Skip to main content

tatenda kavu

University of Zimbabwe, Computer Science, Faculty Member

Followers

56

Following

31

Public Views

Julita Vassileva

University of Saskatchewan

Sebastián Ventura

Universidad de Córdoba

Kostas Zafiropoulos

University of Macedonia

Armando Marques-Guedes

UNL - New University of Lisbon

Dr. Chhavi Rana

Maharshi Dayanand University

Università degli Studi di Bari

Roshan Chitrakar

Nepal College of Information Technology

Graduate Center of the City University of New York

Sylvester Olubolu Orimaye

Monash University

Gujarat Technological University

Interests

Uploads

Papers by tatenda kavu

Analysing the Performance and Interpretability of CNN-Based Architectures for Plant Nutrient Deficiency Identification

Computation, Jun 3, 2024

Early detection of plant nutrient deficiency is crucial for agricultural productivity. This study... more Early detection of plant nutrient deficiency is crucial for agricultural productivity. This study investigated the performance and interpretability of Convolutional Neural Networks (CNNs) for this task. Using the rice and banana datasets, we compared three CNN architectures (CNN, VGG-16, Inception-V3). Inception-V3 achieved the highest accuracy (93% for rice and banana), but simpler models such as VGG-16 might be easier to understand. To address this trade-off, we employed Explainable AI (XAI) techniques (SHAP and Grad-CAM) to gain insights into model decision-making. This study emphasises the importance of both accuracy and interpretability in agricultural AI and demonstrates the value of XAI for building trust in these models.

Comparative Performance Analysis of Machine Learning Classifiers on COVID-19 Datasets: Exploring the Effect of Data Imputation, Cross-Validation, and Principal Component Analysis

PA-362 Towards explainable AI-based decision support in predicting SARS-CoV-2 breakthrough infections in a SSA context

Detecting the most critical clinical variables of COVID-19 breakthrough infection in vaccinated persons using machine learning

DIGITAL HEALTH

Background COVID-19 vaccines offer different levels of immune protection but do not provide 100% ... more Background COVID-19 vaccines offer different levels of immune protection but do not provide 100% protection. Vaccinated persons with pre-existing comorbidities may be at an increased risk of SARS-CoV-2 breakthrough infection or reinfection. The aim of this study is to identify the critical variables associated with a higher probability of SARS-CoV-2 breakthrough infection using machine learning. Methods A dataset comprising symptoms and feedback from 257 persons, of whom 203 were vaccinated and 54 unvaccinated, was used for the investigation. Three machine learning algorithms – Deep Multilayer Perceptron (Deep MLP), XGBoost, and Logistic Regression – were trained with the original (imbalanced) dataset and the balanced dataset created by using the Random Oversampling Technique (ROT), and the Synthetic Minority Oversampling Technique (SMOTE). We compared the performance of the classification algorithms when the features highly correlated with breakthrough infection were used and when ...

A Review of Deep Learning Models for Detecting Cyberbullying on Social Media Networks

Cybernetics Perspectives in Systems

A fraud detection tool in E-auctions

Due to rapid growth of the use of online auctions, fraudsters have taken advantage of these platf... more Due to rapid growth of the use of online auctions, fraudsters have taken advantage of these platforms to participate in their own auctions in order to raise prices (a practice called shilling). Innocent bidders have been forced to pay higher prices than they were willing to offer. This has resulted in the need to design and implement a shill detection algorithm. To eliminate this shilling problem, we designed a shilling detection algorithm integrated with an online auction. The algorithm proved to be effective and it was tested on the internet, and the short time of shill detection proved that the algorithm can work real time on e-auctions with large user base. This method can be used as a technique to eliminate shilling. Key words: E-auction, bidding, shilling, shill attributes, shill score.

