Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{195393,
        author = {Mahadevi Somanth Namose},
        title = {Leveraging Social Big Data and Machine Learning for Advanced Predictive Analytics},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {11},
        pages = {2436-2443},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=195393},
        abstract = {Instability in key socioeconomic indicators can significantly impact global development. This thesis introduces a suite of novel big data analytics algorithms designed to process unstructured web data streams, enabling the automatic inference of events, knowledge graphs, and predictive models. These methods facilitate improved understanding, characterization, and anticipation of socioeconomic indicator volatility. Four principal contributions are presented. First, novel models are proposed for extracting events and learning their spatio-temporal features from large volumes of unstructured news streams. Two types of event models are explored: one based on event triggers and another probabilistic model that identifies meta-events by extracting named entities from text streams. The second contribution addresses the extraction of knowledge graphs from time-sensitive data such as news and real-time events. Event graphs provide a concise representation of event chronologies relevant to specific news queries by characterizing their interconnections through event-phenomenon graphs, while spatio-temporal article graphs capture inherent relationships among news stories. The results of predictive analysis using these approaches are also presented.},
        keywords = {Big data, Machine Learning},
        month = {April},
        }