21838 research outputs found
Sort by
The role of media representations in the racial discrimination against Asian and Black people during the COVID-19 pandemic
No full textAbstracts in English, Zulu and AfrikaansThis study explores the media coverage of minorities, specifically Black and Asian people, during the COVID-19 pandemic in online newspapers and X (previously called Twitter). It focuses on how the media has contributed to racism and discrimination against minority groups. By examining online newspapers, online news networks, and X, the research probes active and inactive racism in mass media in its many forms. This research addressed a fundamental question: What is the role of media representations in the racial discrimination against Asian and Black people during the COVID-19 pandemic? The chosen online newspapers for this study included (but were not limited to) the New York Post, The New York Times in the United States, and The Guardian in the United Kingdom. The theoretical framework of this study is based on established theories on racism in the media: the integrated threat theory, hegemony, otherness and racial perception, agency, critical race theory, media richness theory, conflict theory, and prejudice. These theories provide a foundation for understanding and evaluating the existence and extent of a racial coverage divide. Methodologically, this study employed a mixed-methods approach, integrating both qualitative and quantitative analysis. The qualitative content analysis focused on the representation of Black and Asian Americans in online news coverage and X during the pandemic, while the quantitative analysis involved a systematic examination of the frequency and context of racial terms and narratives in media content. The study included a comprehensive cross-sectional analysis from the initial reported COVID-19 cases to the discovery of the Omicron variant. The COVID-19 crisis led to global health and economic challenges. Nevertheless, for Asian and Black Americans, the pandemic’s repercussions extended beyond the universal consequences. Racially insensitive terms like “Kung flu” and the “Wuhan virus” contributed to bullying and discrimination, leading to the marginalization of these communities. Key findings revealed that media representations often reinforced racial biases and stereotypes, with significant instances of both overt and covert racism. The study highlighted how certain media narratives exacerbated racial tensions and contributed to a climate of fear and prejudice against minority groups. This study contributes to the understanding of the media’s role in perpetuating racial discrimination, emphasizing the complex relationship between media, racism, and society. It serves as a unique contribution to how visible minorities were represented in news media and social media during the global pandemic. Additionally, the study makes notable recommendations for news networks, emphasizing the need for more representative voices to provide accurate and inclusive news reporting.Lolu cwaningo luhlose ukuveza lokho okwakusakazwa abezindaba ngedlanzana labantu bebala elithi, ikakhulu abantu abaNsundu namaSulumani/ama-Asian, ngesikhathi sobhubhane lweCOVID-19 emaphephandabeni aku-inthanethi kanye nakuX (obebizwa ngokuthi uTwitter ngaphambilini). Lapha sigxile ekutheni abezindaba babe nesandla kanjani ekucwaseni ngokwebala nokubandlulula idlanzana labantu bebala elithile. Ngokuhlola amaphephandaba aku-inthanethi, amanethiwekhi ezindaba aku-inthanethi, kanye noX, ucwaningo luzophenya ngokucwasa okukhona nokungagqamile emithonjeni emikhulu yezindaba okwenzeka ngezindlela eziningi. Lolu cwaningo luphendule umbuzo obalulekile othi: Yiliphi iqhaza elabanjwa abezindaba ngokumelelene nokubandlululwa ngokobuhlanga kwabantu abangamaSulumani nabaNsundu ngesikhathi sobhubhane lweCOVID-19? Amaphephandaba aku-inthanethi akhethelwe lolu cwaningo ahlanganisa (nakuba bekungenamkhawulo) iNew York Post, iNew York Times yase-United States, kanye neGuardian yase-United Kingdom. Uhlaka lwetiyori lwalolu cwaningo lususelwe emibonweni esungulelwe ukubheka ngokucwasa ngokobuhlanga kwabezindaba: itiyori edidiyelwe ebheka ukusongelwa, ukuqonelana ngokobuzwe, ukubukwa njengongemuntu kanye nombono wobuhlanga, i-ejensi, itiyori ebhaka ubucayi bobuhlanga, itiyori ebhaka ukunotha kwabezindaba, itiyori yokungezwani ngokuthile, nobandlululo. Lawa matiyori ahlinzeka ngesisekelo sokuqonda nokuhlola ubukhona nezinga lokuhlukaniswa ngokobuhlanga ekuhlinzekweni kwezindaba. Lolu cwaningo lusebenzise indlela yokuhlaziya exubile, luhlanganise ukuhlaziya ngokwezilinganiso kanye nangokwamaqophelo. Ukuhlaziywa kwengqikithi ngokwamaqophelo kugxile ekumelelweni kwabantu abaNsundu eMelika nabangamaSulimani ekusakazweni kwezindaba eziku-inthanethi kanye nakuX ngesikhathi sobhubhane, kanti ukuhlaziya ngokwezilinganiso khona kuhlanganise indlela yokuhlolwa ukwenzeka kwezinto ziziphinda nengqikithi yamatemu obuhlanga kanye nezindaba ezibikwa abezindaba. Lolu cwaningo luhlanganisa ukuhlaziya ngokuqoqa ulwazi eqoqweni labantu ngokwezigameko ezibikiwe zeCOVID-19 kuze kuba kutholakala i-Omicron variant. Inkinga yeCOVID-19 yaqhamuka nezinselelo kwezempilo nezomnotho emhlabeni jikelele. Noma kunjalo, imiphumela yobhubhane kubantu abangamaSulumani nabaNsundu eMelika, yakhomba okungaphezulu kwalokho okwenzeke kwezinye izindawo. Amatemu ahlabayo obuhlanga afana nelithi "Kung flu" kanye nelithi "Wuhan virus" abe nomthelela kubuqhwaga nasekubandlululeni, okuholele ekucwasweni kwale miphakathi. Imiphumela iveza ukuthi imibiko yemithombo yezindaba ivame ukuchema kwezokucwasa ngokobuhlanga nalokho ukuyinkoleloze, kanye nezenzo zokucwasa okusobala nokucashile. Lolu cwaningo lugqamisa indlela imibiko yabezindaba abandisa ngayo izimo zokucwaswa ngokobuhlanga nokube nomthelela esimweni sokwesaba nokucwasa idlanzana labantu. Lolu cwaningo lwengeza ukuqonda esinakho ngendima edlalwa abezindaba ekusabalaliseni ukubandlululwa ngokwebala, ukugcizelela ukwehluka kobudlelwane phakathi kwabezindaba, ukucwasa ngokwebala kanye nomphakathi. Lusebenza ukusihlinzeka ngokuhlukile ngendlela imithombo yabezindaba neyezokuxhumana eyayiveza ngayo idlanzana labantu bebala elithile ngesikhathi sobhubhane emhlabeni jikelele. Ukwengeza, ucwaningo lwenza izincomo okumele ziqashelwe abamanethiwekhi ezindaba, ukugcizelela isidingo sokwengezwa kwamazwi amelele ukuhlinzeka ngemibiko yezindaba eveza konke ngeqiniso.Hierdie studie ondersoek die mediadekking van minderhede, spesifiek swart mense en Asiërs, gedurende die COVID-19-pandemie in aanlyn koerante en op X (voorheen bekend as Twitter). Dit fokus op die manier waarop die media tot rassisme en diskriminasie teen minderheidsgroepe bygedra het. Aktiewe en onaktiewe rassisme in massamedia in sy vele gedaantes is by wyse van die bestudering van aanlyn koerante, aanlyn nuusnetwerke en X ondersoek. Hierdie navorsing het ’n fundamentele vraag aangeroer: Wat is die rol van media-uitbeeldings in rassediskriminasie teen Asiërs en swart mense gedurende die COVID-19-pandemie? Die aanlyn koerante wat vir hierdie studie geselekteer is, het onder meer die New York Post, The New York Times in die Verenigde State en The Guardian in die Verenigde Koninkryk ingesluit. Die teoretiese raamwerk van die studie berus op gevestigde teorieë oor rassisme in die media: die geïntegreerde-bedreiging-teorie (integrated threat theory), hegemonie, andersheid en raspersepsie, agentskap (agency), kritiese rasteorie, die teorie oor