What kind of #conversation is Twitter? Mining #psycholinguistic cues for emergency coordination

作者：

Highlights：

• Information filtering model to reduce Twitter traffic for disaster coordination.

• Modeling of coordination via conversation using pyscholinguistic theories.

• Domain-independent linguistic cues distinguish likely conversation up to ROC = 0.84.

• Higher information density in positively classified conversational messages.

• Proof of same human behavior in face-to-face and online (mediated) communication.

摘要

•Information filtering model to reduce Twitter traffic for disaster coordination.•Modeling of coordination via conversation using pyscholinguistic theories.•Domain-independent linguistic cues distinguish likely conversation up to ROC = 0.84.•Higher information density in positively classified conversational messages.•Proof of same human behavior in face-to-face and online (mediated) communication.

论文关键词：Coordinated behavior,Conversation analysis,Information filtering,Disaster response,Twitter

论文评审过程：Available online 21 June 2013.

论文官网地址：https://doi.org/10.1016/j.chb.2013.05.007