With the rapid use of social media for marketing purposes, a secure online transaction platform on social networking sites has become a serious concern to ensure secure transactions without any fear of privacy breaches. Social media is usually overwhelmed with cases of data breaches or threats to the security of users in terms of secure online transactions. Unfortunately, the factors for enhancing security when transacting on social networks are yet to be fully understood. This paper intends to identify the challenges and risks associated with social media transactions and to propose social media customer-to-customer secure online transaction strategies. To achieve the objective of this paper, quantitative data was collected from a sample of 225 adults in Windhoek, Namibia, using the cluster sampling technique. The research findings reflected that trust, privacy, risk, and security issues still need to be resolved to assure a secure customer-to-customer social media transaction platform.
{"title":"Security Concerns on Social Media Customer-to-Customer Online Transactions. A Case of Namibia Facebook Users","authors":"Knowledge Rusere, Stanford Musarurwa, Fungai Bhunu Shava, Munyaradzi Maravanyika","doi":"10.23919/IST-Africa56635.2022.9845558","DOIUrl":"https://doi.org/10.23919/IST-Africa56635.2022.9845558","url":null,"abstract":"With the rapid use of social media for marketing purposes, a secure online transaction platform on social networking sites has become a serious concern to ensure secure transactions without any fear of privacy breaches. Social media is usually overwhelmed with cases of data breaches or threats to the security of users in terms of secure online transactions. Unfortunately, the factors for enhancing security when transacting on social networks are yet to be fully understood. This paper intends to identify the challenges and risks associated with social media transactions and to propose social media customer-to-customer secure online transaction strategies. To achieve the objective of this paper, quantitative data was collected from a sample of 225 adults in Windhoek, Namibia, using the cluster sampling technique. The research findings reflected that trust, privacy, risk, and security issues still need to be resolved to assure a secure customer-to-customer social media transaction platform.","PeriodicalId":142887,"journal":{"name":"2022 IST-Africa Conference (IST-Africa)","volume":"51 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124844511","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-05-16DOI: 10.23919/IST-Africa56635.2022.9845602
Raeesa Behardien, I. Brown
The adoption of smartphones is increasing exponentially and with this, comes fears of security related threats. Many of these threats aim to manipulate or steal personal electronic information, and the ignorance of the user towards these threats increases the consequences that arise due to these threats. This study investigates the factors that influence end-user smartphone security behaviour. Using a quantitative study of 140 participants, factors are measured and analysed to identify those that have the strongest influence on end-user smartphone security behaviour. The findings of this study show that end-user smartphone security behaviour is influenced by the user’s awareness of smartphone security, the user’s IT sophistication which represents their ability to protect themselves from a security threat and lastly, the trust the user has in society and people in general.
{"title":"Factors Influencing Smartphone End-User Security Behaviour – The Case of Young Adults in South Africa","authors":"Raeesa Behardien, I. Brown","doi":"10.23919/IST-Africa56635.2022.9845602","DOIUrl":"https://doi.org/10.23919/IST-Africa56635.2022.9845602","url":null,"abstract":"The adoption of smartphones is increasing exponentially and with this, comes fears of security related threats. Many of these threats aim to manipulate or steal personal electronic information, and the ignorance of the user towards these threats increases the consequences that arise due to these threats. This study investigates the factors that influence end-user smartphone security behaviour. Using a quantitative study of 140 participants, factors are measured and analysed to identify those that have the strongest influence on end-user smartphone security behaviour. The findings of this study show that end-user smartphone security behaviour is influenced by the user’s awareness of smartphone security, the user’s IT sophistication which represents their ability to protect themselves from a security threat and lastly, the trust the user has in society and people in general.","PeriodicalId":142887,"journal":{"name":"2022 IST-Africa Conference (IST-Africa)","volume":"65 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125896319","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-05-16DOI: 10.23919/IST-Africa56635.2022.9845657
Lorna Mugambi, L. Zühlke, C. Maina
Rheumatic Heart Disease is a cardiovascular disease highly prevalent in developing countries partially because of inadequate healthcare infrastructure to treat Group A streptococcus pharyngitis and thereafter diagnose and document every case of Acute Rheumatic Fever, the immune-mediated antecedent of rheumatic heart disease. Secondary antibiotic treatment with penicillin injections after a diagnosis of Acute Rheumatic Fever and Rheumatic Heart Disease is used to prevent further attacks of Strep A, preferably prior to any heart valve damage. Echocardiographic screening for early detection of Rheumatic Heart Disease has been proposed as a method to improve outcomes but it is time-consuming, costly and few people are skilled enough to reach a correct diagnosis. Machine Learning is an emerging tool in analysing medical images; our aim is to automate the screening process of diagnosing rheumatic heart disease. In this paper, we present a web application to be used to label echocardiography data. These labelled data can then be used to develop machine learning models that can classify echocardiographic views of the heart and damaged valves from the echocardiograms.
