According to the Wikipedia, sentiment analysis is a process of computationally identifying and categorizing opinions expressed in a piece of text, especially in order to determine whether the writer’s
attitude towards a particular topic, product, incident etc., is positive, negative or neutral.
In our research we have planned to use sentiment analysis to identify the positive, negative and
neutral aspects of Twitter data regarding Zika virus (ZIKV). We planned to use a crawler system to
get data from Twitter. In case of sentiment analysis, planned to use three main methods to reach the
expected result. Those will be SentiWordNet, SentiStrength and CoreNLP. These three procedures
will divide Tweets into Positive, Negative and Neutral criteria.
According to those criteria, it is possible to compare the results with real Zika virus (ZIKV) data.
Provided, our methods are accurate, those compared results should be accurate with data of real world
incident.
The research questions motivating our project can be described as follows,
• How to retrieve more accurate results from three sentiment classifiers?
• Accuracy of the method which we are using to retrieve the data?
• How to retrieve a final result from those three classifier results?
• Whether the Twitter data results reflect the results of the real world?