Figure 8: Sentiment Distribution
All of the tweets from the data set were assigned a sentiment score ranging from -6 to +7, with -6 having the most negative sentiment, 0 having a neutral sentiment, and +7 having the most positive sentiment. 64% of the tweets had a neutral sentiment. 79% of the negative tweets scored ≤ -3 were related to a Paris-bound flight that was severely delayed. 8% of the positive tweets scored ≥ +3 were related to the #Askryanair sessions.
Note: This analysis was conducted using packages in R Studio which mapped the tweeted words against a list of positive and negative words. Then, the number of words mapped to “positive” were subtracted by the number of words mapped to “negative” and a net sentiment score was provided. However, these findings are limited as they do not consider the context of the entire string, such as a comparison between two different airlines, nor is it considering language usage such as sarcasm.