{"title":"Towards AI Based Diagnosis of Rheumatic Heart Disease: Data Annotation and View Classification","authors":"Lorna Mugambi, L. Zühlke, C. Maina","doi":"10.23919/IST-Africa56635.2022.9845657","DOIUrl":"https://doi.org/10.23919/IST-Africa56635.2022.9845657","url":null,"abstract":"Rheumatic Heart Disease is a cardiovascular disease highly prevalent in developing countries partially because of inadequate healthcare infrastructure to treat Group A streptococcus pharyngitis and thereafter diagnose and document every case of Acute Rheumatic Fever, the immune-mediated antecedent of rheumatic heart disease. Secondary antibiotic treatment with penicillin injections after a diagnosis of Acute Rheumatic Fever and Rheumatic Heart Disease is used to prevent further attacks of Strep A, preferably prior to any heart valve damage. Echocardiographic screening for early detection of Rheumatic Heart Disease has been proposed as a method to improve outcomes but it is time-consuming, costly and few people are skilled enough to reach a correct diagnosis. Machine Learning is an emerging tool in analysing medical images; our aim is to automate the screening process of diagnosing rheumatic heart disease. In this paper, we present a web application to be used to label echocardiography data. These labelled data can then be used to develop machine learning models that can classify echocardiographic views of the heart and damaged valves from the echocardiograms.","PeriodicalId":142887,"journal":{"name":"2022 IST-Africa Conference (IST-Africa)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122364357","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-05-16DOI: 10.23919/IST-Africa56635.2022.9845582
K. Charvát, Dmitrij Kozhukh, M. Kepka, P. Hájek, Herman Snevajs, M. Kollerová, Hana Kubícková, Tuula Löytty, Ronald Ssembajwe, Akaninyene Obot, Antoine Kantiza, Shadrack Stephene, G. Ravid, E. Gelb
Land use and land cover information in combination with other thematic datasets related to detailed reference spatial data in localities from an important dataset for different types of analyses in different domains. At the time being, when it comes to the strategy of the SDG, Green Deal, Destination Earth, and construction of Earth’s digital twins, there is no model and database that would effectively gather information about the Earth’s surface in sufficient detail and complex relations. The situation is much worse in Africa compared to Europe since there exist only scattered map layers from public sources across all Africa like Africover and CCI Land Cover 2016. Moreover, the other close option ‘OpenStreetMap’ with a continent-wide coverage collects data on a voluntary basis with minimal attributes. For this reason, it’s prudent to provide validation and harmonisation of this data. Therefore, there was a focus on developing and optimising a new solution based on the Open Land Use (OLU) 2.0 data model. The OLU 2.0 database combined various thematic data with the most detailed reference geometry available. Thematic datasets were focused primarily on the information of land use and land cover and additionally on other themes like soil, topographic characteristics, climatic parameters, data from classification of remote sensing data, vegetation indices of field blocks, etc. and in different time periods. In this way, OLU4Africa 2.0 defined a model which can have large potential in Africa for high-end applications such as food security modelling; environment, biodiversity, and ecosystem protection; planning purposes; forest and water protection. It is worth mentioning that the OLU4Africa 2.0 application has been nominated among WSIS Prizes 2022.
