Institution Digital Repository

Recent Submissions

• Loading...

  Item type:Item,

  KENYAN LED UNITED NATION SECURITY MISSION TO HAITI: COMPARING PUBLIC VIEWS IN KENYA AND HAITI

  (UoEm, 2026-02-24)

  Wanyonyi, Elidah Nasimiyu

  Show more

  Haiti, officially the Republic of Haiti, is a country on the island of Hispaniola in the Caribbean Sea, east of Cuba and Jamaica and south of The Bahamas. Since 2018, Haiti's capital, Port-au-Prince, has been the site of gang-dominated chaos. On 2 October 2023, the United Nations Security Council approved a Kenyan-led Multinational Security Support (MSS) Mission in Haiti, in the form of an international police force, to assist the Haitian government in restoring law and order. This study explored the views of a wide cross-section of Kenyan and Haitian citizens on the Kenyan-led mission to Haiti. The study employed a comparative case study research design. Convenience and snowball sampling were used. Data were collected using a semi-structured online questionnaire administered to at least 294 respondents in Kenya and 27 in Haiti, resulting in a final sample of 321. Descriptive analysis was used to explore the views of Kenyans and Haitians, and a Mann-Whitney U test was used to compare their views. Qualitative data were analysed thematically to get a clear understanding of citizens' in-depth opinions and perceptions across both countries. The legitimacy theory of state actions guided the study in evaluating the perceived legitimacy of the Kenyan-led United Nations security mission to Haiti. The findings showed that the mission lacked empirical legitimacy. The majority of respondents in both countries said the mission was unnecessary and that they did not support it. The study, therefore, concludes that although the UN security interventions may have normative legitimacy, they must be socially acceptable to achieve their objectives.

  Show more
• Loading...

  Item type:Item,

  ASSESSING THE POLLUTION STATUS OF RIVER KAPINGAZI EMBU COUNTY, KENYA

  (UoEm, 2026-07-18)

  Yego, Naomy Chepkirui

  Show more

  Water resources confronts immense pressure from human needs, climate change variation, and pollution, which is a major environmental problem. Available literature focuses more on the sources of riverine pollution and their effects on human health. Characterization of the sources of water pollution in the river Kapingazi has not been done necessitating this study. The goal of the research was: to determine different land uses contributing to water pollution in River Kapingazi catchment, Embu County; to evaluate the extent of pollution in River Kapingazi; and to assess the water pollution mitigation measures adopted for River Kapingazi Embu County. For objective one, satellite images (LANDSAT) were utilized to classify the land use land cover (LULC) using supervised maximum likelihood classification. The study analyzed 96 water samples from four locations in a span of eight months which combined the dry and wet seasons of the year to analyze objective two. Parameters measured in-situ included turbidity, pH, total dissolved solids (TDS), temperature, dissolved oxygen (DO) and electrical conductivity (EC) determined using calibrated portable multiparameter analyzer H19829, while ex-situ parameters were salts (phosphates and nitrates) measured using calibrated UV 1800PC and concentrations of heavy metals (iron and Manganese) determined through lab analysis using Atomic Absorption Spectrophotometer. In objective three, a cross-sectional survey design was employed to solicit data from 385 respondents with the aid of a semi-structured questionnaire. Data obtained were cleaned and coded before analysis through descriptive statistics presented in tables, percentage and frequencies, and inferential statistics which employed generalized linear model (GLM), probit model and ordinary least square (OLS) regression model. Results show that tree cover has been decreasing over time while crop land and built areas have been increasing. Water Quality Index (WQI) during the drought period was measured to be 74.05, suggesting that the water quality is only recommended for agricultural and industrial applications. In wet season, the WQI was measured to be 89.67, reflecting a poor status, as more contaminants were likely introduced through surface runoff. This study concludes that there is a sharp decline in tree cover owing to land use operations, which could impact directly on water quality. The water in River Kapingazi is not suitable for human consumption, hence appropriate treatment is essential prior to its use. Involving stakeholders such as NEMA, WRA, EWASCO and Ministry of Agriculture and supporting community programs were crucial strategies in enhancing the water quality outcomes. Measures that prioritize the sustainability of the environment should be emphasized. It is also recommended that the directing resources towards water treatment systems and the regulation of pollution sources ought to be enforced to ensure the safety of river water for diverse applications. Additionally, these findings highlight the significance of collective participation in technical plannnery and cohesive governance towards the safeguarding of riverine ecosystems.

  Show more
• Loading...

