Sentiment Analysis of Twitter Political Data using GRU Neural Network

  • Seenaiah Pedipina, Sankar S and R Dhanalakshmi


The arrival of smart phone, usage of social media and huge development in mobile communication technology have together drastically changed the way to express the feeling, thoughts etc. through social media. People have been using freedom of expression in micro blogging services like Facebook, Twitter etc. with no constraints. Thus, these texts are the sentiments of people can be used to characterize their opinion or mood related to multiple domains like political, entertainment, products etc. In these days political party representatives also started using Twitter, Facebook and blogs to share their party decisions or policies to the public and observing their response over the decisions. Hence, this paper presents an approach using Artificial Neural Network with GRU for sentiment prediction of imbalanced tweets data belongs to political domain. First, a module is developed which collects the reviews or text posts of people. Second, preprocessing or cleansing module is used to remove special symbols, URLs, Junk text, stop words, and tokenize the sentences and to perform the stemming process. Word2vec model is used to perform the process of word embedding to convert the text data into numerical format to pass to Neural Network. Finally Artificial Neural Network with GRU is proposed to predict the sentiments of cleansed tweets. The proposed model has collected 4500 tweets to train and predict the sentiments. After thorough analysis and with the comparison of different models, proposed model has outperformed the other techniques. Experimental analysis implies the effectiveness of the proposed model. This system can be used to understand the winning chances of political party and to understand the response of the people on particular political decision during elections campaign.

How to Cite
Seenaiah Pedipina, Sankar S and R Dhanalakshmi. (2020). Sentiment Analysis of Twitter Political Data using GRU Neural Network. International Journal of Advanced Science and Technology, 29(06), 5307 - 5320. Retrieved from