Ayodeji O. J. Ibitoye

Work place: School of Computing and Mathematical Science, Faculty of Engineering and Science, University of Greenwich, SE10 9LS, London

E-mail: a.o.ibitoye@greenwich.ac.uk


Research Interests: Soft Computing, Big Data Analytics, Decision Support System, Natural Language Processing


Ayodeji Ibitoye currently researches and facilitates at the School of Computing and Mathematical Science, Greenwich University, London, United Kingdom. He obtained his B.Sc. and M.sc Computer Science from the prestigious University of Ilorin, Ilorin Kwara State, Nigeria and University of Ibadan, Ibadan, Oyo state, Nigeria in 2009 and 2014 respectively. He completed his Ph.D. in Computer Science, University of Ibadan in January, 2020. While his research journey started in 2012 in Information Retrieval, with thirst for excellence and potentials for smart outputs in Artificial Intelligence driven solutions, his research in Big Data Analytics and Soft Computing paradigm have been applied in the areas of Predictive Technologies, Natural Language Processing, Pattern Mining and Decision Support Systems

Aside winning different poster presentations at diverse conferences like Humboldt Kolleg/Conference, OAU, IFE, Nigeria in 2021, He won the Maiden Edition of MTN Academic Research and Development Innovation challenge in 2019. He is also a recipient of different local and international fully funded fellowships like the Machine Learning Summer School, London, CODATA RDA Data Science Summer School. ICTP, Trieste, Italy.

Dr Ayodeji is a member of Data Science Nigeria, IAENG, Black in AI among others. He has several peered reviewed publications in journals and conferences in his field of expertise. He loves singing, writing and consulting for corporate organisations and government agencies.

Author Articles
Utilizing RoBERTa Model for Churn Prediction through Clustered Contextual Conversation Opinion Mining

By Ayodeji O. J. Ibitoye Olufade F.W. Onifade

DOI: https://doi.org/10.5815/ijisa.2023.06.01, Pub. Date: 8 Dec. 2023

In computational study and automatic recognition of opinions in free texts, certain words in sentences are used to decide its sentiments. While analysing each customer’s opinion per time in churn management will be effective for personalised recommendations. Oftentimes, the opinion is not sufficient for contextualised content mining. While personalised recommendations are time consuming, it also does not provide complete picture of an overall sentiment in the business community of customers. To help businesses identify widespread issues affecting a large segment of their customers towards engendering patterns and trends of different customer churn behaviour, here, we developed a clustered contextualised conversation as opinions set for integration with Roberta Model. The developed churn behavioural opinion clusters disambiguated short messages while charactering contents collectively based on context beyond keyword-based sentiment matching for effective mining. Based on the predicted opinion threshold, customer churn category for group-based personalised decision support was generated, with matching concepts. The baseline RoBERTa model on the contextually clustered opinions, trained with a batch size of 16, a learning rate of 2e-5, over 8 epochs, using a maximum sequence length of 128 and standard hyperparameters, achieved an accuracy of 92%, Precision of 88%, Recall of 86% and F1 score of 84% over a test set of 30%.

[...] Read more.
Other Articles