Abstract
Deep learning algorithms have achieved remarkable results in the natural language processing(NLP) and computer vision. Hence, a trend still going on to use these algorithms, such as convolution and recurrent neural networks, for text analytic task to extract useful information. Features extraction is one of the important reasons behind the success of these networks. Moreover passing features from one layer to another layer within the network and one network to another network have done. However multilevel and multitype features fusion remains unexplored in sentiment analysis. So, in this paper, we use three datasets to display the advantages of extracting and fusing multilevel as well as multitype features from different neural networks. Multilevel features are from different layers of the same network, and multitype features are from different network architectures. Experiment results demonstrate that the proposed model based on multilevel and multitype weighted features fusion outperforms than many exiting works with an accuracy of 80.2%, 48.2%, and 87.0% on MR, SST1, and SST2 datasets respectively.
Highlights
The enormous and rapid growth of the social network, smart gadgets, and the internet brings together billions of users to generate short texts on the internet such as public opinion on services, products, movies, and blogs
Identifying and classifying proper semantic orientation of text reviews written by authors on the internet is essential to research which solves customers as well as company’s various practical value problems, such as what product a customer like or dislike? whether the product is doing good in the market or not? Sentiment analysis of short text remains a challenging one because short text usually contains limited semantic and contextual information, which limits the accuracy of the analysis
CNN-GRU-Multitype fusion: A model with pretrained word-vectors from GloVe, to perform multitype feature fusion based on CNN and GRU
Summary
The enormous and rapid growth of the social network, smart gadgets, and the internet brings together billions of users to generate short texts on the internet such as public opinion on services, products, movies, and blogs. Chen and Hao [25] and Vu et al [26] both utilized two distinct neural networks together and combine CNN and RNN for relation classification All these model achieved better results compared to existing models. Both CNN and RNN received sentiment text as an input and learns different features according to network architecture. We give word embedding again as an input to RNN and learn temporal features in sentiment text We merge these multiple type features at merge layer to get combined multilevel and multitype features fusion. We separately learn CNN and RNN type features by using word embedding as an input for both CNN and RNN and merge both types of features to get multitype features fusion, Instead of passing CNN features to RNN in sequence way as done in exiting works, perform sentiment analysis over the union of features map.
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
