Exploring sentiments in social media poses a task to natural language processing because of the complexity and variability in the different dialect expression, noisy terms in form of local slang, abbreviation, acronym, emoticon, and spelling blunder combined with the disposal of ever new contents and updates. Most of the knowledge based approaches for resolving these local slangs and acronyms may not always reflect the handling of these blaring terms especially the local Nigerian content. This work implements a designed and enhanced structure meant for social media contents pre-processing that uses the modified Lesk procedure or algorithm to simplify pre-processing of social media contents. The aftermaths after the assessment shown an enhancement over existing methods when applied to supervised learning algorithms in the task of mining thoughts and opinions from Nigeria-Igbo tweets with an accuracy of 90% Keywords: Sentiment Analysis, Pre-processing, Opinion Mining, Nigerians Tweets, Twitter, Data Mining.
• Hardware: Processor: i3 ,i5 RAM: 4GB Hard disk: 16 GB • Software: operating System : Windws2000/XP/7/8/10 Anaconda,jupyter,spyder,flask Frontend :-python Backend:- MYSQL
₹13500 (INR)
NON IEEE -2021