  Item type:Item,

  FORECASTING STOCK PRICES IN NAIROBI STOCK EXCHANGE USING MACHINE LEARNING AND TIMESERIES

  (UoEm, 2026-07-18)

  Macharia, Kevin Ng'ang'a

  Show more

  The volatility, structural inefficiencies, and external shocks, are common in emerging markets such as Nairobi Securities Exchange (NSE). These make predictive modelling challenging in the markets hence stock price forecasting in financial markets has been a critical challenge particularly in emerging markets. This work helps fill gaps in forecasting techniques by creating and testing hybrid models, which combine machine learning and time series methods. The study compared two models, the Autoregressive Integrated Moving Average (ARIMA) and Artificial Neural Network (ANN), it enhances ANNs with Ordinary Differential Equation (ODE)-based features, which can capture multi-scale behavior, and it also augments ARIMA with GARCH model to model volatility clustering. The study utilizes closing prices of Safaricom PLC (2015-2020), a strong stock in the NSE, on a daily basis, to test these frameworks. The ARIMA models were based on linear tendencies, and the ANN model used the feature engineering based on the lagged stock prices, the derivatives to identify the short-term fluctuations, and the integrals to identify the long-term tendencies. The hybrid ARIMA-GARCH accounted volatility persistence. Model performance was measured by the Mean Squared Error (MSE), Mean Absolute Error (MAE), and the Root Mean Squared Error (RMSE). The key findings made included the fact that the ODE-enhanced ANN was better than the standalone ARIMA and the simple ANN models in terms of the decrease of the MSE by 64.7 percent and the decrease of the MAE by 71. The results of the ARIMA-GARCH hybrid were impressive as they reduced RMSE by 17.4 percent and confirmed the applicability of the volatility modeling in the emerging markets. The superior performance of ANN shows that it was able to capture non-linear dynamics and to respond to the extreme fluctuations of the price, and volatility persistence (β = 0.999) in GARCH showed high volatility persistence in NSE that made NSE susceptible to long-term instabilities. The researchers have suggested application of hybrid models among the practitioners of the financial markets as they are able to capture the characteristics of the domain. The research also emphasizes the need for innovative feature engineering in enhancing risk mitigation and trading strategies. To policymakers, this research recommends that it is necessary to reduce market concentration and increase data transparency so as to level the current volatility witnessed in emerging economies. Further areas of research potential would be a combination of other data sets, such as news data, sentiments, economic indexes, among others, to increase the accuracy of the predictive behavior.

  Show more
• Loading...

  Item type:Item,

  SENTIMENT ANALYSIS-BASED MODEL FOR MONITORING USER ENGAGEMENT WITH MENTAL HEALTH CHATBOTS.

  (UoEm, 2025-08-25)

  Mmbayi, Ian Igado

  Show more

  Mental health challenges, particularly among youth, are compounded by stigma and limited access to professional care. This has driven demand for scalable digital solutions like chatbots. This study introduces a sentiment analysis-based model to assess user satisfaction with mental health chatbots, analysing 82,102 reviews from six popular apps on Google Play and Apple’s App Stores. A multi-class sentiment classification of positive, negative, and neutral was implemented, enhanced by Synthetic Minority Over-sampling Technique for class balancing, comparing five traditional machine learning models with Bidirectional Encoder Representations from Transformers, a transformer model. Random Forest achieved 98.18% accuracy among traditional models, while BERT outperformed all with 99.17% accuracy, surpassing prior benchmarks. Aspect-based analysis revealed that Emotion and Usability drive positive feedback, while Reliability issues fuel negative sentiments, offering actionable insights for developers to enhance chatbot design. This work advances digital mental health research by integrating multi-class classification, transformer models, and aspect-based analysis, demonstrating a scalable framework for evaluating user feedback.

  Show more
• Loading...

  Item type:Item,

  Climate Adaptive Extension Services and Resilience of Sorghum Farming Households in Semi-Arid Areas of Embu and Tharaka-Nithi Counties, Kenya

  (South African Journal of Agricultural Extension (SAJAE), 2026)

  Njiru, M.M

  ;

  Kaumi, F.K.

  ;

  Mogaka, Hezron R.

  ;

  Ndirangu, S.N

  ;

  Kiprotich, S

  Show more

  Unpredictable weather events resulting from climate change have caused widespread destruction of people, livestock, and property. To counteract these negative effects and help farmers mitigate the adverse impacts of climate change, climate-adaptive extension services (CAES) have been designed by institutions. The CAES helps farming households respond appropriately by making timely, informed decisions to mitigate the impacts of climate change and enhance resilience. The objective of the study was to determine the level of resilience among sorghum-farming households and the CAEs that enhance resilience in arid and semi-arid lands (ASALs) of Embu and TharakaNithi Counties, Kenya. Primary data were collected from a sample of 426 sorghum-farming households using questionnaires. An ordered probit regression model was estimated in Stata to analyse the data. The results indicated low household resilience to climate change. Moreover, the results revealed that capacity building, information on climate-smart technologies, timely weather information, training, weather advisories, and diversified strategies were effective CAES that enhanced resilience. This information is crucial for policymakers to design ways to enhance the use of effective CAES and increase households’ resilience.

  Show more