AUTHOR=Tariq Muhammad Usman , Babar Muhammad , Poulin Marc , Khattak Akmal Saeed , Alshehri Mohammad Dahman , Kaleem Sarah TITLE=Human Behavior Analysis Using Intelligent Big Data Analytics JOURNAL=Frontiers in Psychology VOLUME=Volume 12 - 2021 YEAR=2021 URL=https://www.frontiersin.org/journals/psychology/articles/10.3389/fpsyg.2021.686610 DOI=10.3389/fpsyg.2021.686610 ISSN=1664-1078 ABSTRACT=Intelligent Big Data analysis is an evolving method used in the age of big data science and artificial intelligence (AI). Analysis of organized data has been very successful, but analyzing human behavior using social media data has been challenging. Social media data comprises a vast and unstructured format that includes the “likes”, comments, tweets, shares, views, and so forth. Data analytics of social media data became a challenging task for companies like Daily Motion that have billions of daily users, and vast numbers of comments, likes, and views. Significant amount of data is created continuously and at great speed. There is a great interest for organizations to store, sort, process, and analysis the data for improving decision-making process. The literature has shown to lack techniques to address challenges to analyze large amounts of social media data. This article proposes a novel architecture using a Big Data analytics mechanism to efficiently and intelligently process the huge datasets resulting from social media data. The proposed architecture is founded on a three-layer architecture. The paper’s main objective is to demonstrate how the proposed framework can show performance improvements for the discussed problem. The framework uses Apache Spark parallel and distributed framework technologies with selected storage and processing mechanisms. The framework’s potential is illustrated by applying it to social media data generated from Daily-Motion. The implementation of the framework utilized the Daily-Motion API (Application Programming Interface), allowing it to incorporate functions suitable to fetch and view information. The API key was generated to fetch information of public channel data in the form of text file, and HIVE storage machinist was utilized with Apache Spark for efficient data processing. The implementation showed the potential effectiveness of the proposed architecture is also highlighted. Results showed the framework can handle the data of the size 13 GB, with improved processing time of 15%.