A System for the Prediction of election results using Vader and hybridized machine learning model

Abraham E. Evwiekpaefe, Department of Computer Science, Nigerian Defence Academy, Kaduna State, NigeriaFollow
Khadijah Kabir, Department of Computer Science, Kaduna State Polytechnic, Kaduna State, NigeriaFollow
Georgina N. Obunadike, Faculty of Computing, National Open University of Nigeria (NOUN), Abuja, NigeriaFollow

Section

Mathematics and Computational Sciences

Abstract

Integrating different classifiers along with sentiment lexicons like Vader, can enhance the performance of sentiment analysis systems. However, such a hybrid model remains underexplored, particularly in the context of regional elections in developing countries like Nigeria. The aim of this research is to develop a hybrid model that combines three machine learning classifiers and Vader lexicon to possibly achieve a higher accuracy. A case study of the 2023 governorship election in Kogi, Bayelsa and Imo State, Nigeria was examined. Twitter API library was utilized to extracted public and personal tweets using hashtags and keywords related to the target data from Wednesday, 14th June 2023 when campaign officially commenced to 9th November 2023, 24 hours to election day. A total of 2,326 tweets were extracted. After several data preprocessing techniques, implementation was done by automatic annotation of extracted tweets to determine their sentiments using Vader. The hybrid model classified tweets into positive, negative and neutral. It performed significantly well in predicting the sentiment of the tweets with an accuracy of 92%. Based on the percentage of positive sentiments, results reflected APC's victory in Imo State while PDP was predicted to win elections in Bayelsa and Kogi State.

Recommended Citation

Evwiekpaefe, Abraham E.; Kabir, Khadijah; and Obunadike, Georgina N. (2026) "A System for the Prediction of election results using Vader and hybridized machine learning model," Tanzania Journal of Science: Vol. 52: Iss. 2, Article 9.
Available at:https://doi.org/10.65085/2507-7961.2254