Deep Learning Framework for Classification of Emoji Based Sentiments

Recent patterns of human sentiments are highly influenced by emoji based sentiments (EBS). Social media users are widely using emoji based sentiments (EBS) in between text messages, tweets and posts. Although tiny pictures of emoji contains sufficient information to be considered for construction of classification model; but due to the wide range of dissimilar, heterogynous and complex patterns of emoji with similar meanings (SM) have become one of the significant research areas of machine vision. This paper proposes an approach to provide meticulous assistance to social media application (SMA) users to classify the EBS sentiments. Proposed methodology consists upon three layers where first layer deals with data cleaning and feature selection techniques to detect dissimilar emoji patterns (DEP) with similar meanings (SM). In first sub step we input set of emoji, in second sub step every emoji has to qualify user defined threshold, in third sub step algorithm detects every emoji by considering as objects and in fourth step emoji images are cropped, after data cleaning these tiny images are saved as emoji images. In second step we build classification model by using convolutional neural networks (CNN) to explore hidden knowledge of emoji datasets. In third step we present results visualization by using confusion matrix and other estimations. This paper contributes (1) data cleaning method to detect EBS; (2) highest classification accuracy for emoji classification measured as 97.63%.