Because the development of resources in any language is an expensive process, many languages, including the indigenous languages of South Africa, can be classified as being resource scarce, or lacking in tagging resources. This study investigates and applies techniques and methodologies for optimising the use of available resources and improving the accuracy of a tagger using Afrikaans as resource-scarce language and aims to i) determine whether combination techniques can be effectively applied to improve the accuracy of a tagger for Afrikaans, and ii) determine whether structural semi-supervised learning can be effectively applied to improve the accuracy of a supervised learning tagger for Afrikaans. In order to realise the first aim, existing methodologies for combining classification algorithms are investigated. Four taggers, trained using MBT, SVMlight, MXPOST and TnT respectively, are then combined into a combination tagger using weighted voting. Weights are calculated by means of total precision, tag precision and a combination of precision and recall. Although the combination of taggers does not consistently lead to an error rate reduction with regard to the baseline, it manages to achieve an error rate reduction of up to 18.48% in some cases. In order to realise the second aim, existing semi-supervised learning algorithms, with specific focus on structural semi-supervised learning, are investigated. Structural semi-supervised learning is implemented by means of the SVD-ASO-algorithm, which attempts to extract the shared structure of untagged data using auxiliary problems before training a tagger. The use of untagged data during the training of a tagger leads to an error rate reduction with regard to the baseline of 1.67%. Even though the error rate reduction does not prove to be statistically significant in all cases, the results show that it is possible to improve the accuracy in some cases. / MSc (Computer Science), North-West University, Potchefstroom Campus, 2015

Because the development of resources in any language is an expensive process, many languages, including the indigenous languages of South Africa, can be classified as being resource scarce, or lacking in tagging resources. This study investigates and applies techniques and methodologies for optimising the use of available resources and improving the accuracy of a tagger using Afrikaans as resource-scarce language and aims to i) determine whether combination techniques can be effectively applied to improve the accuracy of a tagger for Afrikaans, and ii) determine whether structural semi-supervised learning can be effectively applied to improve the accuracy of a supervised learning tagger for Afrikaans. In order to realise the first aim, existing methodologies for combining classification algorithms are investigated. Four taggers, trained using MBT, SVMlight, MXPOST and TnT respectively, are then combined into a combination tagger using weighted voting. Weights are calculated by means of total precision, tag precision and a combination of precision and recall. Although the combination of taggers does not consistently lead to an error rate reduction with regard to the baseline, it manages to achieve an error rate reduction of up to 18.48% in some cases. In order to realise the second aim, existing semi-supervised learning algorithms, with specific focus on structural semi-supervised learning, are investigated. Structural semi-supervised learning is implemented by means of the SVD-ASO-algorithm, which attempts to extract the shared structure of untagged data using auxiliary problems before training a tagger. The use of untagged data during the training of a tagger leads to an error rate reduction with regard to the baseline of 1.67%. Even though the error rate reduction does not prove to be statistically significant in all cases, the results show that it is possible to improve the accuracy in some cases. / MSc (Computer Science), North-West University, Potchefstroom Campus, 2015

