Published Paper Details:

Twitter, as a social network, is a very common medium to share thoughts and communicate with other people in the online world. Tweets collected in aggregate will represent public opinion about events. This paper gives an optimistic or negative feeling to Twitter posts using a well-known machine learning approach for text categorization. In addition, we use manually labeled (positive/negative) tweets to create a qualified system to perform a task. The task is looking for a correlation between twitter sentiment and events that have occurred. The qualified model is built on the classification system of Naive Bayes and Support Vector Machine(SVM). We also used external lexicons to detect arbitrary or objective tweets, added Unigram and Bigram features, and used TF-IDF (Term Frequency-Inverse Document Frequency) to filter out the features. We used the Twitter Streaming API and some of the official hash tags for mine, filter and process tweets to examine the public's view of unusual incidents. The same method can be used as a basis for forecasting future events. In the form of the twitter sentiment analysis, the most basic sentiment analysis quantifies the mood of a tweet or message by counting the number of positive and negative terms.