The IBM Watson Personality Insights service uses linguistic analytics to extract a spectrum of cognitive and social characteristics from the text data that a person generates through blogs, tweets, forum posts, and more.
We need a minimum of 3500 words and ideally 6000 words or more to compute statistically significant results. See the science behind the service.
Ideally, the text should contain words we use in every day life relating to personal experiences, thoughts and responses. See usage guidance for details.