A Novel, Serendipitous and Dynamic User-Centric Recommender Algorithm

Proceedings of the EAI International Conference for Research, Innovation and Development for Africa, 2018

Information filtering for web service using machine learning has recently grown widely , since in... more Information filtering for web service using machine learning has recently grown widely , since information overload has also becoming a serious problem on the World Wide Web. Recommender systems were designed to cater for this problem, but published recommender systems still fail to cope with changes of user's preferences. This paper summarizes a research that is still going on, to solve the lack of novelty, serendipity and dynamism in recommender systems. Recent research has demonstrated different methodologies to create recommender systems , unfortunately many of these which were evaluated using user-centric evaluation frameworks fall short to fulfill users' satisfaction. Therefore we propose a unique computational method to create a novel, serendipitous and dynamic recommender system. We used web content mining to gather user profiles from social media, model these profiles, and create an algorithm to suggest user preferences. The results testify that many users' social profiles for Zimbabweans dominate quite well to determine user preferences. Therefore recommender developers for developing countries, has to gather user's social profiles to predict their preferences. The main contribution is a holistic approach to model and predict dynamic user-specific preferences from categorized social media profiles namely: social, psychological, cultural, and economic profiles

Towards QR Code Health Systems Amid COVID-19: Lessons Learnt from Other QR Code Digital Technologies

Springer Series on Bio- and Neurosystems

Erratum to “Holistic User Context-Aware Recommender Algorithm”

Mathematical Problems in Engineering, 2020

<jats:p />

Successful Utilization of Technology for Knowledge Management: A Review of

While various organizations have invested in knowle dge management (KM), it is not day business. ... more While various organizations have invested in knowle dge management (KM), it is not day business. Technology plays a major role in KM, aiding in the creation, transfer, sharing and storage of knowledge, making it an integral part of KM processes. This has necessitated the need for studies into technology's involvement in KM and how it can contribute effectively to the KM objectives of the imple menting a lack of depth in the fundamental issues and concepts affecting technolog ical underlying issues are left to the implementing orga nization to figure out, there is a weak foundation upon which KM is built. The theoretical framework for technological use in KM is not solidly developed, resulting in an unstructured app roach towards technological use and implementations in KM. disciplinary nature of KM, which has led to academi cs concentrating more on certain disciplines contributing to KM, such as management and social aspects of KM, while disciplines information technology (IT) h...

A universal electronic payment model in Zimbabwe integrating with Small and Medium Enterprises and working with mobile databases

Electronic payment systems are proliferating in banking, retail in government and everywhere mone... more Electronic payment systems are proliferating in banking, retail in government and everywhere money needs to be exchanged. Electronic payment systems are the everyday technology under use, they are the relevant systems which go hand in hand with technology and they are also high in demand. All these issues enlighten a need to design and implement an electronic payment system that addresses the specific requirements for the Zimbabwean market. An effective and universal electronic payment system in Zimbabwe can solve some problems which are currently encountered in e-commerce, thus we designed a light weight electronic payment model, universal and offering better integration to banks, all merchants and Small and Medium Enterprises. It is comprised of attributes which any electronic payment system is expected to have. It has its own security features especially the offline authentication method and other security aspects which are currently in use by banks. The integrated architectural ...

African Journal of Mathematics and Computer Science Research, Jan 31, 2016

Due to rapid growth of the use of online auctions, fraudsters have taken advantage of these platf... more Due to rapid growth of the use of online auctions, fraudsters have taken advantage of these platforms to participate in their own auctions in order to raise prices (a practice called shilling). Innocent bidders have been forced to pay higher prices than they were willing to offer. This has resulted in the need to design and implement a shill detection algorithm. To eliminate this shilling problem, we designed a shilling detection algorithm integrated with an online auction. The algorithm proved to be effective and it was tested on the internet, and the short time of shill detection proved that the algorithm can work real time on e-auctions with large user base. This method can be used as a technique to eliminate shilling.

