Global Awareness Landscape for Ailments—A Twitter Based Microscopic View Into Thought Processes of People

In this day and age, people face a lot of stress due to the fast pace of life. Due to this, people in today's digital age, suffer from a plethora of ailments. It is universally accepted that a greater awareness of ailments and their corresponding symptoms leads to an increased lifespan and better quality of life. Early detection and screening can help doctors nip diseases in their natal stages. However, not everyone is aware of them, which makes it a global issue. The study of the degree of disease awareness amongst people belonging to different nations and continents is a matter of great interest. One method that is suitable for this purpose is using clinical data. But, this data is not readily available. However, today a plethora of platforms are available to people to share their thoughts and experiences. People post about many of the important events in their lives on social media. Their posts offer a microscopic view into their lives and thought processes. Based on this intuition, twitter data pertaining to various chronic and acute diseases has been collected. Tweets for 30 deadly ailments have been collected over a period of 3 months amounting to a total of 19 million. A feature extraction approach is proposed which is used to identify the disease awareness levels across different nations. Deriving the global awareness landscape for ailments can help to identify regions which are well aware and also those that need to get aware. Clustering has been used for this purpose.