mediarykheid, konflikteorie en vooroordeel. Hierdie teorieë bied ’n grondslag waarop die bestaan en omvang van ’n skeiding ten opsigte van rasberiggewing verstaan en beoordeel kan word. Wat metodologie betref, is ’n gemengde-metode-benadering, wat die gebruik van beide kwalitatiewe en kwantitatiewe analise behels, vir die studie gevolg. Die kwalitatiewe inhoudsanalise het op die uitbeelding van swart en Asiatiese Amerikaners in aanlyn nuusdekking en op X tydens die pandemie gefokus. Die kwantitatiewe analise is by wyse van ’n sistematiese verkenning van die voorkoms en konteks van rasterme en -narratiewe in media-inhoud uitgevoer. Die studie het ’n omvattende deursnee-analise vanaf die eerste gerapporteerde COVID-19-gevalle tot die ontdekking van die Omikron-variant behels. Die COVID-19-krisis het tot wêreldwye gesondheids- en ekonomiese uitdagings aanleiding gegee. Vir Asiatiese en swart Amerikaners het die gevolge van die pandemie egter wyer as die algemene nagevolge gestrek. Ras-onsensitiewe terme soos “Kung flu” en “Wuhan virus” het tot afknouery en diskriminasie bygedra, wat tot die marginalisasie van hierdie gemeenskappe gelei het. Sleutelbevindings van die studie het aan die lig gebring dat media-uitbeeldings dikwels rassevooroordeel en -stereotipes versterk het en dat beduidende gevalle van beide openlike en bedekte rassisme voorgekom het. Die studie het aangetoon hoe sekere media-narratiewe rassespanning aangeblaas het en tot ’n klimaat van vrees en vooroordeel teenoor minderheidsgroepe bygedra het. Hierdie studie dra by tot insig in die rol wat die media in die voortsetting van rassediskriminasie speel en benadruk die komplekse verband tussen die media, rassisme en die samelewing. Dit dien as ’n eiesoortige bydrae tot die bestudering van die manier waarop sigbare minderhede tydens die pandemie in die nuusmedia en sosiale media uitgebeeld is. Daarbenewens bevat die studie belangrike aanbevelings vir nuusnetwerke. Die aanbevelings benadruk die behoefte aan stemme wat meer verteenwoordigend is ten einde akkurate en inklusiewe nuusberiggewing te verseker.Ph. D. (Communication Sciences)Communication Scienc
Encountering African pentecostalism : methodologies and evolving tendencies
Get PDFAfrican Pentecostal Christianity is one of the fastest-growing movements among other Christian traditions in the world. This makes African Pentecostal Christianity a major contributor to the growth of global Pentecostalism and world Christianity. However, it is submitted that the study of African Pentecostalism has been dominated by scholars in the Global North. In South Africa, while many Western scholars have taken an interest in African Pentecostalism, only a few indigenous scholars have come up in terms of conducting studies in the same field. It is only in the last few decades that we see a growing interest in studying new developments within South African Pentecostalism. As one of the emerging scholars in South Africa with a proven record of research outputs on African Pentecostalism, the aim and objective here is to share insights and experiences of conducting research in the field. Therefore, this chapter is a reflection of how I study African Pentecostalism, the approaches, and the main challenges.Christian Spirituality, Church History and Missiolog
The impact of rhino poaching on the accountability disclosures of a state-funded conservation organisation
Get PDFAbstracts in English and SpanishThe unprecedented growth in the illegal wildlife trade has created a serious challenge for conservation in Africa. Governments around the world often create entities to protect species and preserve biodiversity in their respective countries. Despite numerous interventions to conserve the world’s threatened rhino populations and reduce incidents of rhino poaching, poaching of the world’s rhino populations continue, especially in South Africa. Descriptive and inferential statistics are used to analyze and compare rhinorelated
disclosures with rhino poaching trends, to identify possible correlations between incidents of rhino poaching and rhino-related, and to establish differences between the periods between 2006 to 2015 (covered in Ackers, 2019) and the subsequent period from 2016 to 2021. Unlike the period from 2006 to 2015 where several rhino-related keywords were strongly correlated with rhino poaching incidents, no correlations were detected from 2016 to 2021. Although incidents of rhino poaching decreased, SANParks appear to have
strategically increased its anti-poaching advocacy by retaining high levels of disclosures about rhino-related issues, demonstrating how it has discharged its biodiversity-related mandate. Using the same mixedmethods research approach and similar data, this paper extends the Ackers (2019) study, which examined how South African National Parks (SANParks), by including the disclosures from 2016 to 2021.El crecimiento sin precedentes del comercio ilegal de especies silvestres ha creado un grave problema para la conservación en África. Los gobiernos de todo el mundo suelen crear entidades para proteger las especies y preservar la biodiversidad en sus respectivos países. A pesar de las numerosas intervenciones para conservar las poblaciones de rinocerontes amenazadas del mundo y reducir los incidentes de caza furtiva de rinocerontes, la caza furtiva de las poblaciones de rinocerontes del mundo continúa, especialmente en Sudáfrica. Se utilizaron estadísticas descriptivas e inferenciales para analizar y comparar las divulgaciones relacionadas con rinocerontes con las tendencias de la caza furtiva de rinocerontes, para identificar posibles correlaciones entre incidentes de caza furtiva de rinocerontes y relacionados con rinocerontes, y para establecer diferencias entre los períodos entre 2006 y 2015 (cubiertos en Ackers, 2019) y el período posterior de 2016 a 2021. A diferencia del período de 2006 a 2015, en el que varias palabras clave relacionadas con el rinoceronte estaban fuertemente correlacionadas con los incidentes de caza furtiva de rinocerontes, no se detectaron correlaciones de 2016 a 2021. Aunque los incidentes de caza furtiva de rinocerontes disminuyeron, SANParks parece haber aumentado estratégicamente su defensa contra la caza furtiva manteniendo altos niveles de divulgación sobre cuestiones relacionadas con los rinocerontes, lo que
demuestra cómo ha cumplido su mandato relacionado con la biodiversidad. Utilizando el mismo enfoque de investigación de métodos mixtos y datos similares, este documento amplía el estudio de Ackers (2019), que examinó cómo los funcionan los South African National Parks (SANParks), al incluir las divulgaciones
de 2016 a 2021.AuditingN/
Exact rotating black hole solutions for f(R) gravity by modified Newman Janis algorithm
No full textAbstract
We show that the f(R)-gravity theories with constant Ricci scalar in the Jordan/Einstein frame can be described by Einstein or Einstein–Maxwell gravity with a cosmological term and a modified gravitational constant. To obtain the rotating axisymmetric solutions for the Einstein/Einstein–Maxwell gravity with a cosmological constant, we also propose a modified Newmann–Janis algorithm which involves the non-complexification of the radial coordinate and a complexification of the polar coordinate. Using the duality between the two gravity theories we show that the stationary or static solutions for the Einstein/Einstein–Maxwell gravity with a cosmological constant will also be the solutions for the dual f(R)-gravity with constant Ricci scalar
