Twitter Visualization and Sentiment Analysis Using Deep Learning

Abstract

Sentiment analysis on social media like Twitter has become a really importantand challenging task. Due to the characteristics of such data tweet length,spelling errors, abbreviations, and special characters the sentiment analysistask in such an environment requires a non-traditional approach. Moreover,social media sentiment analysis is a fundamental problem with many interesting applications. Most current social media sentiment classification methodsjudge the sentiment polarity primarily consistent with textual content and neglectother information on these platforms. In this paper, we propose a neural network model that also incorporates user behavioural information within a givendocument (tweet). We utilize the Convolutional Neural Network in our project. The system is evaluated on two datasets provided bythe SemEval-2016 Workshop. The proposed model outperforms current baseline models (including Naive Bayes and Support Vector Machines), which showsthat going beyond the content of a document (tweet) is useful in sentimentclassification, because it provides the classifier with a deep understanding of the task.