The goal of this term project is to propose and implement a model in measuring individual differences through the lens of language use in the social media.
Corpus
: FB, Twitter and Plurk
Lexicon
: Encode multi-dimensional information (e.g., lexical semantic, emotional and sociopsychological measures) of huge amount of linguistic units (words, phrases, construction, topic).
APP
: Game with a Purpose (GWAP) approach. With the allowance of users, the system access and analyze their language data on the fly, and visualize the profiling results. Interesting functions include visualizing who you are, and distinctions between friends, unknown people and celebrities.