Fiducial and differential cross-section measurements of electroweak W γ j j production in pp collisions at s = 13 TeV with the ATLAS detector
No full textAbstract The observation of the electroweak production of a W boson and a photon in association with two jets, using pp collision data at the Large Hadron Collider at a centre of mass energy of s = 13 TeV, is reported. The data were recorded by the ATLAS experiment from 2015 to 2018 and correspond to an integrated luminosity of 140 fb - 1 . This process is sensitive to the quartic gauge boson couplings via the vector boson scattering mechanism and provides a stringent test of the electroweak sector of the Standard Model. Events are selected if they contain one electron or muon, missing transverse momentum, at least one photon, and two jets. Multivariate techniques are used to distinguish the electroweak W γ j j process from irreducible background processes. The observed significance of the electroweak W γ j j process is well above six standard deviations, compared to an expected significance of 6.3 standard deviations. Fiducial and differential cross sections are measured in a fiducial phase space close to the detector acceptance, which are in reasonable agreement with leading order Standard Model predictions from MadGraph5+Pythia8 and Sherpa. The results are used to constrain new physics effects in the context of an effective field theory
A framework for the reverse logistics management of consumer returns in online retailing
No full textThe effective reverse logistics management (RLM) of consumer returns is critical for the survival of online retailers, given the inevitable nature of product returns in the online retailing industry and the rising volume thereof due to increased online shopping. This study aimed to address the challenges and gaps in RLM practices by examining consumer returns, reverse logistics (RL) processes, practices, and important factors, ultimately developing a framework for the effective RLM of consumer returns in online retailing. The primary objective of this study was to develop a comprehensive framework that online retailers can use to manage consumer returns efficiently, thereby enhancing performance and consumer satisfaction. The secondary objectives of the study aimed at examining RLM, determining the factors that influence RLM implementation and success, exploring consumer return types and RL processes from RL literature and inputs by industry experts, and investigating important factors for the effective RLM of consumer returns in online retailing. This multimethod qualitative study was conducted in three phases. Phase one involved a literature review to conceptualise RLM. Phase two used a qualitative content analysis of 289 journal articles to explore key elements of RLM. Phase three comprised 13 semi-structured interviews with industry experts to explore RLM in online retailing. Rigorous methods such as triangulation, thick description, and audit trails were employed to ensure the trustworthiness of the study. The study revealed that return prevention and control, service quality, and cost efficiency are critical for effective RLM. Service quality emerged as the most significant factor, indicating that online retailers should prioritise service-oriented and consumer-centric practices. The developed framework is a practical guide and benchmark for online retailers to manage consumer returns effectively. It also provides a foundation for future research to test and refine the framework in various settings, contributing to the broader field of RLM. Regarding policy, the study offers key insights and recommendations that can inform policymakers in developing guidelines and regulations to support effective RLM practices. The framework can serve as a policy tool to standardise RLM procedures, enhance consumer satisfaction and improve the sustainability of online retail operationsDie doeltreffende omgekeerde logistiekbestuur van terugsendings deur verbruikers is van kritieke belang vir die oorlewing van aanlyn kleinhandelaars, gegewe die onvermydelike aard van terugsendings van produkte in die aanlyn kleinhandelbedryf en die stygende volume daarvan weens ’n verhoging in aanlyn inkopies. Hierdie studie het probeer om die uitdagings en gapings in omgekeerde logistiekbestuurspraktyke aan te pak deur terugsendings deur verbruikers, omgekeerde logistiekprosesse, -praktyke en belangrike faktore te ondersoek, en uiteindelik ’n raamwerk te ontwikkel vir die doeltreffende omgekeerde logistiekbestuur van die terugsendings van verbruikers in aanlyn kleinhandel. Die primêre doelwit van hierdie studie was om ’n omvattende raamwerk te ontwikkel wat aanlyn kleinhandelaars kan gebruik om terugsendings deur verbruikers doeltreffend te bestuur, en op hierdie wyse prestasie en verbruikersbevrediging te bevorder. Die sekondêre doelwitte van die studie was daarop gerig om omgekeerde logistiekbestuur te ondersoek, die faktore te bepaal wat die implementering en sukses van omgekeerde logistiekbestuur beïnvloed, die tipes terugsendings deur verbruikers en omgekeerde logistiekprosesse van omgekeerde logistiekliteratuur en insette van bedryfskenners te verken, en belangrike faktore te ondersoek vir die doeltreffende omgekeerde logistiekbestuur van terugsendings deur verbruikers in aanlyn kleinhandel. Hierdie multimetode kwalitatiewe studie is in drie fases uitgevoer. Fase een het ’n literatuuroorsig om omgekeerde logistiekbestuur te konseptualiseer behels. Fase twee het ’n kwalitatiewe inhoudsontleding van 289 joernaalartikels gebruik om sleutelelemente van omgekeerde logistiekbestuur te verken. Fase 3 het bestaan uit 13 halfgestruktureerde onderhoude met bedryfskenners om omgekeerde logistiekbestuur in aanlyn kleinhandel te verken. Gestrenge metodes soos triangulasie, dik beskrywing en ouditspore is aangewend om die betroubaarheid van die studie te verseker. Die studie het onthul dat die voorkoming van terugsendings, die beheer van terugsendings, diensgehalte en kostedoeltreffendheid van kritieke belang is vir doeltreffende omgekeerde logistiekbestuur. Diensgehalte was die mees beduidende faktor, en het aangedui dat aanlyn kleinhandelaars voorkeur moet gee aan diensgeoriënteerde en verbruikersentriese praktyke. Die ontwikkelde raamwerk is ’n praktiese gids en maatstaf vir aanlyn kleinhandelaars om die terugsendings van verbruikers doeltreffend te bestuur. Dit bied ook ’n grondslag vir toekomstige navorsing om die raamwerk in verskeie omgewings te toets en te verfyn, wat sal bydra tot die wyer veld van omgekeerde logistiekbestuur. Wat beleid betref, bied die studie sleutelinsigte en -aanbevelings wat beleidmakers van ontwikkelende riglyne en regulasies kan aansê om doeltreffende omgekeerde logistiekbestuurspraktyke te ondersteun. Die raamwerk kan dien as ’n beleidsinstrument om omgekeerde logistiekbestuur-prosedures te standaardiseer, verbruikersbevrediging te bevorder en die volhoubaarheid van aanlyn kleinhandelbedrywighede te verbeter.D. Phil. (Management Studies)Centre for Transport Economics, Logistics and TourismText in English and Afrikaan
Impact of digital technologies on entrepreneurship education within institutions of higher education in the industry 4.0 era: a South African case