土地利用和土地覆盖信息与来自重要数据集的其他专题数据集相关的地方详细参考空间数据相结合，用于不同领域的不同类型分析。目前，在可持续发展目标战略、绿色协议、目的地地球和地球数字孪生体建设方面，还没有一个模型和数据库能够有效地收集到足够详细和复杂关系的地球表面信息。与欧洲相比，非洲的情况要糟糕得多，因为整个非洲只有来自公共资源的分散地图层，比如Africover和CCI Land Cover 2016。此外，另一个封闭的选项“开放街道地图”(OpenStreetMap)覆盖整个大陆，在自愿的基础上以最小的属性收集数据。出于这个原因，提供这些数据的验证和协调是谨慎的。因此，重点是开发和优化基于开放土地使用(OLU) 2.0数据模型的新解决方案。OLU 2.0数据库将各种主题数据与最详细的参考几何图形结合在一起。专题数据集主要集中于土地利用和土地覆盖信息，此外还包括土壤、地形特征、气候参数、遥感数据分类数据、野外块体植被指数等不同时间段的专题数据。通过这种方式，OLU4Africa 2.0定义了一个模型，该模型在非洲具有很大的高端应用潜力，例如粮食安全模型;环境、生物多样性和生态系统保护;规划目的;保护森林和水。值得一提的是，OLU4Africa 2.0应用程序已被提名为2022年WSIS奖项。
{"title":"Optimization of African LULC Database for Sustainable Development","authors":"K. Charvát, Dmitrij Kozhukh, M. Kepka, P. Hájek, Herman Snevajs, M. Kollerová, Hana Kubícková, Tuula Löytty, Ronald Ssembajwe, Akaninyene Obot, Antoine Kantiza, Shadrack Stephene, G. Ravid, E. Gelb","doi":"10.23919/IST-Africa56635.2022.9845582","DOIUrl":"https://doi.org/10.23919/IST-Africa56635.2022.9845582","url":null,"abstract":"Land use and land cover information in combination with other thematic datasets related to detailed reference spatial data in localities from an important dataset for different types of analyses in different domains. At the time being, when it comes to the strategy of the SDG, Green Deal, Destination Earth, and construction of Earth’s digital twins, there is no model and database that would effectively gather information about the Earth’s surface in sufficient detail and complex relations. The situation is much worse in Africa compared to Europe since there exist only scattered map layers from public sources across all Africa like Africover and CCI Land Cover 2016. Moreover, the other close option ‘OpenStreetMap’ with a continent-wide coverage collects data on a voluntary basis with minimal attributes. For this reason, it’s prudent to provide validation and harmonisation of this data. Therefore, there was a focus on developing and optimising a new solution based on the Open Land Use (OLU) 2.0 data model. The OLU 2.0 database combined various thematic data with the most detailed reference geometry available. Thematic datasets were focused primarily on the information of land use and land cover and additionally on other themes like soil, topographic characteristics, climatic parameters, data from classification of remote sensing data, vegetation indices of field blocks, etc. and in different time periods. In this way, OLU4Africa 2.0 defined a model which can have large potential in Africa for high-end applications such as food security modelling; environment, biodiversity, and ecosystem protection; planning purposes; forest and water protection. It is worth mentioning that the OLU4Africa 2.0 application has been nominated among WSIS Prizes 2022.","PeriodicalId":142887,"journal":{"name":"2022 IST-Africa Conference (IST-Africa)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129089709","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-05-16DOI: 10.23919/IST-Africa56635.2022.9845531
T. Mafugu
The study sought to evaluate the effect of online group presentations on the development of pre-service teachers’ pedagogical and assessment skills. The study involved students undertaking the postgraduate Certificate of Education in science course during the COVID-19 pandemic. The study was underpinned by a cross-sectional survey design. Students worked in groups of five to present micro-lessons and assess each other using a rubric prepared by the researcher. In each group, four peers independently assessed each student, and an average mark was calculated. Discussions between students on the strengths and weaknesses of the presentation were held. The researchers moderated the average marks by evaluating the presentations submitted by the students using the same rubric. The researcher gave feedback, highlighting the strengths of the presentations and areas that needed some improvement. Most of the students were of the view that group presentations improved their pedagogical skills and assessment practices. The study recommends the implementation of similar group presentations before teaching practice, as this would help them teach better in the schools.
