AI FOR REAL TIME SOCIAL MEDIA DATA ANALYSIS | IJCT Volume 12 – Issue 6 | IJCT-V12I6P25
International Journal of Computer Techniques
ISSN 2394-2231
Author
Yash Pardeshi , Prof. Priyanka Kute
Abstract
Social media sites like Facebook, Instagram, and Twitter have grown exponentially, creating enormous, ongoing data streams. This data offers a wealth of information that may be used to detect disinformation, analyze new trends, and comprehend public opinion [1]. Its unstructured form and real-time nature, however, make analysis extremely difficult. Deep learning and natural language processing, two areas of artificial intelligence, offer effective methods for drawing conclusions from this data[3]. A framework for AI-powered real-time social media data analysis is presented in this study. The platform combines sophisticated NLP models like BERT and LSTM with big data tools like Apache Kafka and Spark Streaming. Low-latency trend identification, efficient spam/bot filtering, and high sentiment classification accuracy are all achieved by these models, according to results from prototype and literature research [5].
Keywords
Social Media, Artificial Intelligence, Real-Time Analytics, NLP, Sentiment Analysis, Big Data
Conclusion
This study shows that real-time social media data analysis driven by AI is both possible and extremely effective. Large-scale social media streams can be analyzed with low latency and high accuracy by merging sophisticated NLP models (BERT, LSTM, GPT) with big data frameworks (Kafka, Spark Streaming) [1][3]. These systems facilitate stronger crisis response, better governance, and quicker decision-making. Future developments in edge and multimodal AI will increase the technology’s potential and range of uses [12][15].
References
1.[1] Devlin, J., Chang, M. W., Lee, K., & Toutanova, K. (2019). BERT: Pre-training of deep bidirectional transformers for language understanding.
Retrieved from
https://arxiv.org/abs/1810.04805
2.Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., … & Polosukhin, I. (2017). Attention is all you need. Retrieved from https://arxiv.org/abs/1706.03762
3.Ayush Kumar & Kamalraj R (2024). Real-time sentiment analysis on social media streams using BERT and Apache Spark. Journal of Big Data.Retrieved from https://www.researchgate.net/pu blication/380707012_Real-Time
_Sentiment_Analysis_System_ Using_the_BERT_Model
4.Zimbra D., Abbasi A., Zeng D., & Chen, H. (2018). The state-of-the-art in Twitter sentiment analysis: A review and benchmark evaluation. ACM TMIS.Retrieved from https://dl.acm.org/doi/10.1145/3 185045
5. Saif, H., He, Y., Fernandez, M., & Alani, H. (2014). Semantic sentiment analysis of Twitter. Retrieved from
https://doi.org/10.1007/978-3-31 9-11964-9_32 6. Md Shah Alam (2025). A comparative study of NLP models for real-time event detection. Procedia Computer Science.Retrieved from https://www.researchgate.net/pu blication/390335725_SENTIME NT_ANALYSIS_IN_SOCIAL_M EDIA_HOW_DATA_SCIENCE_I MPACTS_PUBLIC_OPINION_K NOWLEDGE_INTEGRATES_N ATURAL_LANGUAGE_PROCE SSING_NLP_WITH_ARTIFICIA L_INTELLIGENCE_AI
7.Chen, E., Lerman, K., &
Ferrara, E. (2020). Tracking social media discourse about COVID-19. JMIR Public Health and Surveillance. Retrieved from https://publichealth.jmir.org/202 0/2/e19273
8. Mahmud H. (2018). Real-time topic detection from Twitter streams: A deep learning approach. Journal of Intelligent & Fuzzy Systems. Retrieved from
https://www.researchgate.net/pu blication/323743194_Real-time
_event_detection_from_the_Twi tter_data_stream_using_the_Tw itterNews_Framework
9.Muhammad, S., Muhammad, A., & Usman, M. (2022).
Comparative analysis of sentiment analysis techniques for Twitter data. PeerJ Computer Science. Retrieved from https://peerj.com/articles/cs-999
/
10.Liu, B. (2020). Sentiment analysis and opinion mining. Synthesis Lectures on HLT. Retrieved from
https://doi.org/10.2200/S00416 ED1V01Y201204HLT016
11.McCreadie, R., Macdonald, C., & Ounis, I. (2019). Incremental update strategies for real-time event detection. Information Retrieval Journal. Retrieved from https://doi.org/10.1007/s10791- 018-09341-3
12.Kumar, A., & Garg, G. (2019).
Sentiment analysis of multimodal Twitter data. Multimedia Tools and Applications. Retrieved from https://doi.org/10.1007/s11042- 019-7593-9
13.Saha, P., Mathews, M., & Goyal, P. (2017). Predicting the real-time impact of events using social media. WWW Companion. Retrieved from https://doi.org/10.1145/3041021
.3054171
14.Rizoiu, M. A., Lee, Y., Conover, M., & Xie, L. (2018). A
data-driven approach to modeling viral content. WSDM.
15.Al-Smadi, M., Talafha, B., & Jararweh, Y. (2019). Aspect-based sentiment analysis of Arabic tweets. Retrieved from
https://doi.org/10.1016/j.future.2 019.02.012
16.Hu, M., & Liu, B. (2004). Mining and summarizing customer reviews. Retrieved from https://doi.org/10.1145/1014052
.1014073
17.Kouloumpis, E., Wilson, T., & Moore, J. (2011). Twitter sentiment analysis: The good, the bad and the OMG! ICWSM. Retrieved from
https://ojs.aaai.org/index.php/IC WSM/article/view/14107 18. Hasan, M., Orgun, M. A., & Schwitter, R. (2018). Real-time event detection from Twitter streams. Information Processing & Management. Retrieved from
https://doi.org/10.1016/j.ipm.201 8.05.001 19.Twitter Developer
Documentation. (2024). Twitter API v2 Documentation. Retrieved from
https://developer.twitter.com/en/ docs 20.Pawar, R., Patil, M., & Joshi, P. (2023). Survey on text summarization techniques in social media analytics. Sustainability.
How to Cite This Paper
Yash Pardeshi , Prof. Priyanka Kute (2025). AI FOR REAL TIME SOCIAL MEDIA DATA ANALYSIS. International Journal of Computer Techniques, 12(6). ISSN: 2394-2231.