No full textThe study investigates the integration of Industry 4.0 digital technologies within entrepreneurship education (EE) at higher education institutions (HEIs). The research examined the impact of advanced technologies, including artificial intelligence (AI), virtual reality (VR), big data analytics, and the Internet of Things, in reshaping EE and fostering an entrepreneurial mindset among students by employing a qualitative methodology. The research study upon which this thesis is based has employed an interpretive approach to the collection, analysis and interpretation of primary data obtained from the South African higher education institution, including seventeen semi-structured interviews with students and faculty members. Due to the relatively small sample size, thematic analysis rather than phenomenography was employed to analyse findings. Thematic analysis, employing colour coding techniques, was utilised to identify recurring patterns in the data. Based upon the findings of this research study, key factors promoting the adoption of 4.0 digital technologies in EE, included enhanced learning experiences, increased student engagement, and alignment with the evolving needs of industries. However, the study also identified several significant barriers, including inadequate digital infrastructure, resistance to change, and a lack of pedagogical preparedness among faculty members. Both faculty and students demonstrated optimism towards 4.0 digital technologies, although varying levels of digital literacy were observed. This emphasizes the importance of customised training programmes aimed at improving digital competencies. Based on the study, an innovative model called the Digital Entrepreneurship Enrichment Model (DEEM) was established. This model provides a structured framework for HEIs incorporating Industry 4.0 technologies into EE. The DEEM assists institutions in effectively embracing Industry 4.0 transformation in the field of EE. This pioneering framework outlines a comprehensive approach to equipping students with entrepreneurial thinking and essential digital skills that align with the evolving entrepreneurial landscape. Finally, the study provides several strategic recommendations to overcome barriers that hinder the adoption of Industry 4.0 technologies in EE including the modernisation of digital infrastructure within HEIs, the assessment of stakeholder digital literacy, the provision of tailored training programs, the cultivation of industry partnerships, and the ongoing monitoring of integration efforts. By implementing these recommendations, institutions can effectively integrate Industry 4.0 technologies into EE. Policy implications include modernising HEI digital infrastructure, assessing stakeholder digital literacy, providing tailored training, cultivating industry partnerships, and monitoring integration efforts. Effective implementation can equip students with entrepreneurial thinking and essential digital skills for the evolving entrepreneurial landscape.Ph.D. (Management Studies)College of Educatio
Agri-environmental literacy and psychological capital model for agritourism
No full textAbstracts in English, Sesotho and AfrikaansAgritourism has been recognised as a niche tourism sector that has the potential to
reshape, reinvent, rekindle and revitalise domestic tourism in South Africa. Domestic
tourism in South Africa faces various challenges, such as a lack of marketing,
promotion and product development, as well as the low availability and distribution of
information. To develop, the agritourism industry needs to identify the important
attributes that would motivate potential agritourists based in Gauteng to visit an
agritourism farm. The study examined the agri-environmental literacy of potential
agritourists that would enable the agritourism establishment to attract the appropriate
pro-environmental market, while also investigating psychological capital (PsyCap) to
identify any connections between potential agritourists’ agri-environmental literacy and
the recognised agritourism attributes. The primary objective of the study was to
develop an agri-environmental literacy and PsyCap model for agritourism.
Panel data from the Bureau of Market Research (Unisa) collected primary data by
sending an online link inviting panel members to participate in the study from 24
August 2020 to 18 January 2021. The data were obtained from 526 potential
agritourists residing in Gauteng. Descriptive statistics provided insight into the agrienvironmental
literacy, PsyCap and important agritourism attributes of potential
agritourists. Exploratory and confirmatory factor analyses, structural equation
modelling (SEM) and mediation were employed to test the two developed conceptual
models.
The study made a threefold contribution: theoretically, it developed two conceptual
agri-environmental literacy and PsyCap models for agritourism, integrating
components from environmental education and positive psychology, thereby
expanding the knowledge of tourism management. Empirically, the study tested and
confirmed these models through SEM, identifying critical paths that enhance product
development and marketing for agritourism. It revealed the significant role of agrienvironmental
literacy in influencing attitudes and behaviours in agritourism.
Practically, the insights led to a proposed agri-environmental literacy and PsyCap
model for agritourism, for product development and marketing aligned with agritourists' needs. The study provided insights and recommendations to improve domestic
tourism development and the effective marketing of agritourism in South Africa.
Future research is recommended to diversify the sample by focusing on other
provinces in South Africa, allowing for regional comparisons and a broader
understanding of the dynamics of agritourism.jwa temothuo bo tsewa jaaka lephata le le kgethegileng la bojanala le le nang
le kgonagalo ya go bopa sešwa, go fetola, go tlhosetsa le go tsosolosa bojanala jwa
selegae mo Aforikaborwa. Bojanala jwa selegae mo Aforikaborwa bo lebanwe ke
dikgwetlho tse di farologaneng di tshwana le tlhaelo ya papatso, tsweletso le go
tlhabololwa ga ditlhagiswa, gammogo le go tlhaela ga tshedimosetso le go
phasaladiwa ga yone. Gore indaseteri ya bojanala jwa temothuo e gole, indaseteri e
tlhoka go supa diponagalo tsa botlhokwa tse di ka rotloetsang batho ba e ka nnang
bajanala ba temothuo mo Gauteng go etela polase ya bojanala jwa temothuo.
Thutopatlisiso e tlhatlhobile kitso ya temothuo-tikologo ya ba e ka nnang bajanala ba
temothuo e e ka kgontshang setheo sa bojanala jwa temothuo go ngokela mmaraka
o o maleba o o ratang tshomarelo ya tikologo, mme gape go ntse go batlisisiwa letlotlo
la tlhaloganyo (PsyCap) go supa kgolagano magareng ga kitso ya ba e ka nnang
bajanala ba temothuo le diponagalo tse di gona tsa bojanala jwa temothuo. Maikaelelo
magolo a thutopatlisiso e ne e le go tlhamela bojanala jwa temothuo sekao sa kitso
ya temothuto-tikologo le PsyCap.
Datha ya phanele go tswa kwa Birong ya Dipatlisiso tsa Mebaraka (Unisa) e kokoantse
datha ya tshimologo ka go romela segokedi sa seranyane go laletsa ditokololo tsa
phanele go tsaya karolo mo thutopatlisisong go tloga ka 24 Phatwe 2020, go fitlha ka
18 Firikgong 2021. Datha e bonwe go tswa mo bathong ba e ka nnang bajanala ba
temothuo ba le 526 ba ba nnang mo Gauteng. Dipalopalo tse di tlhalosang di
tlhagisitse kitso ya bojanala jwa temothuo, PsyCap le diponagalo tsa botlhokwa tsa
bojanala jwa temothuo mo go ba e ka nnang bajanala ba temothuo. Go dirisitswe
ditokololo tsa tlhotlhomiso le netefatso ya dintlha, tiriso ya mmeo e e farologaneng
(SEM) le thuanyo go lekeletsa dikao tse pedi tse di tlhamilweng.