A Novel, Serendipitous and Dynamic User-Centric Recommender Algorithm

Information filtering for web service using machine learning has recently grown widely , since in... more Information filtering for web service using machine learning has recently grown widely , since information overload has also becoming a serious problem on the World Wide Web. Recommender systems were designed to cater for this problem, but published recommender systems still fail to cope with changes of user's preferences. This paper summarizes a research that is still going on, to solve the lack of novelty, serendipity and dynamism in recommender systems. Recent research has demonstrated different methodologies to create recommender systems , unfortunately many of these which were evaluated using user-centric evaluation frameworks fall short to fulfill users' satisfaction. Therefore we propose a unique computational method to create a novel, serendipitous and dynamic recommender system. We used web content mining to gather user profiles from social media, model these profiles, and create an algorithm to suggest user preferences. The results testify that many users' social profiles for Zimbabweans dominate quite well to determine user preferences. Therefore recommender developers for developing countries, has to gather user's social profiles to predict their preferences. The main contribution is a holistic approach to model and predict dynamic user-specific preferences from categorized social media profiles namely: social, psychological, cultural, and economic profiles

Characterisation of User-Contexts for Context-Aware Recommendation Systems

Proceedings of the Future Technologies Conference (FTC) 2021, Volume 1

A Characterisation and Framework for User-Centric Factors in Evaluation Methods for Recommender Systems

International Journal of ICT Research in Africa and the Middle East, 2017

Researchers have worked on-finding e-commerce recommender systems evaluation methods that contrib... more Researchers have worked on-finding e-commerce recommender systems evaluation methods that contribute to an optimal solution. However, existing evaluations methods lack the assessment of user-centric factors such as buying decisions, user experience and user interactions resulting in less than optimum recommender systems. This paper investigates the problem of adequacy of recommender systems evaluation methods in relation to user-centric factors. Published work has revealed limitations of existing evaluation methods in terms of evaluating user satisfaction. This paper characterizes user-centric evaluation factors and then propose a user-centric evaluation conceptual framework to identify and expose a gap within literature. The researchers used an integrative review approach to formulate both the characterization and the conceptual framework for investigation. The results reveal a need to come up with a holistic evaluation framework that combines system-centric and user-centric evaluation methods as well as formulating computational user-centric evaluation methods. The conclusion reached is that, evaluation methods for e-commerce recommender systems lack full assessment of vital factors such as: user interaction, user experience and purchase decisions. A full consideration of these factors during evaluation will give birth to new types of recommender systems that predict user preferences using user decision-making process profiles, and that will enhance user experience and increase revenue in the long run.

Holistic User Context-Aware Recommender Algorithm

Mathematical Problems in Engineering

Existing recommender algorithms lack dynamism, human focus, and serendipitous recommendations. Th... more Existing recommender algorithms lack dynamism, human focus, and serendipitous recommendations. The literature indicates that the context of a user influences user decisions, and when incorporated in recommender systems (RSs), novel and serendipitous recommendations can be realized. This article shows that social, cultural, psychological, and economic contexts of a user influence user traits or decisions. The article demonstrates a novel approach of incorporating holistic user context-aware knowledge in an algorithm to solve the highlighted problems. Web content mining and collaborative filtering approaches were used to develop a holistic user context-aware (HUC) algorithm. The algorithm was evaluated on a social network using online experimental evaluations. The algorithm demonstrated dynamism, novelty, and serendipity with an average of 84% novelty and 85% serendipity.

Searching Objects in a Video Footage

International Journal of ICT Research in Africa and the Middle East

Due to the increase in video content being generated from surveillance cameras and filming, video... more Due to the increase in video content being generated from surveillance cameras and filming, videos analysis becomes imperative. Sometimes it becomes tedious to watch a video captured by a surveillance camera for hours, just to find out the desired footage. Current state of-the-art video analysis methods do not address the problem of searching and localizing a particular object in a video using the name of the object as a query and to return only a segment of the video clip showing the instances of that object. In this research the authors make use of combined implementations from existing work and also applied the dropping frames algorithm to produce a shorter, trimmed video clip showing the target object specified by the search tag. The resulting video is short and specific to the object of interest.

