Probing 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 error coupled with the availability of real-time content. Most of the knowledge based approaches for resolving local Nigerian slangs, abbreviation and acronym do not consider the issue of ambiguity that evolves in the usage of these noisy terms. This research implements an improved framework for social media feed pre-processing that leverages on the adapted Lesk algorithm to facilitate pre-processing of social media feeds. The results from the experimental evaluation revealed an improvement over existing methods when applied to supervised learning algorithms in the task of extracting sentiments from Nigeria-Igbo tweets with an accuracy of 90%.
展开▼