Thutopatlisiso e dirile kakgelo e e maphata mararo: mo tioring, e tlhametse bojanala
jwa temothuo dikao tse pedi tsa kitso ya temothuo-tikologo, e golaganya dikarolo tsa
thuto ya tikologo le kakanyo e e siameng, mme ka go rialo go atolosiwa kitso ya
tsamaiso ya bojanala. Mo ntlheng ya tekeletso le kelotlhoko, thutopatlisiso e
lekeleditse le go tlhomamisa dikao tseno ka SEM, e supa ditselana tsa botlhokwa tse
di tokafatsang tlhabololo ya ditlhagiswa le papatso mo bojanaleng jwa temothuo. E
senotse seabe sa botlhokwa sa kitso ya temothuo-tikologo go tlhotlheletsa mekgwa le maitsholo mo bojanaleng jwa temothuo. Mo ntlheng ya tirisego, tshedimosetso e
lebisitse kwa sekaong se se tshitshinngwang sa kitso ya temothuo-tikologo le PsyCap
sa bojanala jwa temothuo, malebana le tlhabololo ya ditlhagiswa le papatso e e
lepalepaneng le ditlhokego tsa bajanala ba temothuo. Thutopatlisiso e neetse
tshedimosetso le dikatlenegiso tsa go tokafatsa tlhabololo ya bojanala jwa selegae le
papatso e e bokgoni ya bojanala jwa temothuo mo Aforikaborwa.
Go atlenegisiwa dipatlisiso tse dingwe mo isagong gore go dirisiwe sampole e e
farologaneng ka go lebelela diporofense tse dingwe mo Aforikaborwa, go letla gore go
nne le tshwantshanyo ya dikgaolo le go tlhaloganya dintlha tse di fetogang tsa
bojanala jwa temothuo.Landboutoerisme is erken as ’n nis-toerismesektor wat die potensiaal het om
binnelandse toerisme in Suid-Afrika te hervorm, weer aan te vuur en nuwe lewe te
gee. Daar is heelwat uitdagings vir binnelandse toerisme in Suid-Afrika, insluitende ’n
gebrek aan bemarking, bevordering en produkontwikkeling, asook dat daar nie
voldoende inligting beskikbaar is en versprei word nie. Om te kan ontwikkel, moet die
landboutoerisme-bedryf die belangrike kenmerke identifiseer wat potensiële
landboutoeriste wat in Gauteng gebaseer is, sal motiveer om ’n
landboutoerisme-plaas te besoek. Die studie het die landbou-omgewingsgeletterdheid
van potensiële landboutoeriste ondersoek wat landboutoerisme in staat stel om die
toepaslike pro-omgewingsmark aan te trek, terwyl die studie ook sielkundige kapitaal
(PsyCap) ondersoek om enige verbintenisse tussen potensiële landboutoeriste se
landbou-omgewingsgeletterdheid en die erkende landboutoerisme-kenmerke te
identifiseer. Die hoofdoelwit van die studie was om ’n
landbou-omgewingsgeletterdheid- en PsyCap-model vir landboutoerisme te
ontwikkel.
Paneeldata van die Buro van Bemarkingsnavorsing (Unisa) het primêre data
ingesamel deur ’n aanlyn skakel te stuur na paneellede om deel te neem aan die studie
van 24 Augustus 2020 tot 18 Januarie 2021. Die data is ingesamel by 526 potensiële
landboutoeriste wat in Gauteng woon. Beskrywende statistiek het insig gegee in die
landbou-omgewingsgeletterdheid, PsyCap en belangrike landboutoerisme-kenmerke
van potensiële landboutoeriste. Verkennende en bevestigende faktorontledings,
strukturele vergelykingsmodellering (SEM) en bemiddeling is aangewend om die twee
ontwikkelde begripsmodelle te toets.
Die studie het ’n drievoudige bydrae gemaak: In teorie het die studie twee
begripsmodelle vir landbou-omgewingsgeletterdheid en PsyCap ontwikkel vir
landboutoerisme, deur komponente van omgewingsonderrig en positiewe sielkunde
te integreer, en só die kennis van toerismebestuur uit te brei.
Hierdie studie het op ’n empiriese wyse hierdie modelle deur SEM getoets en bevestig,
en kritieke weë geïdentifiseer wat produkontwikkeling en bemarking vir
landboutoerisme bevorder. Dit het die beduidende rol onthul van die invloed van Landboutoerisme is erken as ’n nis-toerismesektor wat die potensiaal het om
binnelandse toerisme in Suid-Afrika te hervorm, weer aan te vuur en nuwe lewe te
gee. Daar is heelwat uitdagings vir binnelandse toerisme in Suid-Afrika, insluitende ’n
gebrek aan bemarking, bevordering en produkontwikkeling, asook dat daar nie
voldoende inligting beskikbaar is en versprei word nie. Om te kan ontwikkel, moet die
landboutoerisme-bedryf die belangrike kenmerke identifiseer wat potensiële
landboutoeriste wat in Gauteng gebaseer is, sal motiveer om ’n
landboutoerisme-plaas te besoek. Die studie het die landbou-omgewingsgeletterdheid
van potensiële landboutoeriste ondersoek wat landboutoerisme in staat stel om die
toepaslike pro-omgewingsmark aan te trek, terwyl die studie ook sielkundige kapitaal
(PsyCap) ondersoek om enige verbintenisse tussen potensiële landboutoeriste se
landbou-omgewingsgeletterdheid en die erkende landboutoerisme-kenmerke te
identifiseer. Die hoofdoelwit van die studie was om ’n
landbou-omgewingsgeletterdheid- en PsyCap-model vir landboutoerisme te
ontwikkel.
Paneeldata van die Buro van Bemarkingsnavorsing (Unisa) het primêre data
ingesamel deur ’n aanlyn skakel te stuur na paneellede om deel te neem aan die studie
van 24 Augustus 2020 tot 18 Januarie 2021. Die data is ingesamel by 526 potensiële
landboutoeriste wat in Gauteng woon. Beskrywende statistiek het insig gegee in die
landbou-omgewingsgeletterdheid, PsyCap en belangrike landboutoerisme-kenmerke
van potensiële landboutoeriste. Verkennende en bevestigende faktorontledings,
strukturele vergelykingsmodellering (SEM) en bemiddeling is aangewend om die twee
ontwikkelde begripsmodelle te toets.
Die studie het ’n drievoudige bydrae gemaak: In teorie het die studie twee
begripsmodelle vir landbou-omgewingsgeletterdheid en PsyCap ontwikkel vir
landboutoerisme, deur komponente van omgewingsonderrig en positiewe sielkunde
te integreer, en só die kennis van toerismebestuur uit te brei.
