A Sentiment-Based Recommender System Framework for Social Media Big Data Using Open-Source Tech Stack Shini Renjith, Mable Biju, and Monica Merin Mathew Abstract The large volume of data getting generated on the internet has become an opportunity for data analysts to retrieve information and perform decision-making. However, the extraction of relevant information has turned out to be an extremely difficult task, especially when dealing with big data sources like social media. Intel- ligent approaches like recommendation systems came into existence to deal with such situations. These systems require the capability to deal with various big data sources like user-generated content—reviews, comments, ratings, likes, etc. This work proposes a four-stage recommender system architecture for big data processing using open-source technology stack. The key objective of our proposed architecture is to ensure an efficient and robust recommendation system with excellent efficiency. Keywords Big data · Recommendation system · Open-source · Natural language processing · Machine learning S. Renjith · M. Biju · M. M. Mathew Department of Computer Science and Engineering, Mar Baselios College of Engineering, Thiruvananthapuram, Kerala 695015, India e-mail: mablebj15@gmail.com M. M. Mathew e-mail: monica.m.mathew@gmail.com S. Renjith (B ) Department of Computer Applications, Cochin University of Science and Technology, Kochi, Kerala 682022, India e-mail: shinirenjith@gmail.com © Springer Nature Singapore Pte Ltd. 2021 V. K. Gunjan and J. M. Zurada (eds.), Proceedings of International Conference on Recent Trends in Machine Learning, IoT, Smart Cities and Applications, Advances in Intelligent Systems and Computing 1245, https://doi.org/10.1007/978-981-15-7234-0_36 407