Human Action Prediction Using Sentiment Analysis on Social Networks

International Journal of ICT Research in Africa and the Middle East, 2017

There is a rapid increase of mass demonstrations in different locations worldwide triggered by so... more There is a rapid increase of mass demonstrations in different locations worldwide triggered by social networks discussions, as witnessed in the USA, Egypt, and South Africa. This paper challenges the underutilization of social media to detect people's' mood and to predict their actions based on their sentiments. Recent published work has demonstrated utility of sentiments on Twitter to predict outcomes of different events, so to come up with the geographical action prediction tool the authors utilized geocodes, sentiment analysis, probability theory, and logistic regression. The tool informs relevant authorities like governments to know the state of people's moods. Entities like business enterprises also benefit from this tool in their plans, especially in avoiding unnecessary costs due to infrastructure destruction.

A Characterisation and Framework for User-Centric Factors in Evaluation Methods for Recommender Systems

International Journal of ICT Research in Africa and the Middle East, 2017

Researchers have worked on-finding e-commerce recommender systems evaluation methods that contrib... more Researchers have worked on-finding e-commerce recommender systems evaluation methods that contribute to an optimal solution. However, existing evaluations methods lack the assessment of user-centric factors such as buying decisions, user experience and user interactions resulting in less than optimum recommender systems. This paper investigates the problem of adequacy of recommender systems evaluation methods in relation to user-centric factors. Published work has revealed limitations of existing evaluation methods in terms of evaluating user satisfaction. This paper characterizes user-centric evaluation factors and then propose a user-centric evaluation conceptual framework to identify and expose a gap within literature. The researchers used an integrative review approach to formulate both the characterization and the conceptual framework for investigation. The results reveal a need to come up with a holistic evaluation framework that combines system-centric and user-centric evalua...

A Cloud mining model for SMEs in E-commerce in Zimbabwe

Cloud mining is an important research topic in the field of data mining and knowledge discovery. ... more Cloud mining is an important research topic in the field of data mining and knowledge discovery. Due to the fact that a number of organizations have opted for cloud storage, it is important to use efficient and effective data mining methods to mine the large databases in the cloud so as to extract the previously unknown interesting patterns and relationships. The data patterns are of importance in business intelligence thus for forecasting, market basket analysis, cross selling, market segmentation and customer retention purposes which helps to increase the profits of business organizations. The cloud is a large repository of data units on the World Wide Web which contains social, cultural, political, educational, academic and commercial data which is usually accessed via a web browser. The data repositories can be used by all forms of business enterprises including Small and Medium Enterprises for knowledge discovery to gain business insight and intelligence. This paper seeks to investigate current cloud e-commerce systems in the world and design a model that simulates knowledge extraction for business intelligence from a cloud which store SMEs' data in Zimbabwe.

Analysing the Performance and Interpretability of CNN-Based Architectures for Plant Nutrient Deficiency Identification

Computation, Jun 3, 2024

Early detection of plant nutrient deficiency is crucial for agricultural productivity. This study... more Early detection of plant nutrient deficiency is crucial for agricultural productivity. This study investigated the performance and interpretability of Convolutional Neural Networks (CNNs) for this task. Using the rice and banana datasets, we compared three CNN architectures (CNN, VGG-16, Inception-V3). Inception-V3 achieved the highest accuracy (93% for rice and banana), but simpler models such as VGG-16 might be easier to understand. To address this trade-off, we employed Explainable AI (XAI) techniques (SHAP and Grad-CAM) to gain insights into model decision-making. This study emphasises the importance of both accuracy and interpretability in agricultural AI and demonstrates the value of XAI for building trust in these models.

Comparative Performance Analysis of Machine Learning Classifiers on COVID-19 Datasets: Exploring the Effect of Data Imputation, Cross-Validation, and Principal Component Analysis

PA-362 Towards explainable AI-based decision support in predicting SARS-CoV-2 breakthrough infections in a SSA context

Detecting the most critical clinical variables of COVID-19 breakthrough infection in vaccinated persons using machine learning

DIGITAL HEALTH

Background COVID-19 vaccines offer different levels of immune protection but do not provide 100% ... more Background COVID-19 vaccines offer different levels of immune protection but do not provide 100% protection. Vaccinated persons with pre-existing comorbidities may be at an increased risk of SARS-CoV-2 breakthrough infection or reinfection. The aim of this study is to identify the critical variables associated with a higher probability of SARS-CoV-2 breakthrough infection using machine learning. Methods A dataset comprising symptoms and feedback from 257 persons, of whom 203 were vaccinated and 54 unvaccinated, was used for the investigation. Three machine learning algorithms – Deep Multilayer Perceptron (Deep MLP), XGBoost, and Logistic Regression – were trained with the original (imbalanced) dataset and the balanced dataset created by using the Random Oversampling Technique (ROT), and the Synthetic Minority Oversampling Technique (SMOTE). We compared the performance of the classification algorithms when the features highly correlated with breakthrough infection were used and when ...

