← Back to VOLUME 13, ISSUE 10, OCTOBER 2026
This work is licensed under a Creative Commons Attribution 4.0 International License.
Big Data Based Social Media Sentiment Analysis and User Behavior Mining
Sheeba S, Dileepa D, Gagan R, Varun Gowda G P, Vikram R T
👁 5 views📥 1 download
Abstract: Social media platforms generate a continuous stream of user-generated content in the form of posts, comments, reactions, reviews, and other interactions. Although this information can provide useful insights into public opinion and user behavior, its large volume, high generation rate, and unstructured nature make conventional processing approaches difficult to apply. This paper presents a Big Data-based framework for analyzing social media content by combining distributed data processing, Natural Language Processing (NLP), and machine learning techniques. Apache Hadoop and Apache Spark are used to support large-scale data storage and processing, while NLP techniques are applied to prepare the collected textual data for analysis. User behavior is studied using parameters such as posting frequency, interaction levels, activity periods, and engagement patterns. For sentiment classification, the textual data is represented using Term Frequency-Inverse Document Frequency (TF-IDF), followed by classification using the Multinomial Naive Bayes algorithm. The resulting data is presented through charts and analytical reports to make the identified trends easier to interpret. The system classifies social media content into positive, negative, and neutral categories and provides behavioral information that can be used for further analysis.
Keywords: user behavior mining, sentiment analysis, social media, computer big data analysis, user experience.
Keywords: user behavior mining, sentiment analysis, social media, computer big data analysis, user experience.
How to Cite:
[1] Sheeba S, Dileepa D, Gagan R, Varun Gowda G P, Vikram R T, “Big Data Based Social Media Sentiment Analysis and User Behavior Mining,” International Advanced Research Journal in Science, Engineering and Technology (IARJSET), DOI: 10.17148/IARJSET.2026.131051
