AAAI 2013 Spring Symposium on Analyzing Microtext

Microtext are short snippets of text found in many modes of communication: microblogs (e.g., Twitter, Plurk), Short Message Streams (SMS), chat (e.g., instant messaging, Internet Relay Chat), and transcribed conversations (e.g., FBI hostage negotiations). Microtext often has the characteristics of informality, brevity, varied grammar, frequent misspellings (both accidental and purposeful), and usage of abbreviations, acronyms, and emoticons. With more conversational forms of microtext such as multiparticipant chat, there are also entangled conversation threads. These characteristics create many difficulties for analyzing and understanding microtext, often causing traditional NLP techniques to fail. Research on microtext is becoming increasingly necessary given the explosion of on-line microtext language. Yet, very few suitable tools have been developed for analyzing it. Also, there are few sufficiently-large publicly-available data sets (such as the Twitter corpus). Currently, most NLP tools are designed to deal with grammatical, properly spelled and punctuated language corpora. However, the reality is that a vast portion of online data does not conform to the canons of standard grammar and spelling. There is a growing need for specialized tools that tolerate noisy and fragmented microtext. Bringing together researchers from various fields to discuss microtext analysis will pave the way towards bringing the NLP methods, tools, and corpora in line with the current needs of the NLP community in academia, industry, and government.