A Review of Deep Learning Models for Detecting Cyberbullying on Social Media Networks

Cybernetics Perspectives in Systems

A fraud detection tool in E-auctions

Due to rapid growth of the use of online auctions, fraudsters have taken advantage of these platf... more Due to rapid growth of the use of online auctions, fraudsters have taken advantage of these platforms to participate in their own auctions in order to raise prices (a practice called shilling). Innocent bidders have been forced to pay higher prices than they were willing to offer. This has resulted in the need to design and implement a shill detection algorithm. To eliminate this shilling problem, we designed a shilling detection algorithm integrated with an online auction. The algorithm proved to be effective and it was tested on the internet, and the short time of shill detection proved that the algorithm can work real time on e-auctions with large user base. This method can be used as a technique to eliminate shilling. Key words: E-auction, bidding, shilling, shill attributes, shill score.

A Novel, Serendipitous and Dynamic User-Centric Recommender Algorithm

Proceedings of the EAI International Conference for Research, Innovation and Development for Africa, 2018

Information filtering for web service using machine learning has recently grown widely , since in... more Information filtering for web service using machine learning has recently grown widely , since information overload has also becoming a serious problem on the World Wide Web. Recommender systems were designed to cater for this problem, but published recommender systems still fail to cope with changes of user's preferences. This paper summarizes a research that is still going on, to solve the lack of novelty, serendipity and dynamism in recommender systems. Recent research has demonstrated different methodologies to create recommender systems , unfortunately many of these which were evaluated using user-centric evaluation frameworks fall short to fulfill users' satisfaction. Therefore we propose a unique computational method to create a novel, serendipitous and dynamic recommender system. We used web content mining to gather user profiles from social media, model these profiles, and create an algorithm to suggest user preferences. The results testify that many users' social profiles for Zimbabweans dominate quite well to determine user preferences. Therefore recommender developers for developing countries, has to gather user's social profiles to predict their preferences. The main contribution is a holistic approach to model and predict dynamic user-specific preferences from categorized social media profiles namely: social, psychological, cultural, and economic profiles

Towards QR Code Health Systems Amid COVID-19: Lessons Learnt from Other QR Code Digital Technologies

Springer Series on Bio- and Neurosystems

Erratum to “Holistic User Context-Aware Recommender Algorithm”

Mathematical Problems in Engineering, 2020

<jats:p />

Successful Utilization of Technology for Knowledge Management: A Review of

While various organizations have invested in knowle dge management (KM), it is not day business. ... more While various organizations have invested in knowle dge management (KM), it is not day business. Technology plays a major role in KM, aiding in the creation, transfer, sharing and storage of knowledge, making it an integral part of KM processes. This has necessitated the need for studies into technology's involvement in KM and how it can contribute effectively to the KM objectives of the imple menting a lack of depth in the fundamental issues and concepts affecting technolog ical underlying issues are left to the implementing orga nization to figure out, there is a weak foundation upon which KM is built. The theoretical framework for technological use in KM is not solidly developed, resulting in an unstructured app roach towards technological use and implementations in KM. disciplinary nature of KM, which has led to academi cs concentrating more on certain disciplines contributing to KM, such as management and social aspects of KM, while disciplines information technology (IT) h...

