WASSUP? LOL : Characterizing Out-of-Vocabulary Words in Twitter
This addresses the challenge of noisy social media text for natural language processing applications, though it is incremental as it builds on existing OOV classification work.
The paper tackled the problem of out-of-vocabulary words in Twitter language by studying their sociolinguistic properties and proposing a classification model to categorize them into at least six categories, achieving 81.26% accuracy with high precision and recall.
Language in social media is mostly driven by new words and spellings that are constantly entering the lexicon thereby polluting it and resulting in high deviation from the formal written version. The primary entities of such language are the out-of-vocabulary (OOV) words. In this paper, we study various sociolinguistic properties of the OOV words and propose a classification model to categorize them into at least six categories. We achieve 81.26% accuracy with high precision and recall. We observe that the content features are the most discriminative ones followed by lexical and context features.