Personality Prediction Based on Users' Tweets

The extensive use of social media has a tremendous impact on culture, business and politics in the world at large with potentially positive and negative effects. Personality traits are generally referred to as relatively stable patterns based on one's past experiences, upbringing, environment, all the opinions that one forms over time. It's closely bonded to how one feels, thinks and behaves, which has been associated with a wide range of important life outcomes and choices. Hence, in recent years, there has been a massive increase in the interest to develop models which use online data on human behaviour and preferences to automatically predict an individual's personality traits. In our research, to compute the accuracy of the personality predicted, it is first ensured that the dataset of stream of Tweets is almost equally divided into 16 different personality types, and be cleaned properly. We propose an advanced framework to identify and scrape tweets and retweets of Twitter user accounts and eventually applying Machine Learning algorithms for Personality Prediction.