Differentiating users by language and location estimation in sentiment analisys of informal text during major public events
作者：
Highlights：
• Novel method to assess social media users engagement during public global events.
• Method considers three dimensions: location, time and sentiment analysis.
• Unsupervised SA strategy based on semantic dependencies with propagation.
• Novel language-agnostic network-oriented location approach without assumptions.
• Coherent with disposition theory of individual users to players and group belonging.
摘要
•Novel method to assess social media users engagement during public global events.•Method considers three dimensions: location, time and sentiment analysis.•Unsupervised SA strategy based on semantic dependencies with propagation.•Novel language-agnostic network-oriented location approach without assumptions.•Coherent with disposition theory of individual users to players and group belonging.
论文关键词：Sentiment analysis,Opinion mining,Spatio-temporal analysis,User location,nlp,Artificial intelligence
论文评审过程：Received 17 April 2018, Revised 3 September 2018, Accepted 4 September 2018, Available online 19 September 2018, Version of Record 26 September 2018.
论文官网地址：https://doi.org/10.1016/j.eswa.2018.09.007