A universal electronic payment model in Zimbabwe integrating with Small and Medium Enterprises and working with mobile databases

Electronic payment systems are proliferating in banking, retail in government and everywhere mone... more Electronic payment systems are proliferating in banking, retail in government and everywhere money needs to be exchanged. Electronic payment systems are the everyday technology under use, they are the relevant systems which go hand in hand with technology and they are also high in demand. All these issues enlighten a need to design and implement an electronic payment system that addresses the specific requirements for the Zimbabwean market. An effective and universal electronic payment system in Zimbabwe can solve some problems which are currently encountered in e-commerce, thus we designed a light weight electronic payment model, universal and offering better integration to banks, all merchants and Small and Medium Enterprises. It is comprised of attributes which any electronic payment system is expected to have. It has its own security features especially the offline authentication method and other security aspects which are currently in use by banks. The integrated architectural ...

African Journal of Mathematics and Computer Science Research, Jan 31, 2016

Due to rapid growth of the use of online auctions, fraudsters have taken advantage of these platf... more Due to rapid growth of the use of online auctions, fraudsters have taken advantage of these platforms to participate in their own auctions in order to raise prices (a practice called shilling). Innocent bidders have been forced to pay higher prices than they were willing to offer. This has resulted in the need to design and implement a shill detection algorithm. To eliminate this shilling problem, we designed a shilling detection algorithm integrated with an online auction. The algorithm proved to be effective and it was tested on the internet, and the short time of shill detection proved that the algorithm can work real time on e-auctions with large user base. This method can be used as a technique to eliminate shilling.

A Novel, Serendipitous and Dynamic User-Centric Recommender Algorithm

Information filtering for web service using machine learning has recently grown widely , since in... more Information filtering for web service using machine learning has recently grown widely , since information overload has also becoming a serious problem on the World Wide Web. Recommender systems were designed to cater for this problem, but published recommender systems still fail to cope with changes of user's preferences. This paper summarizes a research that is still going on, to solve the lack of novelty, serendipity and dynamism in recommender systems. Recent research has demonstrated different methodologies to create recommender systems , unfortunately many of these which were evaluated using user-centric evaluation frameworks fall short to fulfill users' satisfaction. Therefore we propose a unique computational method to create a novel, serendipitous and dynamic recommender system. We used web content mining to gather user profiles from social media, model these profiles, and create an algorithm to suggest user preferences. The results testify that many users' social profiles for Zimbabweans dominate quite well to determine user preferences. Therefore recommender developers for developing countries, has to gather user's social profiles to predict their preferences. The main contribution is a holistic approach to model and predict dynamic user-specific preferences from categorized social media profiles namely: social, psychological, cultural, and economic profiles

Characterisation of User-Contexts for Context-Aware Recommendation Systems

Proceedings of the Future Technologies Conference (FTC) 2021, Volume 1

A Characterisation and Framework for User-Centric Factors in Evaluation Methods for Recommender Systems

International Journal of ICT Research in Africa and the Middle East, 2017

Researchers have worked on-finding e-commerce recommender systems evaluation methods that contrib... more Researchers have worked on-finding e-commerce recommender systems evaluation methods that contribute to an optimal solution. However, existing evaluations methods lack the assessment of user-centric factors such as buying decisions, user experience and user interactions resulting in less than optimum recommender systems. This paper investigates the problem of adequacy of recommender systems evaluation methods in relation to user-centric factors. Published work has revealed limitations of existing evaluation methods in terms of evaluating user satisfaction. This paper characterizes user-centric evaluation factors and then propose a user-centric evaluation conceptual framework to identify and expose a gap within literature. The researchers used an integrative review approach to formulate both the characterization and the conceptual framework for investigation. The results reveal a need to come up with a holistic evaluation framework that combines system-centric and user-centric evaluation methods as well as formulating computational user-centric evaluation methods. The conclusion reached is that, evaluation methods for e-commerce recommender systems lack full assessment of vital factors such as: user interaction, user experience and purchase decisions. A full consideration of these factors during evaluation will give birth to new types of recommender systems that predict user preferences using user decision-making process profiles, and that will enhance user experience and increase revenue in the long run.

