@inproceedings{cc34fcaef7604c118103668898da90a1,
title = "Twitter vs. printed English: An information-theoretic comparison",
abstract = "The popular social networking and microblogging service Twitter contains language that is very different from what is considered proper. This paper quantifies those linguistic differences between printed English and Tweetspeak using information-theoretic concepts. Letter-based n-gram entropies are calculated and compared to analagous data from two corpora of printed English to demonstrate that 1) Twitter's entropy is overall higher than that of printed English, and 2) individual users' entropies are on average higher the less conventional their language use is. The implications for digitally-mediated communication in general are also discussed.",
keywords = "Twitter, computer mediated communication, information entropy, information theory, redundancy",
author = "Emma Glennon and Lalitha Sankar and Poor, {H. Vincent}",
year = "2012",
doi = "10.1109/ICASSP.2012.6288563",
language = "English (US)",
isbn = "9781467300469",
series = "ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings",
pages = "3069--3072",
booktitle = "2012 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2012 - Proceedings",
note = "2012 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2012 ; Conference date: 25-03-2012 Through 30-03-2012",
}