Social media research: The application of supervised machine learning in organizational communication research.
作者：
Highlights：
• Supervised Machine Learning (SML) is suitable for coding social media content.
• Linear Support Vector Machine and Naïve Bayes classifiers can be trained using 4000 training tweets.
• SML enables researchers to escalate the scope of their research without compromising data size or depth.
• Linear Support Vector Machine and Naïve Bayes outperform the logistic regression classifier.
• Classifiers perform better based on stratified random samples compared to random samples when training samples are small.
摘要
•Supervised Machine Learning (SML) is suitable for coding social media content.•Linear Support Vector Machine and Naïve Bayes classifiers can be trained using 4000 training tweets.•SML enables researchers to escalate the scope of their research without compromising data size or depth.•Linear Support Vector Machine and Naïve Bayes outperform the logistic regression classifier.•Classifiers perform better based on stratified random samples compared to random samples when training samples are small.
论文关键词：Twitter,Supervised machine learning,Communication research,Content analysis
论文评审过程：Received 25 November 2015, Revised 10 May 2016, Accepted 12 May 2016, Available online 20 May 2016, Version of Record 20 May 2016.
论文官网地址：https://doi.org/10.1016/j.chb.2016.05.028