{"title":"Constructivist Learning during the COVD-19 Pandemic: Teaching and Assessment Skills in a Post Graduate Certificate of Education Students","authors":"T. Mafugu","doi":"10.23919/IST-Africa56635.2022.9845531","DOIUrl":"https://doi.org/10.23919/IST-Africa56635.2022.9845531","url":null,"abstract":"The study sought to evaluate the effect of online group presentations on the development of pre-service teachers’ pedagogical and assessment skills. The study involved students undertaking the postgraduate Certificate of Education in science course during the COVID-19 pandemic. The study was underpinned by a cross-sectional survey design. Students worked in groups of five to present micro-lessons and assess each other using a rubric prepared by the researcher. In each group, four peers independently assessed each student, and an average mark was calculated. Discussions between students on the strengths and weaknesses of the presentation were held. The researchers moderated the average marks by evaluating the presentations submitted by the students using the same rubric. The researcher gave feedback, highlighting the strengths of the presentations and areas that needed some improvement. Most of the students were of the view that group presentations improved their pedagogical skills and assessment practices. The study recommends the implementation of similar group presentations before teaching practice, as this would help them teach better in the schools.","PeriodicalId":142887,"journal":{"name":"2022 IST-Africa Conference (IST-Africa)","volume":"240 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121192079","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-05-16DOI: 10.23919/IST-Africa56635.2022.9845553
J. Osakwe, G. Iyawa, M. Ujakpa, Teresia Ankome
Universities across the world use different policies in data collection thus, some have different ways of using Learning Analytics (LA) to assist in improving students’ performance. The purpose of this paper was to investigate the perceptions of LA as a tool for enhancing students’ performance. 1,395 lecturers in 12 countries, spread through 5 continents participated in the survey picked randomly to ensure diversity in this research. The findings revealed that the majority of the lecturers are aware of LA and their institutions use a variety of LA tools. The study also found that most lecturers use these novative tools in their institutions. However, there are challenges such as skills development, incompatible institutional policies and lack of resources, which hindered the full implementation and use of LA tools in higher educational institutions.
{"title":"Learning Analytics Tools for Enhancing Students’ Performance: A Global Perspective","authors":"J. Osakwe, G. Iyawa, M. Ujakpa, Teresia Ankome","doi":"10.23919/IST-Africa56635.2022.9845553","DOIUrl":"https://doi.org/10.23919/IST-Africa56635.2022.9845553","url":null,"abstract":"Universities across the world use different policies in data collection thus, some have different ways of using Learning Analytics (LA) to assist in improving students’ performance. The purpose of this paper was to investigate the perceptions of LA as a tool for enhancing students’ performance. 1,395 lecturers in 12 countries, spread through 5 continents participated in the survey picked randomly to ensure diversity in this research. The findings revealed that the majority of the lecturers are aware of LA and their institutions use a variety of LA tools. The study also found that most lecturers use these novative tools in their institutions. However, there are challenges such as skills development, incompatible institutional policies and lack of resources, which hindered the full implementation and use of LA tools in higher educational institutions.","PeriodicalId":142887,"journal":{"name":"2022 IST-Africa Conference (IST-Africa)","volume":"62 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116280454","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-05-16DOI: 10.23919/IST-Africa56635.2022.9845609
Katazo N. Amunkete, J. Osakwe
Online stores offer various conveniences such as allowing people to shop from the comfort of their homes, using a multitude of devices such as mobile phones. People living with disabilities should also be able to enjoy the conveniences that come with online stores. The purpose of this study was to determine whether web accessibility guidelines, that allow people living with disabilities to navigate easier on websites, have been implemented on Namibian online stores. Another objective of the study was to determine whether the owners of the online stores are familiar with web accessibility and assistive technologies. A case study was undertaken, using 7 online stores as cases. The cases were purposively selected. Three of the 7 online stores participated in a qualitative interview. It was found that the online stores had some features that provided for accessibility and that were compatible with assistive technologies but there were also some features lacking that would make the stores more accessible. The site owners additionally showed a low-level understanding of what web accessibility and assistive technologies are. The study calls for the inclusivity of people living with disabilities in using and navigating Namibian online stores.
