The Topic & Sentiment Map of #royalmail Tweets interactive map analyzes Twitter messages to show where people in the UK are happy or disappointed in their postal services. By carrying out a sentiment analysis of Tweets containing the hashtag '#royalmail' the map is able to show where people are posting positive and negative messages about their mail delivery.
Emoji markers are used on the map to show the type of sentiment expressed towards the Royal Mail in Twitter messages. You can click on the individual markers to read the Tweet yourself. Negative messages towards the postal service outweigh the positive messages on the map. This may well be a common problem with this type of sentiment analysis - as I think it is more likely that people will take to Twitter to vent their dissatisfaction with the postal service than they are to write a favorable Tweet about their local postie.
However that doesn't mean that this type of sentiment analysis mapping of social media messages can't be extremely useful. It would appear to have great potential for identifying in near real-time emerging problems in a network, or at the very least identify locations where there is a large level of customer dissatisfaction.
If you are interested in how machine learning was used to determine the sentiment of #royalmail Tweets then you should read An AI-Powered Analysis of our Postal Service Through Tweets, which does a great job of explaining how a machine learning model was trained to analyze the sentiments expressed in Twitter messages towards the Royal Mail. It also includes a link to the GitHub repo of the project.
You can read about previous examples of setiment mapping based on Twitter messages in the post Sentiment Mapping. This post links to three previous mapping projects which attempted to map sentiments expressed in Twitter messages (unfortunately all three projects are now dead links).