Hierdie studie het op ’n empiriese wyse hierdie modelle deur SEM getoets en bevestig,
en kritieke weë geïdentifiseer wat produkontwikkeling en bemarking vir
landboutoerisme bevorder. Dit het die beduidende rol onthul van die invloed van landbou-omgewingsgeletterdheid op houdings en gedrag in landboutoerisme.
Prakties gesproke het die insigte gelei tot ’n voorgestelde
landbou-omgewingsgeletterdheid- en PsyCap-model vir landboutoerisme, vir
produkontwikkeling en bemarking wat in lyn gebring is met landboutoeriste se
behoeftes. Die studie het insigte en aanbevelings verskaf om die ontwikkeling van
binnelandse toerisme en die effektiewe bemarking van landboutoerisme in Suid-Afrika
te verbeter.
Toekomstige navorsing word aanbeveel om die steekproefneming te diversifiseer deur
te fokus op ander provinsies in Suid-Afrika, deur streeksvergelykings toe te laat, en
deur ’n wyer verstandhouding van die dinamiek van landboutoerisme.D. Phil. (Tourism Management)Centre for Public Administration and Managemen
Teachers’ perceptions towards mediating behavioural challenges in the primary school classrooms of Bojanala District, Northwest Province.
Get PDFThe perceptions of teachers towards mediating behavioural challenges in mainstream primary school classrooms remains a critical part of the inclusion policy and practice in South African schools. This study is aimed at exploring teachers’ perceptions towards mediating behavioural challenges experienced by grade 7 learners in mainstream primary school classrooms of Bojanala District. The objectives of the study were to investigate teachers’ perceptions towards mediation of behavioural challenges, explore the factors influencing the development of behavioural challenges and finally, to establish strategies for teachers to mediate behavioural challenges in the primary school classrooms. The qualitative research methodology and data analysis was employed to comprehend and view behavioural challenges from teachers’ own interpretations and experiences. In-depth, face-to-face interviews, focus group discussion and non-participant observations were used to collect information from twelve, purposively selected primary school teachers. The study revealed that teachers experienced behavioural challenges daily in their grade 7 classrooms, which caused plenty of disruptions to the teaching and learning process. Various factors were mentioned by teachers as influencing the development of behavioural challenges, such as overcrowding, parental involvement and peer relationships. What emerged further from the findings of the study is that teachers are inadequately trained in inclusive education and effective classroom management, which needs to be urgently addressed to enable them to mediate behavioural challenges in the classroom.M.A. (Inclusive Education)Educational Studie
Exploring the accuracy-explainability trade-off on credit scoring classifiers
Get PDFText in English with summaries in Afrikaans and TswanaRecent research has highlighted the significance of accuracy and explainability of
classification models applied across various disciplines. A wide range of classification
models and combinations of models have been extensively studied to determine those
with superior performance. These studies demonstrate that models that tend to
be more accurate are also difficult to understand; there appears to be a trade-off
between accuracy and explainability. Consequently, this has led to an increased focus
on explainable artificial intelligence, a field of research concerned with explaining
model predictions.
Although explainable artificial intelligence is an area of research with growing popularity
in the science community, there are still limited case studies that explore its
applications in credit default risk. Credit default risk refers to the potential financial
loss or risk that is incurred by a credit provider when an obligor fails to meet their
debt obligations. To quantify, mitigate and manage the risk associated with granting
credit proactively, credit providers utilise scoring classifiers to assess the risk of credit
applicants prior to granting credit. Furthermore, credit risk providers are legally
required to explain predictions of scoring classifiers.
Popular classifiers used in credit risk include logistic regression, discriminant analysis,
decision trees, random forests, bootstrap aggregation, neural networks, support vector
machines and gradient boosting algorithms. Logistic regression and discriminant
analysis are widely adopted in the financial industry because they perform reasonably
well and are inherently interpretable. However, these approaches are giving way to
alternative approaches that offer improved accuracy in risk assessment, even though
these alternatives lack interpretability; they are less comprehensible and are often
regarded as black boxes. This lack of interpretability has resulted in a reluctance to
adopt these alternative techniques in credit granting.
The aim of this study is to remove the aforementioned barrier of using black box
models by utilising explainable artificial intelligence methods, such as Shapley additive
explanations and local interpretable model-agnostic explanations. The study also
examines the accuracy-explainability trade-off of different classifiers by developing
and evaluating eight classification models on two publicly available credit datasets.
Eight classification models were constructed, including decision trees, logistic regression,
linear discriminant analysis, support vector machines, artificial neural networks,
bootstrap aggregation, random forest, and light gradient boosting classifier. Their
performance and interpretability were assessed after training and tuning the hyperparameters
for optimal comparison on training, testing and validation subsets of the
data. Performance accuracy was measured using the area under the curve on 30
random subsets generated from the validation data. Furthermore, the Kruskal Wallis
test and Dunn’s multi-comparison test were used to rank the predictive models by
accuracy and to determine if the differences in mean accuracy are statistically significant.
The interpretability of these classifiers was conducted for both transparent and
black box models. To achieve these ends, key preprocessing steps were developed to
reduce the complexities of local and global model interpretation. In addition, Shapley
additive explanations and local interpretable model-agnostic explanations were
utilised to analyse the relative importance of features and the impact on predictions.
The experiments show that the artificial neural network, ensembles and other treebased
algorithms significantly outperform logistic regression and linear discriminant
analysis in the first case study. However, contradictory results are obtained for the
second case study, as the performance of the classifiers are relatively comparable.
This indicates that model performance depends on the data from which the models
are constructed. These two case studies show that the perceived trade-off between
accuracy and explainability does not always hold true. Furthermore, Shapley additive
explanations yielded results that are consistent with the intrinsic interpretability
results of the transparent methods. This post-hoc interpretability enables us to
understand how the predictions are made and what factors contributed to the
prediction. This is important to create a reliable and trustworthy framework that
uses black box models for credit decisions.
The research highlights the benefits of using alternative methods for credit risk
scoring, showing that the performance can vary significantly. It also demonstrates
the effectiveness of Shapley additive explanations and local interpretable modelagnostic
explanations to explain predictions of black box classifiers. However, it
identifies challenges in using the Shapley additive explanations. The mean absolute
value may be sensitive to outliers, which could have an impact on feature importance.
Therefore, further work is required to enhance the efficiency of calculating Shapley
additive explanations’ values for linear classifiers and some ensembles.Onlangse navorsing het die belangrikheid uitgelig van die akkuraatheid en verduidelikbaarheid
van klassifikasiemodelle wat dwarsoor verskeie dissiplines toegepas word.
’n Wye reeks klassifikasiemodelle en modelkombinasies is omvattend bestudeer om
daardie modelle met voortreflike prestasie te bepaal. Hierdie studies het gedemonstreer
dat modelle wat neig om meer akkuraat te wees, ook moeilik is om te verstaan;
dit kom voor of daar ’n kompromie is tussen akkuraatheid en verduidelikbaarheid. Dit
het gevolglik aanleiding gegee tot ’n verhoogde fokus op verduidelikbare kunsmatige
intelligensie, ’n navorsingsveld wat met die verduideliking van modelvoorspellings
gemoeid is.