{"title":"Accessibility Friendly? A Case of Namibian Online Stores","authors":"Katazo N. Amunkete, J. Osakwe","doi":"10.23919/IST-Africa56635.2022.9845609","DOIUrl":"https://doi.org/10.23919/IST-Africa56635.2022.9845609","url":null,"abstract":"Online stores offer various conveniences such as allowing people to shop from the comfort of their homes, using a multitude of devices such as mobile phones. People living with disabilities should also be able to enjoy the conveniences that come with online stores. The purpose of this study was to determine whether web accessibility guidelines, that allow people living with disabilities to navigate easier on websites, have been implemented on Namibian online stores. Another objective of the study was to determine whether the owners of the online stores are familiar with web accessibility and assistive technologies. A case study was undertaken, using 7 online stores as cases. The cases were purposively selected. Three of the 7 online stores participated in a qualitative interview. It was found that the online stores had some features that provided for accessibility and that were compatible with assistive technologies but there were also some features lacking that would make the stores more accessible. The site owners additionally showed a low-level understanding of what web accessibility and assistive technologies are. The study calls for the inclusivity of people living with disabilities in using and navigating Namibian online stores.","PeriodicalId":142887,"journal":{"name":"2022 IST-Africa Conference (IST-Africa)","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121750713","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-05-16DOI: 10.23919/IST-Africa56635.2022.9845628
Yves Bizumuremyi, N. Mabanza, M. Masinde
Missionary services have contributed to the development of many communities worldwide. However, many of these valuable services remain invisible to people who need them because of a lack of easily accessible information about these services. This complex issue can be solved by bringing all missionary services together on a single digital platform. However, the fact that data in such platforms is stored in the cloud, can cause privacy breaches of sensitive information. On the other hand, blockchain technology is predicted to be the main driver of the next-generation digital platforms. This paper investigates if the implementation of Blockchain Technology for data security could accelerate the adoption and use of digital platforms for missionary services. Such implementation would, however, require being backed by up-to-date current trends, concerns, and ongoing research in the field of blockchain technology and data security. This is the gap that this paper intends to fill through a bibliometric analysis of scientific publications made from 2016 to 2021.
{"title":"Bibliometric Analysis of the Application of Blockchain Technology for Data Security: a Case Study of Global Mission Services’ Digital Platform","authors":"Yves Bizumuremyi, N. Mabanza, M. Masinde","doi":"10.23919/IST-Africa56635.2022.9845628","DOIUrl":"https://doi.org/10.23919/IST-Africa56635.2022.9845628","url":null,"abstract":"Missionary services have contributed to the development of many communities worldwide. However, many of these valuable services remain invisible to people who need them because of a lack of easily accessible information about these services. This complex issue can be solved by bringing all missionary services together on a single digital platform. However, the fact that data in such platforms is stored in the cloud, can cause privacy breaches of sensitive information. On the other hand, blockchain technology is predicted to be the main driver of the next-generation digital platforms. This paper investigates if the implementation of Blockchain Technology for data security could accelerate the adoption and use of digital platforms for missionary services. Such implementation would, however, require being backed by up-to-date current trends, concerns, and ongoing research in the field of blockchain technology and data security. This is the gap that this paper intends to fill through a bibliometric analysis of scientific publications made from 2016 to 2021.","PeriodicalId":142887,"journal":{"name":"2022 IST-Africa Conference (IST-Africa)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131571460","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-05-16DOI: 10.23919/IST-Africa56635.2022.9845618
Boago Okgetheng, Emmanuella Budu
Language identification of text has become increasingly important as large quantities of text are processed or filtered automatically. It is one of the preprocessing steps in Natural Language Processing (NLP) tasks such as information retrieval and machine translation. Few studies have worked on Bantu Languages in automatic language identification. Language identification is a challenge in Bantu languages because of lack of data and in addition to that, languages which are written similarly like Setswana and Sesotho are also challenging. In this paper, we present a word-based Naïve Bayes classifier to identify words of Sesotho and Setswana language. The classifier was trained with words from both Setswana and Sesotho in a supervised manner. Adjectives, pronouns, adverbs and enumeratives are also included. The classifier shows that the two languages can be individually identified as it gives an accuracy of 71.4%. Despite that when we increase the data to double the number of words, the model increased performance to 78%. We also report that the classifier fails with homographs. The performance could be improved by using more data. Additionally, the syllable identification and sentence identification could be implemented along with word-based classifier.
