Loading article...
Loading article...
Stream/Area:
-
Subject:
-
Paper ID:
IJSREM63498
Volume:
10 |
5 |
May 2026
Pages:
1-5
Publication Frequency:
Monthly (12 issues per year)
License:International Journal of Scientific Research in Engineering and Management follows the Creative Commons Attribution 4.0 (CC BY 4.0) License, allowing free use and distribution with proper attribution.
Master Of Computer Applications
Bapuji Institute of Engineering And Technologies
Master Of Computer Applications
Bapuji Institute of Engineering And Technologies.
The exponential proliferation of social media podia has essentially transformed the landscape of digital communication, generating a chaotic and continuous stream of unstructured data that imitates the collective consciousness of the global population. This project, titled "R&D - Large Scale Social Media Sentiment and Trend Analysis," proposes the research, design, and development of a high-performance computing framework capable of ingesting, processing, and analysing massive sources in near real-time. Content ranging from textual tweets and status updates to multimedia captions and comments reaches petabyte scales, proven insufficient This research covers developing Deep Learning architectures and distributed computing ecosystems that would address the gap between raw big data and actionable intelligence. The core objective of this research is By using the state-of-the-art models based on Transformers - latest BERT and RoBERT - fine-tuned on domain-specific corpora, deciphering complex linguistic nuances-sarcasm, irony, and local dialects-can, in large parts, be overstepped. Moreover, the project applies a trend detection engine that uses temporal analysis and graph theory for recognising viral topics at their nascent stage and thereby helps an organization to change their strategy proactively instead of being reactive. This system is architected on a scalable big data stack technically, supported by high- streaming throughput data using Apache Kafka and in-memory processing using Apache Spark to provide low latency even under heavy loads. For an abstracted view of the information, the user interface includes an interactive multi-dimensional visual dashboard showing granular analysis of demographic segmentation, geographical sentiment hotspots, and temporal evolution of public opinion. Eventually, this R&D effort aims at democratizing access to high-level social data science, empowering stakeholders ranging from brand managers and political analysts to financial forecasters with a robust in social conversations.
KEYWORDS
This particular "Large Scale Social Media Sentiment and Trend Analysis" project is definitely an important milestone in the realm of computational social sciences. Our R&D efforts in this area have resulted in successful demonstration of the ability to blend fast streaming of information with deep learning in order to harness intelligence from chaos in information.The project successfully demonstrated the limitations of existing lexicon-based systems and proved that context-aware Transformer models can dramatically reduce false positives in sentiment detection, especially when sarcasm and slang come into play. The use of a scalable distributed architecture makes the system future-proof for handling ever-increasing volumes of global social media traffic. In addition, the emerging trend analysis component reveals the possibility to identify nascent viral topics that give organizations a competitive edge in decision-making. This system fills the gap between raw data and actionable strategy, providing a strong tool in brand management, political analysis, and social research. The successful execution of this project sets research into human-computer interaction and automated semantic understanding.
1. Vaswani,A.,Shazeer,N.,Parmar,N.,Uszkoreit,J.,Jones, L., Gomez,N., …&Polosukhin,I.(2017).”Attention is all you need.”Advance in Systems for Neural Information Processing,30,5998-6008. 2. Devlin, J., Chang, M. W., Lee, K., & Toutanova, K. (2018). "BERT: Pre-training of deep transfermers for Bidirectional Language Understanding.”Proceedings of the NAACL-HLT,4171-4186. 3. Go, A., Bhayani, R., & Huang, L. (2009). "Twitter sentiment classification using distant supervision.”CS224N Project Report ,Stanford. 4. BIFET, A., & Frank, E. (2010). "Sentiment knowledge discovery in twitter streaming data.”discovery Science,1-15. 5. Zaharia, M., Xin, R. S., Wendell, P., Das, T., Armbrust, M., Dave, A., ... & Stoica, I. (2016). "Apache Spark: a single engine for Processing large amount of data.”communication of the ACM,59(11),56-65.
Publication Date
5/19/2026
Peer Review Type
Double-Blind Peer Review
Review Rounds: 2
Documents
Article Views
0
Total views since publication
PDF Downloads
2
Total downloads since publication
Geographic Reach
5
Digital Preservation: This article is permanently archived on Zenodo and complies with all data preservation standards across major indexing platforms.
Plagiarism Screening
This manuscript has been checked for plagiarism using TurnitinPlagiarismChecker software.
Conflict of Interest
The authors declare no conflict of interest related to this research work.
Funding Information
No funding information available for this research.
Related research in the same subject area
Loading similar articles...