Sentiment analysis system adaptation for multilingual processing: The case of tweets
作者：
Highlights：
• We study different strategies to classify sentiment from tweets, using supervised learning with hybrid features.
• We experiment with English and Spanish data and compare against benchmark competitions.
• We employ machine-translated data from other languages for training.
• We show that the use of multilingual data improves the sentiment classification accuracy.
摘要
•We study different strategies to classify sentiment from tweets, using supervised learning with hybrid features.•We experiment with English and Spanish data and compare against benchmark competitions.•We employ machine-translated data from other languages for training.•We show that the use of multilingual data improves the sentiment classification accuracy.
论文关键词：Subjectivity analysis,Sentiment analysis,Multilingual resources,Social media mining,Chat analysis
论文评审过程：Received 6 December 2013, Revised 1 October 2014, Accepted 8 October 2014, Available online 3 December 2014, Version of Record 6 June 2015.
论文官网地址：https://doi.org/10.1016/j.ipm.2014.10.004