Alhoewel verduidelikbare kunsmatige intelligensie ’n navorsingsgebied is wat besig
is om in gewildheid toe te neem binne die wetenskapgemeenskap, is daar steeds
beperkte gevallestudies wat die toepassing daarvan op kredietwanbetalingsrisiko ondersoek.
Kredietwanbetalingsrisiko verwys na die potensi¨ele finansi¨ele verlies of risiko
waaraan ’n kredietverskaffer blootgestel word wanneer ’n skuldenaar in gebreke bly
om hul skuldverpligtinge na te kom. Ten einde die risiko wat met kredietverskaffing
geassosieer word proaktief te kwantifiseer, versag en bestuur, moet kredietverskaffers
kredietgraderingsklassifiseerders gebruik om die moontlike risiko te evalueer wat
kredietaansoekers inhou, voordat krediet toegestaan word. Voorts is kredietrisikoverskaffers
volgens wet verplig om die voorspellings van kredietgraderingsklasifiseerders
te verduidelik.
Gewilde klassifiseerders wat in kredietrisiko gebruik word, sluit logistieke regressie,
diskriminantanalise, besluitnemingsbome, ewekansige woude, skoenlussamevoeging,
neurale netwerke, ondersteuningsvektormasjiene en gradi¨entversterkingsalgoritmes
in. Logistieke regressie en diskriminantanalise is algemeen deur die finansi¨ele bedryf
aanvaar aangesien hulle redelik goed presteer en inherent verduidelikbaar is. Hierdie
benaderings skep egter ruimte vir alternatiewe benaderings wat verbeterde akkuraatheid ten opsigte van risiko-assessering bied selfs al gaan hierdie alternatiewe
benaderings mank aan interpreteerbaarheid; hulle is nie so verstaanbaar nie en word
dikwels as swartkissies (black boxes) gesien. Hierdie gebrek aan interpreteerbaarheid
het tot gevolg dat daar ’n traagheid is om hierdie alternatiewe kredietverleningstegnieke
aan te neem.
Hierdie studie het ten doel om die voorafgenoemde versperring tot die gebruik
van swartkissiemodelle te verwyder deur verduidelikbare kunsmatige intelligensiemetodes
soos Shapely se additiewe verduidelikings en plaaslike interpreteerbare
model-agnostiese verklarings te gebruik. Die studie ondersoek ook die akkuraatheidverduidelikbaarheidskompromie
van verskillende klassifiseerders deur agt klassifikasiemodelle
vir twee openbaar beskikbare kredietdatastelle te ontwikkel en te evalueer.
Agt klassifikasiemodelle is saamgestel, naamlik besluitnemingsbome, logistieke regressie,
liniˆere diskriminantanalise, ondersteuningsvektormasjiene, kunsmatige neurale
netwerke, skoenlussamevoeging, ewekansige woud en ligte gradi¨entversterkingsklassifiseerder.
Hul prestasie en interpreteerbaarheid is geassesseer na opleiding
en instelling van die hiperparameters vir optimale vergelyking van opleiding, toetsing
en geldigverklaring van deelversamelings van die data. Prestasie-akkuraatheid is
gemeet deur van die area onder die kurwe van 30 ewekansige deelversamelings wat
uit die geldigverklaarde data gegenereer is, gebruik te maak. Voorts is daar van
die Kruskal Wallis-toets en Dunn se multivergelykingstoets gebruik gemaak om die
voorspellingsmodelle ten opsigte van akkuraatheid te klassifiseer en te bepaal of
die verskille in gemidddelde akkuraatheid statisties beduidend is. Die interpreteerbaarheid
van hierdie klassifiseerders is vir beide deursigtige en swartkassiemodelle
uitgevoer. Om hierdie resultate te verkry, is belangrike voorverwerkingstappe ontwikkel
om die kompleksiteite van plaaslike sowel as globale modelinterpretasie
te verminder. Daarbenewens is Shapley se additiewe verduidelikings en plaaslike
interpreteerbare model-agnostiese verduidelikings ook ingespan om die relatiewe
belangrikheid van kenmerke en die impak op voorspellings te ontleed.
Die eksperimente toon dat die kunsmatige neurale netwerk, ensembles en ander
boomgebaseerde algoritmes in die eerste gevallestudie beduidend beter as die logistieke
regressie en liniˆere diskriminantanalise presteer het. Die tweede gevallestudie het
egter teenstrydige resultate opgelewer. In die tweede gevallestudie is die prestasie
van die klassifiseerders relatief vergelykbaar. Dit is ’n aanduiding dat modelprestasie
afhanklik is van die data waaruit die modelle saamgestel is. Hierdie twee gevallestudies
toon dat die waargenome kompromie tussen akkuraatheid en verduidelikbaarheid
nie altyd waar is nie. Boonop het die Shapley additiewe verduidelikings resultate
opgelewer wat met die intrinsieke interpreteerbaarheidsresultate van die deursigtige
metodes ooreenstem. Hierdie post-hoc interpreteerbaarheid help ons om te verstaan
hoe die voorspellings gemaak word en watter faktore tot die voorspellings bygedra
het. Laasgenoemde is belangrik ten einde ’n betroubare en geloofwaardige raamwerk
te skep wat van swartkassiemodelle vir kredietbesluite gebruik maak.
Die navorsing beklemtoon die voordele van die gebruik van alternatiewe metodes
vir kredietrisikogradering; dit toon dat die prestasie aansienlik kan varieer. Dit
demonstreer ook die doeltreffendheid van die Shapley additiewe verduidelikings
en plaaslike interpreteerbare model-agnostiese verduidelikings in die verduideliking
van voorspellings van swartkissieklassifiseerders. Dit is egter so dat dit uitdagings
ten opsigte van die Shapley additiewe verduidelikings identifiseer. Die gemiddelde
absolute waarde mag dalk sensitief wees vir uitskieters wat ’n impak op die belangrikheid
van kenmerke kan hˆe. Daarom is verdere werk nodig om die doeltreffendheid
van die berekening van Shapley se additiewe verduidelikings se waardes vir liniˆere
klassifiseerders en sommige ensembles te versterk.Diphuputso tsa morao tjena di totobaditse bohlokwa ba ho nepahala le ho hlaloswa
ha mefuta ya dihlopha e sebediswang dikarolong tse fapaneng. Mefuta e mengata e
fapaneng ya dihlopha le motswako wa mefuta e nnile ya ithutwa haholo ho fumana
hore na ke efe e nang le tshebetso e phahameng. Diphuputso tsena di bontsha hore
mehlala e atisang ho nepahala haholwanyane le yona e thata ho e utlwisisa; ho
bonahala ho e na le kgwebo pakeng tsa ho nepahala le ho hlalosa. Ka lebaka leo,
sena se lebisitse tlhokomelong e eketsehileng ho bohlale bo hlakileng ba maiketsetso,
lefapha la dipatlisiso le amanang le ho hlalosa dikgakanyo tsa mohlala.
