REGRESSION METHODS FOR SOCIAL MEDIA DATA ANALYSIS

Abstract

In the early 2000s, the more traditional modes of communication via mobile devices were voice calls, emails, and short message services (SMS). Nowadays, communication through mobile applications such as WhatsApp, Facebook, Twitter, Instagram, etc. About Facebook the leading social network with monthly active users of about 2.85 billion people. With this number of users, a large amount of data is generated. Exploring this data provides an insight into the users’ activities which can aid in tackling security challenges and business planning, among other benefits. This study presents a neighborhood component analysis (NCA) and relief-based weight generation methods for a regression task on Facebook data. The features are calculated using the weight generated and four widely used activation functions. The features are then fed to four regression models for prediction. The proposed model is used to predict nine different attributes of the FB dataset whose values are continuous. RMSE, R-squared, MSE, MAE, and training time were calculated and used as evaluation metrics for all nine cases. The average R-square value of the Relief and NCA-based methods were calculated as 0.9689 and 0.9667, respectively. The results indicated that our proposed methods are very efficient and successful for regression tasks on Facebook data.