Social Media Sources for Personality Profiling

Social media provide a rich source of author-identified text that can be used for personality profiling. However, differences in length and number of entries, syntax, abbreviations, spelling and grammar errors, and topics can affect type and difficulty of preprocessing to extract appropriate text, accuracy of training, time period sampling for training texts, and rate of degradation of accuracy over time. Biases introduced by the topic areas of the social media, author self-selection, and current events affect different social media to varying extents and can bias both the demographics and possibly the personality types of users.