An attention-based CNN-LSTM model for subjectivity detection in opinion-mining
Neural Computing and Applications
Opinion-mining generally refers to analyzing opinions on various topics available in the form of text. It is an essential operation of natural language processing since it enables efficient decision-making and planning for users and businesses. Opinion-mining can be made more comfortable and more effective by initially performing subjectivity detection, i.e., identifying the text as subjective or objective. An opinion-mining model can better identify the opinions present in the remaining subjective statements by removing objective statements. With this reasoning, we present an efficient subjectivity detection model for improved accuracy in Opinion-mining. The model uses a strategic combination of convolutional neural network (CNN) and long short-term memory (LSTM). CNN and LSTM are state-of-the-art deep learning models that can efficiently process textual data and identify inherent connections and patterns with varying abstraction levels. The proposed work combines the strengths of both these models in an ensemble model. Effectiveness of the model is enhanced with the incorporation of an attention network. In the present task, the sentences are represented as word embeddings that include sentiment information and part-of-speech. The proposed model is applied on two movie review datasets, and its performance is evaluated compared with state-of-the-art methods. Various performance indexes have validated the superiority of the proposed model in the opinion-mining task.
Sagnika, Santwana; Mishra, Bhabani Shankar Prasad; and Meher, Saroj K., "An attention-based CNN-LSTM model for subjectivity detection in opinion-mining" (2021). Journal Articles. 1692.