Natural Language Processing (NLP) is used to analyze and classify personality types. Predicting the personality of users is of relevance in marketing, politics, psychology, and health care. A study by Margaret Mitchell in 2015 shows a correlation between tweets and schizophrenia.
Plank and Hovy found that INTROVERT–EXTROVERT (I–E) and THINKING–FEELING (T–F), can be predicted from social media data with high reliability, while others are hard to predict. They also believe that the algorithm will improve with more data.
The code is available at: https://bitbucket.org/bplank/wassa2015/src/master/
Personality
Traits on Twitter —or— How to Get 1,500 Personality Tests in a Week paper by
Barbara Plank and Dirk Hovy.