNet-LSTM+CNN model with attention mechanism showed superior performance in aspect categorization and opinion classification.