Impact of Social Games in Aggregating Relationships in Social Capital through Online Social Media Network

Abstract

In recent days, social network sites connect people and help them maintain social ties through aggregating and accumulating social capital. This trait is important for organisation and individual success. The literature in the field indicates that there is a wide gap in automating the prediction of aggregation of social capital through online social games in social media networks. The analysis of the impact of social games in facilitating Social Capital (SC) is very vital. The existing mathematical and statistical modelling techniques fail to recognise the inherent and latent associations among the exploratory variables. Hence, this work proposes an ensemble machine learning model that learns the inherent features from the questionnaire collected from online gamers on three genres, namely media technology availability, multimedia communication channels and degree of social connectedness. The base learners explore the data domain in different ways to extract the features. The efficacy of the model's prediction is done by analysing the accuracy, F1 score, precision and recall. The results indicate that the model can effectively classify the instances, whether they positively or negatively contribute to the aggregation of SC. As a future extension of the research, the model can be made to learn more extensive attributes.