• Okpalla C.L.
• Ezekwem F.C.
• Benson-Emenike M.E
• Amaka E,N,
• Iwuchukwu V.C.

Driven by the necessity for inexpensive sentiment analysis in Nigeria, where public opinion influence commercial and political outcomes, this research paper developed a Social Media Sentiment Analyzer customized for brands and political material on the X platform. The lack of real-time, low-resource tools to interpret multilingual data, such as Pidgin and slang is normally a problem; manual methods are slow and biased, and expensive tools like BERT, which require 16GB RAM PCs, are unaffordable for small businesses in rural Enugu or Onitsha and frequently misclassify local phrases like "dey try." In order to solve this, the system gathered 1,000 posts through the X API, preprocessed them using Python 3.8 to handle Pidgin translations, trained a Naive Bayes model on a PC with 4GB of RAM, and produced Matplotlib pie charts for visualization that were tailored to Nigeria's varied user base. The results, which tracked a positive rise during an MTN event, revealed 75% accuracy over 500 test postings with 65% positive, 20% negative, and 15% neutral sentiments. Feedback from a marketing manager and a small business owner validated its usefulness for making decisions. The research provides a scalable framework for emerging markets, suggesting potential improvements with deep learning to empower consumers from Lagos to rural villages, despite restrictions like public data bias and delayed processing owing to RAM constraints.

Sentiment Analysis, X Platform, Naive Bayes, Visualization, Social Media.

"A SENTIMENT ANALYSIS SYSTEM FOR BRANDS AND POLITICAL CONTENT USING SOCIAL MEDIA DATA ", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.13, Issue 1, page no.b10-b17, January-2026, Available :http://www.jetir.org/papers/JETIR2601103.pdf

"A SENTIMENT ANALYSIS SYSTEM FOR BRANDS AND POLITICAL CONTENT USING SOCIAL MEDIA DATA ", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.13, Issue 1, page no. ppb10-b17, January-2026, Available at : http://www.jetir.org/papers/JETIR2601103.pdf