The aim of this study is to investigate whether a combination of agile system development methodologies (ASDMs) and project management methodologies (PMMs) can be used to develop a hybrid APMM that will have the ability to deliver information technology (IT) projects successfully in a constantly changing business and project environment. To achieve this objective, a literature review was conducted on the relatively well–established ASDMs by firstly defining a SDM and an ASDM. Each ASDM and its effectiveness are described, after which ASDMs in general are evaluated by considering their area of application, advantages and disadvantages. A comparison is then done of the seven different ASDMs using the four elements of an SDM (Huisman & Iivari, 2006:32) to emphasise some of the main similarities and differences amongst the different ASDMs. The seven ASDMs investigated in this study are Dynamic System Development Methodology, Scrum, Extreme Programming, Feature Driven Development, Crystal ASDMs ? Crystal Clear and Crystal Orange in particular, Adaptive Software Development and Lean Development. A literature review was also conducted on two structured and relatively well–established PMMs, PMBOK and PRINCE2, and a relatively new PMM called Agile Project Management. Each PMM is evaluated by considering their area of application, advantages, disadvantages and integration with other methodologies, after which a comparison is made of the different PMMs. The research was conducted by following a mixed methods research plan, which included the mixed methods research paradigm (combination of the interpretive research paradigm and the positivistic research paradigm), research methods (design science, case study and survey), quantitative and qualitative data–collection techniques (interviews and questionnaires), and dataanalysis techniques (cross–case and statistical). The reasons that projects fail and critical project success factors were studied and summarised to form the critical project success criteria, which were used to create the agile project success criteria. The ASDM best practice and PMM best practice frameworks were created by identifying whether a certain ASDM or PMM would satisfy a specific agile project success factor (APSF) of the agile project success criteria. The findings of each APSF in the respective frameworks were used as a foundation to develop a hybrid APMM (ver. 0) that would address the agile project success criteria. The hybrid APMM (ver. 0) was developed interpretively using design science (research approach) and constructivism by combining the strengths, addressing the weaknesses and bridging the gaps identified in the frameworks. The hybrid APMM (ver. 0) was then evaluated and improved by conducting an interpretive case study, which entailed interviewing participants from large and small organisations. Once the qualitative data collected had been analysed using cross–case analysis, the findings were incorporated in order to create an improved hybrid APMM (ver. 1). The hybrid APMM (ver. 1) too was evaluated and improved by conducting a survey, which entailed administering questionnaires to various respondents in order to collect quantitative and qualitative data. The findings of the statistical analysis of the data were also used to improve the hybrid APMM (ver. 1), resulting in the final hybrid APMM (ver. 2). This study demonstrates that a combination of ASDMs and PMMs can be used to develop a hybrid APMM with the ability to deliver IT projects in a constantly changing project and business environment. / Thesis (Ph.D. (Computer Science))--North-West University, Potchefstroom Campus, 2012.

The aim of this study is to investigate whether a combination of agile system development methodologies (ASDMs) and project management methodologies (PMMs) can be used to develop a hybrid APMM that will have the ability to deliver information technology (IT) projects successfully in a constantly changing business and project environment. To achieve this objective, a literature review was conducted on the relatively well–established ASDMs by firstly defining a SDM and an ASDM. Each ASDM and its effectiveness are described, after which ASDMs in general are evaluated by considering their area of application, advantages and disadvantages. A comparison is then done of the seven different ASDMs using the four elements of an SDM (Huisman & Iivari, 2006:32) to emphasise some of the main similarities and differences amongst the different ASDMs. The seven ASDMs investigated in this study are Dynamic System Development Methodology, Scrum, Extreme Programming, Feature Driven Development, Crystal ASDMs ? Crystal Clear and Crystal Orange in particular, Adaptive Software Development and Lean Development. A literature review was also conducted on two structured and relatively well–established PMMs, PMBOK and PRINCE2, and a relatively new PMM called Agile Project Management. Each PMM is evaluated by considering their area of application, advantages, disadvantages and integration with other methodologies, after which a comparison is made of the different PMMs. The research was conducted by following a mixed methods research plan, which included the mixed methods research paradigm (combination of the interpretive research paradigm and the positivistic research paradigm), research methods (design science, case study and survey), quantitative and qualitative data–collection techniques (interviews and questionnaires), and dataanalysis techniques (cross–case and statistical). The reasons that projects fail and critical project success factors were studied and summarised to form the critical project success criteria, which were used to create the agile project success criteria. The ASDM best practice and PMM best practice frameworks were created by identifying whether a certain ASDM or PMM would satisfy a specific agile project success factor (APSF) of the agile project success criteria. The findings of each APSF in the respective frameworks were used as a foundation to develop a hybrid APMM (ver. 0) that would address the agile project success criteria. The hybrid APMM (ver. 0) was developed interpretively using design science (research approach) and constructivism by combining the strengths, addressing the weaknesses and bridging the gaps identified in the frameworks. The hybrid APMM (ver. 0) was then evaluated and improved by conducting an interpretive case study, which entailed interviewing participants from large and small organisations. Once the qualitative data collected had been analysed using cross–case analysis, the findings were incorporated in order to create an improved hybrid APMM (ver. 1). The hybrid APMM (ver. 1) too was evaluated and improved by conducting a survey, which entailed administering questionnaires to various respondents in order to collect quantitative and qualitative data. The findings of the statistical analysis of the data were also used to improve the hybrid APMM (ver. 1), resulting in the final hybrid APMM (ver. 2). This study demonstrates that a combination of ASDMs and PMMs can be used to develop a hybrid APMM with the ability to deliver IT projects in a constantly changing project and business environment. / Thesis (Ph.D. (Computer Science))--North-West University, Potchefstroom Campus, 2012.