Exploring Influential Users on Social Media Using Artificial Neural Network Techniques in Python for Enhancing Online Marketing Performance
Subject Areas : Futurologyhossein emamirad 1 , Abas Asadi 2
1 - M.A student, Department of Information Technology, Science and Research Branch, Islamic Azad University, Tehran, Iran
2 - استادیار، گروه مدیریت بازاریابی، واحد ورامین- پیشوا، دانشگاه آزاد اسلامی، ورامین، ایران(نویسنده مسئول)
Keywords: social networks, influential users, deep learning, internet marketing, Python,
Abstract :
In recent years, with the advent of social media, the discussion of analyzing user behavior based on their data has gained more attention than ever. During these years, organizations and large companies are interested in investing in data to better understand their customers. One of the crucial topics in the field of data science is the identification of influential users. These users can increase product and service purchases and reduce advertising and customer acquisition costs by exerting more influence on other users. The aim of this issue is to improve advertising and marketing performance. To identify these users, Twitter data has been used, and, according to the crisp model, data is first collected, then preprocessed, and finally modeled and evaluated. Deep learning algorithms have been used for modeling, and in the evaluation phase, this model has been compared to other machine learning models, including Bayesian networks, random forests, and support vector machines. Using data science evaluation methods, including sensitivity, specificity, accuracy, and F-measure, the proposed model has outperformed traditional models. Therefore, the proposed method is expected to have better performance.