Leha bohlale ba maiketsetso bo hlaloswang e le sebaka sa dipatlisiso se ntseng se hola
setumo se ntseng se hola setjhabeng sa mahlale, ho ntse ho na le dithuto tse fokolang
tse hlahlobang tshebediso ya yona kotsing ya ho se be teng ha mekitlane. Kotsi
ya ho se be teng ha mokitlane e bolela tahlehelo ya ditjhelete e ka bang teng kapa
kotsi e hlahiswang ke mofani wa mokoloto ha motho ya tlamang a hloleha ho fihlela
mekoloto ya hae. Ho lekanya, ho fokotsa le ho laola kotsi e amanang le ho fana ka
mokoloto ka potlako, bafani ba mekitlane ba sebedisa dihlopha tsa dintlha ho lekola
kotsi ya bakopi ba mekitlane pele ba fana ka mokoloto. Ho feta moo, bafani ba kotsi
ya mokoloto ba hlokwa ka molao ho hlalosa dikgakanyo tsa dihlopha tsa dintlha.
Dihlopha tse tsebahalang tse sebediswang e le kotsi ya mokoloto di kenyelletsa ho
theola maemo, hlahlobo ya kgethollo, difate tsa diqeto, meru e sa rerwang, pokello
ya bootstrap, marangrang a neural, metjhini ya divector ya tshehetso le dialgorithms
tse matlafatsang. Phokotso ya dintho le hlahlobo ya kgethollo di amohelwa haholo
indastering ya ditjhelete hobane di sebetsa hantle ka mokgwa o utlwahalang mme ka
tlhaho di ka tolokwa. Leha ho le jwalo, mekgwa ena e fana ka mokgwa wa mekgwa e
meng e fanang ka ho nepahala ho ntlafetseng ha ho hlahlojwa kotsi, le hoja mekgwa
ena e meng e se na tlhaloso; ha di utlwisisehe mme hangata di nkwa e le mabokose a
matsho. Kgaello ena ya hlaloso e bakile ho qeaqea ho sebedisa mekgwa ena e meng ya ho fana ka mekoloto.
Sepheo sa thuto ena ke ho tlosa mokwallo o boletsweng ka hodimo wa ho sebedisa
mehlala ya diblackbox ka ho sebedisa mekgwa e hlakileng ya bohlale ba maiketsetso,
jwalo ka dihlaloso tsa tlatsetso tsa Shapley le dihlaloso tsa sebaka sa habo bona tsa
agnostic. Boithuto bona bo boetse bo hlahloba kgwebo e nepahetseng le hlaloso e
nepahetseng ya dihlopha tse fapaneng ka ho theha le ho lekola mefuta e robedi ya
dikarolo ho didatabase tse pedi tse fumanehang phatlalatso ya tsa mekoloto.
Ho ile ha ahwa mefuta e robedi ya dikarolo, ho kenyeletswa lifate tsa liqeto, ho theoha
ha thepa, hlahlobo ya kgethollo e tshwanang, metjhini ya divector tse tshehetsang,
marangrang a maiketsetso a neural, aggregation ya bootstrap, moru o sa rerwang,
le sehlopha se matlafatsang se bobebe. Tshebetso ya bona le hlaloso ya bona di
ile tsa hlahlojwa ka mora ho kwetliswa le ho lokisa di-hyperparameters bakeng sa
papiso e nepahetseng mabapi le kwetliso, diteko le ho netefatsa dikarolwana tsa data.
Ho nepahala ha tshebetso ho ile ha lekanyetswa ho sebediswa sebaka se ka tlasa
lekgalo ho disubsets tse 30 tse sa rerwang tse hlahisitsweng ho data ya netefatso.
Ho feta moo, teko ya Kruskal Wallis le ya Dunn ya ho bapisa dintho tse ngata di
ile tsa sebediswa ho beha maemo a ponelopele ka ho nepahala le ho fumana hore
na diphapano tsa ho nepahala ha moelelo di bohlokwa ho latela dipalo. Hlaloso
ya dihlopha tsena e ile ya etswa bakeng sa mehlala ya dibox tse bonaletsang le tse
ntsho. Ho finyella diphello tsena, mehato ya bohlokwa ya ho lokisa esale pele e ile
ya ntlafatswa ho fokotsa ho rarahana ha hlaloso ya mohlala ya lehae le ya lefatshe.
Ntle le moo, dihlaloso tsa tlatsetso tsa Shapley le dihlaloso tsa sebaka sa sebaka sa
motlolo wa agnostic di ile tsa sebediswa ho sekaseka bohlokwa bo lekanyeditsweng
ba dikarolo le phello ya dikgakanyo.
Diteko di bontsha hore marangrang a maiketsetso a methapo ya kutlo, di-ensembles
le di-algorithms tse ding tse thehilweng sefateng di feta haholo ho theoha ha thepa
le hlahlobo e fapaneng ya kgethollo thutong ya pele. Leha ho le jwalo, diphetho tse
hanyetsanang di fumanwa bakeng sa thuto ya mohlala ya bobedi, kaha tshebetso
ya dihlopha di batla di bapiswa. Sena se bontsha hore tshebetso ya mohlala e
itshetlehile ka data eo mehlala e ahilweng ho yona. Dithuto tsena tse pedi tsa
dinyewe di bontsha hore phapang pakeng tsa ho nepahala le ho hlalosa ha se kamehla
e leng nnete. Ho feta moo, dihlaloso tsa tlatsetso tsa Shapley di hlahisitse ditholwana
tse tsamaellanang le sephetho sa ho toloka ha mekgwa e pepeneneng. Hlaloso ena
ya post-hoc e re thusa ho utlwisisa hore na dikgakanyo di etswa jwang le hore na
ke dintlha dife tse tlatseditseng ho bolela esale pele. Sena ke sa bohlokwa ho theha
moralo o ka tsheptjwang le o ka tsheptjwang o sebedisang mehlala ya lebokose le
letsho bakeng sa diqeto tsa mokitlane.
Patlisiso e totobatsa melemo ya ho sebedisa mekgwa e meng bakeng sa dintlha
tsa kotsi ya mokoloto, e bontsha hore tshebetso e ka fapana haholo. E boetse e
bontsa katleho ya dihlaloso tsa tlatsetso ya Shapley le dihlaloso tsa sebaka seo ho ka tolokwang tsa mohlala-agnostic ho hlalosa dikgakanyo tsa dihlopha tsa diblackbox.
Leha ho le jwalo, e supa mathata a ho sebedisa dihlaloso tsa tlatsetso ya Shapley.
Theko ya boleng bo felletseng e kanna ya ameha ho barekisi ba kantle, e ka amang
bohlokwa ba karolo. Ka hona, mosebetsi o mong o a hlokahala ho ntlafatsa bokgoni
ba ho bala boleng ba dihlaloso tsa tlatsetso tsa Shapley bakeng sa dihlopha tsa linear
le diensembles tse ding.M. Sc. (Operations Research)College of Engineering, Science and Technolog