Exploring the Ensemble of Classifiers for Sentimental Analysis
Ali Athar, Wasi Haider Butt, Muhammad Waseem Anwar, Muhammad Latif, Farooque Azam · 2017
Text classification is a well-known machine learning approach to simplify the domain-specific investigation. Therefore, it is commonly utilized in the field of sentimental analysis to achieve the particular business goals. Different ensemble approaches are frequently introduced to unify the desired classifiers for the improvement of sentimental classification. However, to the best of our knowledge, no study is available yet that investigate and summarize the leading ensemble approaches, classifiers, features, tools and datasets altogether in the domain of sentimental analysis. Therefore, in this paper, a Systematic Literature Review (SLR) is performed to identify 31 studies published during 2008--2016. Subsequently, 14 modern ensemble techniques, 26 leading classifiers, 15 benchmark datasets, 19 prominent features and 8 tools are presented in the context of sentimental analysis. This investigation certainly benefits the scholars and industrial experts of the domain while deciding the right choices according to the given requirements.