Sentiment Analysis of Twitter Data on Public Perception of NNPCL in the South South Zone

📖 ABSTRACT/OVERVIEW

Understanding public sentiment toward the Nigerian National Petroleum Company Limited is important for corporate reputation management and policy communication, and social media data provides a rich, unstructured source for this analysis. This study performed sentiment analysis on Twitter posts related to NNPCL from users in Rivers, Delta, Bayelsa, Akwa Ibom, Cross River, and Edo States representing the South South geopolitical zone. A total of 28,400 tweets were collected using the Twitter API with geolocation filters over a six-month period from January to June 2023. Text preprocessing involved tokenisation, stop word removal, stemming, and emoji interpretation. VADER and TextBlob sentiment classifiers were applied and compared, with VADER achieving higher accuracy on domain-specific labelled validation data (82.1 percent versus 74.6 percent). Sentiment results showed that 38.4 percent of tweets were negative, 31.7 percent positive, and 29.9 percent neutral. Negative sentiment spiked during fuel supply disruptions and following announcements of price adjustments. Positive sentiment was linked to community development initiatives and refinery progress announcements. Qualitative content analysis of the most-retweeted negative posts identified environmental remediation concerns as the dominant grievance theme. The study demonstrates the feasibility of real-time reputation monitoring using social media analytics in the Nigerian oil sector. Recommendations include establishing a social media listening dashboard for NNPCL, developing communication strategies responsive to identified grievance themes, and engaging community stakeholders in the South South zone through evidence-based dialogue.

Keywords: sentiment analysis, Twitter, NNPCL, public perception, South South Nigeria

Need Complete Chapters of the Above Topic?

Get high-quality, Zero-AI research materials with current citations.

Request via WhatsApp 💬
Departments# Data Science