https://repository.maseno.ac.ke/handle/123456789/2981 Fri, 15 May 2026 12:33:54 GMT 2026-05-15T12:33:54Z https://repository.maseno.ac.ke/handle/123456789/6211 State of NLP in Kenya: A Survey Cynthia Jayne Amol, Everlyn Asiko Chimoto, Rose Delilah Gesicho, Antony M Gitau, Naome A Etori, Caringtone Kinyanjui, Steven Ndung'u, Lawrence Moruye, Samson Otieno Ooko, Kavengi Kitonga, Brian Muhia, Catherine Gitau, Antony Ndolo, Lilian DA Wanzare, Albert Njoroge Kahira, Ronald Tombe Kenya, known for its linguistic diversity, faces unique challenges and promising opportunities in advancing Natural Language Processing (NLP) technologies, particularly for its underrepresented indigenous languages. This survey provides a detailed assessment of the current state of NLP in Kenya, emphasizing ongoing efforts in dataset creation, machine translation, sentiment analysis, and speech recognition for local dialects such as Kiswahili, Dholuo, Kikuyu, and Luhya. Despite these advancements, the development of NLP in Kenya remains constrained by limited resources and tools, resulting in the underrepresentation of most indigenous languages in digital spaces. This paper uncovers significant gaps by critically evaluating the available datasets and existing NLP models, most notably the need for large-scale language models and the insufficient digital representation of Indigenous languages. We also analyze key NLP applications: machine translation, information retrieval, and sentiment analysis-examining how they are tailored to address local linguistic needs. Furthermore, the paper explores the governance, policies, and regulations shaping the future of AI and NLP in Kenya and proposes a strategic roadmap to guide future research and development efforts. Our goal is to provide a foundation for accelerating the growth of NLP technologies that meet Kenya's diverse linguistic demands. Sun, 13 Oct 2024 00:00:00 GMT https://repository.maseno.ac.ke/handle/123456789/6211 2024-10-13T00:00:00Z https://repository.maseno.ac.ke/handle/123456789/3009 Post adoption evaluation model for cloud computing services utilization in universities in Kenya Titus M Muhambe Cloud computing is a new computing paradigm that is gaining popularity in Kenya and the world over and as such this study was conducted in order to gain a better understanding of this phenomenon. This study was primarily aimed at: identifying the primary factors that influence the acceptance and use of cloud computing services in Universities in Kenya, establishing the moderating factors to the identified primary factors, present a model for post adoption evaluation of cloud computing services utilization in universities in Kenya and compare utilization levels of the different categories of cloud computing services among university students in Kenya. We reviewed literature on technology adoption theories and models, focusing . on the postulates of these theories and models, their strengths and weaknesses, selected case studies where each of the theories or model had been used in technology adoption studies, the results obtained and the conclusions drawn. Our research methodology involved the use of questionnaires and Focus Group Discussion (FGD) to gather data, analysis of the quantitative data was through computation of partial correlation coefficients between the dependent and independent variables and using the Focus Group Discussion to explain some of the observed trends and phenomenon. Our findings revealed that Performance Expectancy and Facilitating Conditions were the two main factors that influence Behavioral Intention to accept cloud computing services, while behavioral intention directly influences use behavior. Effort Expectancy and Social Influence constructs were both found have no significant influence on … Tue, 01 Jan 2013 00:00:00 GMT https://repository.maseno.ac.ke/handle/123456789/3009 2013-01-01T00:00:00Z https://repository.maseno.ac.ke/handle/123456789/3008 Evaluating the sustainability of mHealth systems in developing countries: the knowledge gap Muhambe Titus Mukisa, Daniel Orwa Ochieng, Peter Wagacha Waiganjo The use of mobile technology in healthcare, known as mHealth is being explored across the developing countries as part of the effort to tackle growing disease burden through, prevention and appropriate and prompt intervention strategies. Although the outcomes of some of the implemented mHealth projects have been successful with very promising results, a significant number of the projects have failed after a short period of use. Studies carried out on the failed projects pointed to lack of sustainability. Review of existing technology evaluation model against the cited challenges reveals significant deficiencies in the models and thus not suitable to evaluate sustainability of mHealth system in developing countries. It is clear that there exist a knowledge gap and hence the need to develop and validate a suitable mHealth system sustainability evaluation model. Sun, 01 Jan 2017 00:00:00 GMT https://repository.maseno.ac.ke/handle/123456789/3008 2017-01-01T00:00:00Z https://repository.maseno.ac.ke/handle/123456789/3007 An Evaluation of Hybrid Machine Learning Classifier Models for Identification of Terrorist Groups in the aftermath of an Attack Peter Opiyo Oketch, Muhambe Titus Mukisa, Makiya Cyprian Ratemo The urgency of responding to a terrorist attack and the subsequent nature of analysis required to identify the terrorist group involved in an attack demands that the performance of the machine learning classifiers yield highly accurate outcomes. In order to improve the performance of machine learning classifiers, hybrid machine learning algorithms are used with the goal of improving the accuracy. The aim of the study was to build and evaluate hybrid classifier models for identification of terrorist groups. The research specifically sought to: build base classifiers (Naïve Bayes, K-Nearest Neighbor, Decision Trees, Support Vector Machines and Multi-Layer Perceptron); build hybrid classifier models from a combination of the base classifiers; and compare the performance of the hybrid and base classifiers. The study adopted an experimental research method using WEKA tool for data mining and real-world terrorist datasets for the period 1999-2017 for Sub-Saharan Africa region from the Global Terrorism Database. WEKA supervised filter Ranker was used to select 6 attributes of data and 784 records. The classifiers were evaluated using 10-fold cross validation. The study established that the optimal performance for all the classifiers was realized with a more balanced class at a resample rate of 1000%. The study concludes that hybrid classifiers perform better than base classifiers, and the best performing model was a hybrid combination of KNN, and DT. The study provides insights on the performance of hybrid machine learning classifiers and lays a foundation for further research in hybrid machine learning approaches. Tue, 01 Jan 2019 00:00:00 GMT https://repository.maseno.ac.ke/handle/123456789/3007 2019-01-01T00:00:00Z