Multi-sentiment Modeling with Scalable Systematic Labeled Data Generation via Word2Vec Clustering

.
Abstract:
Social networks are now a primary source for news and opinions on topics ranging from sports to politics. Analyzing opinions with an associated sentiment is crucial to the success of any campaign (product, marketing, or political). However, there are two significant challenges that need to be overcome. First, social networks produce large volumes of data at high velocities. Using traditional (semi-) manual methods to gather training data is, therefore, impractical and expensive. Second, humans express more than two emotions, therefore, the typical binary good/bad or positive/negative classifiers are no longer sufficient to address the complex needs of the social marketing domain. This paper introduces a hugely scalable approach to gathering training data by using emojis as proxy for user sentiments. This paper also introduces a systematic Word2Vec based clustering method to generate emoji clusters that arguably represent different human emotions (multi-sentiment). Finally, this paper also introduces a threshold-based formulation to predicting one or two class labels (multi-label) for a given document. Our scalable multi-sentiment multi-label model produces a cross-validation accuracy of 71.55% (± 0.22%). To compare against other models in the literature, we also trained a binary (positive vs. negative) classifier. It produces a cross-validation accuracy of 84.95% (± 0.17%), which is arguably better than several results reported in literature thus far.
.
https://ieeexplore.ieee.org/document/7836770