A Comprehensive Comparative Evaluation of Machine Learning Algorithms on Facebook Comment Dataset

Data mining is an emerging technique with its application in various areas such as health care, education, travel, social media, and banking. The data can be either labeled or unlabeled. When it comes to social media, the various platforms generate an infinite amount of data. This data can be of immense importance as a lot of hidden information can be discovered after data mining. In this paper, machine-learning algorithms such as Decision Trees, SVM, and Linear Regression and their variants are applied on the Facebook comment dataset, obtained from the UCI machine learning repository. The dataset has 40,949 instances and 54 attributes. The goal is to predict the number of comments a Facebook post will get based on various conditions. The results indicate that the Fine Gaussian SVM variation of SVM yielded the highest prediction accuracy. The evaluation was done on different parameters such as average testing accuracy (%), Root Mean Square Error (RMSE), R- Squared, Mean Square Error (MSE), Mean Absolute Error (MAE), prediction speed (Obs/sec), and training time (Machine cycle). It is concluded that SVM is an ideal choice to solve prediction problems associated with social media data.