A framework for pre-processing of social media feeds based on integrated local knowledge base

作者：

Highlights：

• Noisy terms in social media posts must be semantically analysed to gain full insights.

• Better understanding and interpretation of social media feeds is critical for techniques building on them.

• Localized knowledge sources can fully capture social media noisy terms from a particular location.

• Resolving ambiguity in the use of slangs/ acronyms/abbreviation lead to improved accuracy.

摘要

•Noisy terms in social media posts must be semantically analysed to gain full insights.•Better understanding and interpretation of social media feeds is critical for techniques building on them.•Localized knowledge sources can fully capture social media noisy terms from a particular location.•Resolving ambiguity in the use of slangs/ acronyms/abbreviation lead to improved accuracy.

论文关键词：Social media analysis,Tweet analysis,Event detection,Machine learning,Big data analytics,Sentiments analysis

论文评审过程：Received 5 January 2020, Revised 25 May 2020, Accepted 22 June 2020, Available online 4 July 2020, Version of Record 4 July 2020.

论文官网地址：https://doi.org/10.1016/j.ipm.2020.102348