Twitter data analysis for unemployment crisis

Twitter is the most popular microblogging and social media services used by millions of Web users worldwide to read and write short messages about the topic related to their current status. Such social media sites usually has lots of irrelevant, unwanted and also huge information to carry out the study of human behaviour, new trends and so on. Highly influential, popular persons and public users tweet their status that are retweeted or replied by set of the audiences those view the tweets. By applying Sentiment analysis on the tweets made by the popular users and the audiences, we can discover whether the audiences are in favour to the views expressed. This work focuses on mining the information posted on twitter site about unemployment using hash tags. The proposed system is implemented using R language which makes it easy to mine data from Twitter with its support for twitter mining through wide range of APIs available. Mined twitter data is written into CSV files as the input dataset. Sentiment analysis is performed on the input dataset that initially performs data cleaning by removing the stop words, followed by classifying the tweets as positive and negative by matching with the positive-word and negative-word text dictionary to assigns the scores for every tweet. Next, Text mining is performed on the related hash-tags to generate the word cloud. Finally the analysis of the unemployment rate is performed on the individual hash tags and the merged hash tags based on the scores recorded for every tweets during the Sentiment analysis stage.