Mining language variation using word using and collocation characteristics
作者:
Highlights:
• Two metrics are proposed for extracting language variation characteristics.
• Two textual features are derived by employing the two proposed textual metrics.
• Using our features, language variation cues can be visualized.
• Our method can display language changes when semantics and syntax are unknown.
• Both entropy-based analysis and simulations prove the feasibility of our algorithm.
摘要
•Two metrics are proposed for extracting language variation characteristics.•Two textual features are derived by employing the two proposed textual metrics.•Using our features, language variation cues can be visualized.•Our method can display language changes when semantics and syntax are unknown.•Both entropy-based analysis and simulations prove the feasibility of our algorithm.
论文关键词:Language variation,Text mining,Frequency Rank Ratio,Overall Intimacy
论文评审过程:Available online 1 June 2014.
论文官网地址:https://doi.org/10.1016/j.eswa.2014.05.018