A framework for event classification in tweets based on hybrid semantic enrichment

作者：

Highlights：

• A hybrid semantic enrichment framework to classify event-related tweets

• Combines semantic enrichment, external documents and named-entity recognition

• A semantic feature pruning algorithm and feature selection to deal with huge volume of features

• Assessment of each framework component using a broad experimental setup

• Superior results compared to a textual baseline and a word embeddings baseline

摘要

•A hybrid semantic enrichment framework to classify event-related tweets•Combines semantic enrichment, external documents and named-entity recognition•A semantic feature pruning algorithm and feature selection to deal with huge volume of features•Assessment of each framework component using a broad experimental setup•Superior results compared to a textual baseline and a word embeddings baseline

论文关键词：Event classification,Semantic web,DBPedia,Twitter,Discriminative features

论文评审过程：Received 17 January 2018, Revised 27 September 2018, Accepted 14 October 2018, Available online 15 October 2018, Version of Record 23 October 2018.

论文官网地址：https://doi.org/10.1016/j.eswa.2018.10.028