Holistic User Context-Aware Recommender Algorithm

Mathematical Problems in Engineering

Existing recommender algorithms lack dynamism, human focus, and serendipitous recommendations. Th... more Existing recommender algorithms lack dynamism, human focus, and serendipitous recommendations. The literature indicates that the context of a user influences user decisions, and when incorporated in recommender systems (RSs), novel and serendipitous recommendations can be realized. This article shows that social, cultural, psychological, and economic contexts of a user influence user traits or decisions. The article demonstrates a novel approach of incorporating holistic user context-aware knowledge in an algorithm to solve the highlighted problems. Web content mining and collaborative filtering approaches were used to develop a holistic user context-aware (HUC) algorithm. The algorithm was evaluated on a social network using online experimental evaluations. The algorithm demonstrated dynamism, novelty, and serendipity with an average of 84% novelty and 85% serendipity.

Searching Objects in a Video Footage

International Journal of ICT Research in Africa and the Middle East

Due to the increase in video content being generated from surveillance cameras and filming, video... more Due to the increase in video content being generated from surveillance cameras and filming, videos analysis becomes imperative. Sometimes it becomes tedious to watch a video captured by a surveillance camera for hours, just to find out the desired footage. Current state of-the-art video analysis methods do not address the problem of searching and localizing a particular object in a video using the name of the object as a query and to return only a segment of the video clip showing the instances of that object. In this research the authors make use of combined implementations from existing work and also applied the dropping frames algorithm to produce a shorter, trimmed video clip showing the target object specified by the search tag. The resulting video is short and specific to the object of interest.

Human Action Prediction Using Sentiment Analysis on Social Networks

International Journal of ICT Research in Africa and the Middle East, 2017

There is a rapid increase of mass demonstrations in different locations worldwide triggered by so... more There is a rapid increase of mass demonstrations in different locations worldwide triggered by social networks discussions, as witnessed in the USA, Egypt, and South Africa. This paper challenges the underutilization of social media to detect people's' mood and to predict their actions based on their sentiments. Recent published work has demonstrated utility of sentiments on Twitter to predict outcomes of different events, so to come up with the geographical action prediction tool the authors utilized geocodes, sentiment analysis, probability theory, and logistic regression. The tool informs relevant authorities like governments to know the state of people's moods. Entities like business enterprises also benefit from this tool in their plans, especially in avoiding unnecessary costs due to infrastructure destruction.

A Characterisation and Framework for User-Centric Factors in Evaluation Methods for Recommender Systems

International Journal of ICT Research in Africa and the Middle East, 2017

Researchers have worked on-finding e-commerce recommender systems evaluation methods that contrib... more Researchers have worked on-finding e-commerce recommender systems evaluation methods that contribute to an optimal solution. However, existing evaluations methods lack the assessment of user-centric factors such as buying decisions, user experience and user interactions resulting in less than optimum recommender systems. This paper investigates the problem of adequacy of recommender systems evaluation methods in relation to user-centric factors. Published work has revealed limitations of existing evaluation methods in terms of evaluating user satisfaction. This paper characterizes user-centric evaluation factors and then propose a user-centric evaluation conceptual framework to identify and expose a gap within literature. The researchers used an integrative review approach to formulate both the characterization and the conceptual framework for investigation. The results reveal a need to come up with a holistic evaluation framework that combines system-centric and user-centric evalua...

A Cloud mining model for SMEs in E-commerce in Zimbabwe

Cloud mining is an important research topic in the field of data mining and knowledge discovery. ... more Cloud mining is an important research topic in the field of data mining and knowledge discovery. Due to the fact that a number of organizations have opted for cloud storage, it is important to use efficient and effective data mining methods to mine the large databases in the cloud so as to extract the previously unknown interesting patterns and relationships. The data patterns are of importance in business intelligence thus for forecasting, market basket analysis, cross selling, market segmentation and customer retention purposes which helps to increase the profits of business organizations. The cloud is a large repository of data units on the World Wide Web which contains social, cultural, political, educational, academic and commercial data which is usually accessed via a web browser. The data repositories can be used by all forms of business enterprises including Small and Medium Enterprises for knowledge discovery to gain business insight and intelligence. This paper seeks to investigate current cloud e-commerce systems in the world and design a model that simulates knowledge extraction for business intelligence from a cloud which store SMEs' data in Zimbabwe.