Convolutional Neural Networks (CNN) Model for Mobile Brand Sentiment Analysis

Nowadays, the demand of sentiment analysis is increasing due to the requirement of analyzing and structuring hidden information from unstructured data. The sentiment on public views such as on products, services, and issues can be collected from social media platforms in text form. Convolutional neural network (CNN) is a class of deep neural networks method which can enhance the learning procedures by utilizing the layers with convolving filters that are updating to local features CNN models. This will achieve excellent results for Natural Language Processing (NLP) tasks especially as it can better reveal and obtain the internal semantic representation of text information. Due to this reason, this study attempts to apply this technique in mobile brand reviews sentiment analysis. There are four phases involved in this study which is knowledge acquisition and data preparation; CNN model development and enhancement; and model performance evaluation phases. As a result, the CNN model has been proposed by enhancing the model strategicmapping for optimal solution in producing high accuracy model. In future work, this study plans to explore other parameters such as in data pre-processing and network training to enhance the performance of CNN model. The proposed method can be used as sentiment analysis mechanism in many areas such as in review analytic, search query retrieval and sentence modelling.