{"title":"Word-Based Bantu Language Identification using Naïve Bayes","authors":"Boago Okgetheng, Emmanuella Budu","doi":"10.23919/IST-Africa56635.2022.9845618","DOIUrl":"https://doi.org/10.23919/IST-Africa56635.2022.9845618","url":null,"abstract":"Language identification of text has become increasingly important as large quantities of text are processed or filtered automatically. It is one of the preprocessing steps in Natural Language Processing (NLP) tasks such as information retrieval and machine translation. Few studies have worked on Bantu Languages in automatic language identification. Language identification is a challenge in Bantu languages because of lack of data and in addition to that, languages which are written similarly like Setswana and Sesotho are also challenging. In this paper, we present a word-based Naïve Bayes classifier to identify words of Sesotho and Setswana language. The classifier was trained with words from both Setswana and Sesotho in a supervised manner. Adjectives, pronouns, adverbs and enumeratives are also included. The classifier shows that the two languages can be individually identified as it gives an accuracy of 71.4%. Despite that when we increase the data to double the number of words, the model increased performance to 78%. We also report that the classifier fails with homographs. The performance could be improved by using more data. Additionally, the syllable identification and sentence identification could be implemented along with word-based classifier.","PeriodicalId":142887,"journal":{"name":"2022 IST-Africa Conference (IST-Africa)","volume":"89 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133211027","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-05-16DOI: 10.23919/IST-Africa56635.2022.9845660
A. Khoda, J. Njenga
Although mobile phone penetration in Kenya stands at 132.2%, mHealth uptake in rural regions is significantly low. This paper evaluates factors of mHealth adoption by analysing diverse behavioural change theories from social, technology and health backgrounds. A quantitative research approach was used to collect data from a random sample of 315 respondents in Nyatoto sub-county of Western Kenya. The results show that the most significant contributor to mHealth adoption was the ease of using mHealth technology as perceived by the potential user. Besides, disease threat in terms of its severity and susceptibility informed the perceived usefulness of mHealth technology. Individual’s age, literacy in the language used to deliver healthcare information, social influence by the significant peers, and the perceived usefulness of the mHealth technology jointly affected the user’s perceived ease of using the mHealth technology. The findings from this research may guide successful mHealth deployment in rural settings.
{"title":"mHealth Enablers and Inhibitors in a Rural Poor Setting","authors":"A. Khoda, J. Njenga","doi":"10.23919/IST-Africa56635.2022.9845660","DOIUrl":"https://doi.org/10.23919/IST-Africa56635.2022.9845660","url":null,"abstract":"Although mobile phone penetration in Kenya stands at 132.2%, mHealth uptake in rural regions is significantly low. This paper evaluates factors of mHealth adoption by analysing diverse behavioural change theories from social, technology and health backgrounds. A quantitative research approach was used to collect data from a random sample of 315 respondents in Nyatoto sub-county of Western Kenya. The results show that the most significant contributor to mHealth adoption was the ease of using mHealth technology as perceived by the potential user. Besides, disease threat in terms of its severity and susceptibility informed the perceived usefulness of mHealth technology. Individual’s age, literacy in the language used to deliver healthcare information, social influence by the significant peers, and the perceived usefulness of the mHealth technology jointly affected the user’s perceived ease of using the mHealth technology. The findings from this research may guide successful mHealth deployment in rural settings.","PeriodicalId":142887,"journal":{"name":"2022 IST-Africa Conference (IST-Africa)","volume":"29 2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125694095","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：