Abstract:

The concept of sentiment analysis of twitter data and semantic analysis with the augmentation of machine learning methodologies has become a hot topic in recent years. Many strategies have been presented in the area of sentiment analysis in the last few years to evaluate social media data and produce a graphical presentation towards a certain business. Sentiment analysis shows you how people feel about a product or brand when penning a social media message about it. This is crucial information if you know that one persons opinion of a firm or its products might impact the opinions of others. Like many other online data mining systems, sentiment analysis platforms are based on Support Vector Machine algorithms. This algorithm, in this situation, recognises specific terms as positive or negative, indicating whether or not your brand is being adored or floored. So, in this paper, we first pre-processed the dataset, then extracted the adjectives from the dataset that have some meaning (feature vector), then selected the feature vector list, and finally applied machine learning based classification algorithms such as Nave Bays, Maximum entropy, and SVM, as well as the Semantic Orientation based WordNet to extract synonyms and similarity for the content feature. Finally, we evaluated the classifiers performance in terms of recall, precision, and accuracy.

Keywords: