International Journal of Science Annals, Vol. 8, No. 2, 2025 рrint ISSN: 2617-2682; online ISSN: 2707-3637; DOI:10.26697/ijsa SOCIAL AND BEHAVIORAL SCIENCES. Economics ORIGINAL RESEARCH Data Quality Factors for Big Data Analytics in Occupational Health and Risk Management Authors’ Contribution: A – Study design; Lephoto N. 1 ABCDEFG , Segooa M. A. 1 ABCDEFG , B – Data collection; Motjolopane I. 2 ABCDEFG , Seaba T. R. 3 ABCDEFG C – Statistical analysis; 1 Tshwane University of Technology, South Africa D – Data interpretation; 2 University of Witwatersrand, South Africa E – Manuscript preparation; 3 Nelson Mandela University, South Africa F – Literature search; G – Funds collection Received: 30.10.2025; Accepted: 19.12.2025; Published: 25.12.2025 Abstract Background and Occupational health and risk management (OHRM) in the South African mining Aim of Study: sector remains a critical national priority, where the life or death outcomes can be impacted by poor quality-data usage. Big data analytics (BDA) is increasingly used for hazards predictions and timely decision-making. The aim of the study: to explore critical data quality factors that influence the reliability and effectiveness of BDA for decision-making to guide occupational health practitioners and risk managers within South African mining sector. Material and Methods: The study employed a quantitative survey methodology, informed by the literature review, to identify key data quality factors of BDA impacting OHRM in the South African mining sector. Underpinned by Technological, Organizational and Environmental (TOE) theory and contextual factors within big data quality dimensions and big data sources. Data was collected from 103 OHRM experts determined by the population size of 140. Results: The results reveal the following factors to have influence on data quality for BDA within SA mining OHRM; Environmental factors with a predictive power of 25.0% (β=0.250) at p=0.014; followed by big data quality dimensions with 24.1% (β=0.241) at p=0.008; then, technological factors with 15.9% (β=0.159) at p=0.027; big data sources with 13.2% (β=0.132) at p=0.026; lastly organisational factors was less significant at p=0.228 with 10.0% (β=0.100). Conclusions: This study identifies the factors of data quality, highlighting its role in BDA for decision-making within OHRM. These factors can further be used to provide guidance for SA mining OHRM decision makers to target critical data quality improvement areas for enhanced decision making in the sector. Keywords: big data analytics, data quality, mining safety, occupational health, risk management, South Africa. Copyright: © 2025 Lephoto N., Segooa M. A., Motjolopane I., Seaba T. R. Published by Archives of International Journal of Science Annals DOI: https://doi.org/10.26697/ijsa.2025.2.5 Conflict of interests: The authors declare that there is no conflict of interests Peer review: Double-blind review Source of support: This research did not receive any outside funding or support Information about Lephoto Nyakallo (Corresponding Author) – https://orcid.org/0009-0000-7899- the authors: 6950; n.lephotoj@gmail.com; Department of Informatics, Tshwane University of Technology, Pretoria, South Africa. Segooa Mmatshuene Anna – https://orcid.org/0000-0002-4190-8256; Doctor of Computing, Senior Lecturer, Department of Informatics, Tshwane University of Technology, Pretoria, South Africa. Motjolopane Ignitia – https://orcid.org/0000-0001-9047-6720; PhD in Information Systems, Associate Professor, Digital Business Wits Business School, University of Witwatersrand, Johannesburg, South Africa. Seaba Tshinakaho Relebogile – https://orcid.org/0000-0002-5773-887X; Doctor of Computing in Informatics, Senior Lecturer, Department of IT Management and Governance, Nelson Mandela University, Gqeberha, South Africa. 36 International Journal of Science Annals, Vol. 8, No. 2, 2025 рrint ISSN: 2617-2682; online ISSN: 2707-3637; DOI:10.26697/ijsa Introduction The mining sector serves as the pillar of the world’s amounts of data (Feng et al., 2019), in which impacts the financial resource; however, minimizing risk-related success of the processes that are driven by data, analytics issues and negative environmental effects presents a and decision-making systems (Rangineni et al., 2023). significant challenge in the industry (Bag et al., 2021). According to Bisschoff and Grobbelaar (2022), data The mining industry leverages various big data sources quality is critical to obtain accurate insights and protect to prevent occupational hazards, and to ensure a secure companies from making poor decisions as a result of working environment (Abd Karim & Sejati, 2021). poor data quality and includes objectively and correctly These big data sources generates vast amount of data, describing real situations (Tylečková & Noskievičová, according to Ntlhakana et al. (2021), big data has a 2020). radical effect on occupational health and enables the High-quality data is critical in the mining sector due to early identification of high-risk patients through the the nature of the environment, which involves managing integration of big data source technologies (Brouwer & number of risks, including safety, health, and Rees, 2020). Mining industry professionals make use of environmental sustainability. Hence, in South African this data to inform decision-making processes and mining sector, sustainable development entails the mitigate the adverse effects of the occupational health investigation for the intersections between the mining challenges such as occupational hearing loss (Moroe et companies’ goals, their business procedures, and the al., 2019). Failure to address environmental, social and subsequent effects on the welfare of the community, governance challenges may negatively impact the safety, and health (Bag et al., 2021). Poor data quality reputation of organisations. Loss of revenue and further leads to inaccurate evaluations of occupational health increase the risk of none compliance (van Rensburg et risks, in which can potentially compromise employees’ al., 2019).Therefore, big data analytics (BDA) and data safety, increase penalties (Mishra & Mishra, 2023), quality may be of value, as both appear to be drivers of erroneous reporting and noncompliance with various transformation and improvement in the mining industry occupational health and safety regulations (Maroun, (Bisschoff & Grobbelaar, 2022). 2019). In addition, Feng et al. (2022) emphasized the The use of BDA is expanding with increasing significance of missed organizational learning acknowledgement from academia and industry. BDA opportunities within the healthcare field, pointing out refers to the systematic examination and analysis of concerns related to underreporting, contributing factors, large datasets that exceed traditional analytical and quality improvement projects. Organizations capabilities (Hariri et al., 2019), utilizing innovative involved in mining can gain a better understanding of techniques for data storage, management, analysis, and unsafe behaviours and potentially uncover instances of visualization (Vassakis et al., 2018) of massive and underreporting that impact the accuracy and reliability complex datasets, commonly known as Big Data (Kuo of data related to occupational health and safety in the et al., 2014). BDA offers potential significant benefits mining sector (Kumar & Bhattacharjee, 2023). for organisational performance in the mining industry. Moreover, Luo et al. (2023) emphasized how inadequate Furthermore, can enables data driven decision making, safety technology training and delayed hazard which may lead to improvement of organisation’s identification can contribute to underreporting of efficiency and profitability (Vassakis et al., 2018). accidents, affecting quality of data within the OHRM in Additionally, applying BDA within Occupational the mining sector. Health and Risk Management (OHRM) in the mining The aim of the study. To analyse the factors that sector may improve effectiveness of the environment influence data quality in big data analytics to improve using big data-driven innovations beneficial for decision making within the SA mining sector. By sustainability (Bag et al., 2021). exploring these factors, the study is intended to address Despite noticeable BDA potential on OHRM, data big data quality challenges as well as their impact in quality remains the main challenge to the accuracy of the decision making processes for OHRM within SA mining outcomes. Poor data quality appears to be organisations. disadvantaging organisations to fully benefiting from the value of using BDA (Cai & Zhu, 2015). According Materials and Methods to Vassakis et al. (2018) obtaining the insightful According to Lim et al. (2013) the information services outcomes from BDA analysis of accurate and reliable (IS) theories are considered a foundation of information data of is required. As data quality remains essential to systems research study, which provides a design and leverage accurate and meaningful decision-making, guidance on investigating a phenomena. For the which may influence organizational growth (Segooa & researcher to present unbiased results, the choice of IS Kalema, 2024) taking into account the conditions of theory framework is derived from the topic of the study, digitalisation in the economy (Pypenko, 2019; Pypenko research objectives and literature review (Chukwuere, & Melnyk, 2021). 2021). Data Quality is defined as the degree of data usefulness This study integrated TOE IS theory with big data (Wang et al., 2023), for its intended application and quality dimensions and big data sources, as an requirements (Declerck et al., 2024). In the realm of big underlying theory to expand the existing theoretical data analytics, data quality is critical for identifying body of knowledge, considering the factors identified by patterns, correlations, and trends within massive the researcher while during the review of the literature. 37 International Journal of Science Annals, Vol. 8, No. 2, 2025 рrint ISSN: 2617-2682; online ISSN: 2707-3637; DOI:10.26697/ijsa TOE framework is known for its ability to provide a Figure 1 presents conceptual model of enhanced data more comprehensive approach by taking into account quality for BDA to improve decision making in SA technological, organisational and environmental factors mining OHRM. (Ullah et al, 2021). Figure 1 Conceptual Model of Enhanced Data Quality for Big Data Analytics to Improve Decision Making in South African Mining Occupational Health and Risk Management This study employed quantitative methodology relevant participants and aligned with the field of study following positivist approach to explore big data quality and research objective to obtain insights and measure factors for BDA to improve decision making in the SA data quality factors identified during the review of the mining industry. Positivist approach is usually literature in the OHRM within the mining sector. To associated with the quantitative research paradigm, in collect data from the sample size of 103 OHRM which the researcher would utilize surveys, participants, the researcher used google forms to create questionnaires, or experimental techniques to extract a questionnaire for seamless administration of the and generalize the results (Kivunja & Kuyini, 2017). responses. The questionnaire was developed and employed as a This study considered directly impacted stakeholders data collection tool in this study, to discover patterns and from one of the largest gold mine in South Africa as a factors that influence the quality of data in BDA, for the sample population, specifically selected subject matter incidents involving occupational health and safety experts (SMEs) within the OHRM disciplines such as (OHS), risk hazards and processes for decision making. occupational health, occupational hygiene, safety This study used sampling determinants method by management, radiation and risk management. As they Krejcie and Morgan (1970) to determine the sample size rely on BDA for decision making and data quality is of the study, which guided that the population of 140, critical for their prediction. The selection criteria is requires a sample size of 103. The researcher selected presented on Table 1. 38 International Journal of Science Annals, Vol. 8, No. 2, 2025 рrint ISSN: 2617-2682; online ISSN: 2707-3637; DOI:10.26697/ijsa Table 1 Table 2 Selection Criteria Overall Reliability Statistics The overall reliability statistics based on the Cronbach’s alpha coefficient was 0.966 measured on 86 items. This value is acceptable (Taber, 2017) as it is above the According to Albers (2017), in order to reach a minimum value of 0.7. conclusion in a quantitative research study, a numerical data must be gathered and analysed. Data analysis Results reveals the linkage of the study’s contextual setting, The study considered South African Mining main trends and patterns. In this study statistical tests Occupational Health and Risk Management experts, and tools such as Statistical Package for the Social which included the total responses of 104 participants. Sciences (SPSS) version 28.0.0.0 from IBM was used Thus, 1 chief safety officer, 9 group technology (GT) for data analysis to obtain conclusions from the systems specialists, 15 occupational health managers, 22 collected data. According to Bauer et al. (2021) most of occupational health nursing practitioners, 1 the quantitative studies consists of the basic statistical occupational hygiene manager, 12 occupational analytic methods, such as correlation regressions, hygienists, 13 occupational medical practitioners, 1 descriptive statistics, and analysis with or without radiation manager, 8 radiation protection officers, 20 probabilities, measurements of statistical significance risk management specialists and 2 safety officers as and interactions. The results overall reliability was shown in Table 3. conducted for the study as presented in Table 2. Table 3 Frequencies of Participants’ Demographics 39 International Journal of Science Annals, Vol. 8, No. 2, 2025 рrint ISSN: 2617-2682; online ISSN: 2707-3637; DOI:10.26697/ijsa Furthermore, Table 3 presents that OHRM discipline mining organisation only operates in 3 provinces in consists more of employees above 31 years of age than South Africa, which is Free State, Gauteng and North 21-30 years of age; this result is valid as mining industry West. On BDA utilization, Table 3 indicates retains its employees due to level of experience mostly demonstrates that only 5 participants of the total of 104 in occupational safety and risk. Moreover, the table participants which is 4.8% are not using big data shows that 9.6% of participants had matric certificates analytics tools in their daily duties. As a result, 95.2% of as their highest qualification, 30.8% had national the participants utilize big data analytics tools for diploma, 52.9% had Bachelor’s degree, 5.8% had decision-making. Master’s degree and 1.0% of the participants had PhD, Regression Statistical Analysis the findings indicates that most participants hold This study considered regression statistical analysis to Bachelor’s degree with 55.0%. Therefore, this study is determine the relationship between enhancing data valid as OHRM specialists are required to have attended quality for BDA analytics as an independent variable a formal training and education. Table 3 further and number of dependent variables thus, Technological, demonstrates locations, and only 3 provinces out of 9 in Environmental, Organisational, Big Data Quality South Africa, and South Africa as country, the dimensions and Big Data Sources. Linear regression assumption is that participant might be working in statistical analysis is an analytical method used to multiple provinces, according to the results Gauteng had determine the influence that an independent variables the highest responses at 47.1%, followed by Free State has on the dependent variable (Wardhani et al., 2021). with 30.8% and the lowest being North West with The results of the statistical analysis are presented in 22.1%. Therefore, this study is valid as the sampled Table 4. Table 4 Model Summary Note. a. Predictors: (Constant), Big Data Sources, Technological, Organisational, Data Quality and Environmental; b. Dependent Variable: Enhancing Data Quality for BDA. According to Table 4, the correlation value of R Square making in South African Mining Sector OHRM is is 60.8% (0.608), which indicates the contribution 77.9%. between the individual variables towards dependent Furthermore, the sig. F change value of 0.00, which is variable “Enhancing data quality in BDA for effective below 0.05, indicates that the prediction of the identified decision-making”. While the correlation value of 0.779 big data quality factors for BDA is significant and can indicates, the overall contribution of individual be considered to improve decision making in SA mining independent factors towards the conceptual model to sector. The regression coefficients are shown in Table 5. enhancing data quality in BDA for improved decision- Table 5 Regression Coefficients Note. TechFactor – technological factors; OrgFactor – organisational factors; EnvFactor – environmental factors; DataQualityFac01 – big data quality dimensions; BigDataSourcesfac01 – big data sources. Based on the regression coefficients on Table 5, the p=0.014 which is the most influential; followed by big findings reveal that the factors that influence data quality data quality dimensions with 24.1% (β=0.241) at for BDA within SA mining OHRM are; Environmental p=0.008; then, technological factors with a predictive factors with a predictive power of 25.0% (β=0.250) at power of 15.9% (β=0.159) with significance level of 40 International Journal of Science Annals, Vol. 8, No. 2, 2025 рrint ISSN: 2617-2682; online ISSN: 2707-3637; DOI:10.26697/ijsa p=0.027; big data sources with 13.2% (β=0.132) at The results indicates that only four of the hypotheses significance level of p=0.026; lastly organisational were supported after quantitative data analysis: H1, H3, factors was found to be less significant at p=0.228 with H4 and H5. While one hypothesis, which is H2 – predictive power of 10.0% (β=0.100). organisational factors, was rejected. Table 6 presents the results for the tested set hypotheses of the study. Table 6 Hypotheses Results Discussion and implementing safety measures effectively, mining The aim of this study was to identify critical factors of organizations can enhance data quality, reduce negative data quality in BDA to improve decision making within occurrences, and cultivate a safe working environment OHRM for mining sector. In this section, the researcher for employees (Stojanović et al., 2024). discusses the key data quality factors identified during Big Data Quality Organisational Factors literature review, which informed hypotheses, and further Table 6 shows H2 (P=0.288>0.05), was rejected which tested in this study. indicates that organisational factors such as leadership, Big Data Quality Technological Factors lack of training, resources, lack of awareness within Table 6 shows that H1 (P=0.027<0.05) was accepted, Health and Safety, poor monitoring of OHS, and suggesting that Technological factors such as reporting inaccurate Reliance do not significantly have influence systems, OHRM systems and underreporting have on data quality enhancement within BDA for effective significant influence on enhancing data quality for BDA decision-making in South African mining OHRM. within South African mining OHRM to improve According to Sarstedt and Mooi (2018), the overall decision-making. These results are supported by the parameter that it is greater than 0.05 is considered to be study conducted by Famure et al. (2019) that Electronic not significant. Health Record (EHR) systems have contributed to the These organisational factors were identified in emergence of BDA in healthcare by offering chances for accordance to the literature conducted by Johnson et al. quality improvements, which are crucial components for (2021) who revealed that data quality improvement is a enhancing data quality in occupational health and safety. top management function through an empirical Consistently, the study conducted by Yang et al. (2021) investigation of BDA capabilities implementation. underscores the importance of robust reporting systems Whilst, Haas (2020) established that leadership has a and information technology in identifying causes of critical role in shaping safety culture and impacting safety issues and accidents within the coal mine industry, health and risk management processes at the operational emphasizing the role of technological advancements in level, on the study highlighting the need for developing enhancing safety practices and data quality within the effective decision-making models in occupational health industry. Moreover, the study by Zhou et al. (2018) and safety. Moreover, research by Hermanus (2007) further supports the outcomes highlighting the critical identified resource limitations in small mining companies importance of robust OHS systems and risk management contribute significantly to health and risk management within the mining sector. Additionally, the research concerns. highlights the significance of OHS management practices Furthermore, Franke and Hiebl (2022) acknowledged the in fostering organizational safety culture, risk need for skilled data analytics resources to effectively management, and incident prevention, by managing risks examine big data and derive meaningful insights for 41 International Journal of Science Annals, Vol. 8, No. 2, 2025 рrint ISSN: 2617-2682; online ISSN: 2707-3637; DOI:10.26697/ijsa informed decision-making in mining. In support, conducted by Abd Karim and Sejati (2021), indicating Alnefaie et al. (2022) identified the vital role played by that the mining industry leverages various big data data specialists play in processing big data to facilitate sources such as OHRM systems to prevent occupational decision support, and identifying data sources and hazards, and to ensure a secure working environment required competencies can significantly influence data (Andri Estining Sejati, 2021). Furthermore, the study quality in mining. In addition, According to Nazari et al. conducted by Montisci et al. (2022) identified the variety (2020), training and knowledge development are of big data sources, such as systems for injury-reported essential to overcome BDA challenges and leverage its incidents, clinical examinations, and electronic health benefits effectively. Similarly, Muhunzi et al. (2023) records. Moreover, mining industries integrated multiple found that training healthcare professionals to leverage big data sources such as remote sensing technologies, BDA effectively may improve patient outcomes and geographical information systems (GIS) and machine reduce healthcare costs. Moreover, Andrews et al. (2019) learning to enhance safety and risk management supported that stuff training along with data quality decision-making (Musiałek & Maksymowicz, 2024; Li et initiatives are critical for improving healthcare delivery al., 2021). Additionally, according to Ntlhakana et al. processes, and for accurate process mining outcomes. (2021) mining industries are using electronic health Big Data Quality Environmental Factors management systems to maintain employee’s records and The study accepted H3 (P=0.014<0.05) – environmental to proactively monitor occupational health diseases, factors, which include external governance, legislation which includes hearing loss and respiratory conditions in and compliance are significantly influencing the the mining environment. enhancement of data quality for BDA within the South Big Data Quality Dimensions African mining OHRM to improve decision-making, as As presented in Table 6, this study accepted the shown in Table 6. These results are supported by Muthelo significance of H5 (P=0.008<0.05) – big data quality et al. (2022), who focused on investigating occupational dimensions, which consist of data availability, health and safety practices and compliance within South cleanliness, imbalanced data, reliability, incompleteness African mining sector, specifically in the province of and quality assurance have influence in enhancing data Limpopo, utilizing principal component analysis. By quality for BDA in the South African mining OHRM to identifying key attributes associated with compliance improve decision-making. This outcome was supported with health and safety standards, this study indirectly by Arikekpar and Bestman (2023), who identified underscores the importance of regulatory adherence in accuracy, completeness and timeliness as main upholding data quality within the OHS context of the components of data quality. In addition, Abburi (2024) mining sector (Muthelo et al., 2022). Moreover, Donkor identified consistency and accessibility as key et al. (2023) further emphasized the significance of dimensions to ensure that data is fit for purpose. complying with safety regulations to mitigate risks and Furthermore, findings by Cresswell et al. (2024) further safeguard workers’ well-being, which can ultimately identified features such relevance and reliability as impact data quality by ensuring precise reporting and relatively defined with major data quality components monitoring of occupational health and safety metrics. such accuracy, timeliness and representativeness. Moreover, Chikosi and Mutezo (2023) identified that According to Luo et al. (2023) there are persistent data occupational health and safety risks are frequently known availability issues impacting the implementation of challenges within the mining industry, which includes the appropriate risk management strategies for effective inefficient organisational governance systems. In decision-making within responsible customs addition, it is important to implement effective data departments guided by risk assessment outcomes. In governance to manage and control data use, enhancing addition, Hermanus (2007) identified the reliability issue data quality, availability, and integrity within in occupational health data as a challenge where there is organizations (Aseeri & Kang, 2022). South African a lack of reporting systems and criteria that are well- mining sector is a very well regulated and governed established such as within developing countries which entity more especially within the areas of occupational includes South Africa (Gheorghe et al., 2022) further health and risk management. According to Rikhotso et al. supported the outcomes through comparison of the (2022), each regulatory compliance is associated with the inconsistent number of loss-of-life cases and incidents as cost, which corresponds to the requirements such as evidence in the assessment of data quality for medical examination, risk assessment and reassessment, underreporting within occupational health and safety. workplace inspections, training programs, workplace control, PPEs and labelling, disposal, offenses and Conclusions penalties, and keeping records. This paper has presented and explored the critical data Big Data Quality Sources quality factors that impact decision making within the Table 6 it shows that H4 (P=0.026<0.05) was accepted mining OHRM. The identified factors been technologial, which indicates that big data sources such as environmental, big data quality dimensions and big data occupational safety systems EHMS, GIS, advanced sources. These findings suggest that SA mining industry monitoring sensors, remote sensing technology, have is well regulated by environmental factors such as influence on data quality enhancement in BDA within the external governance and compliance. Therefore, there is South African mining OHRM for effective decision- a full reliance on big data sources to capture data and making. These results are consistent with the study support effective decision-making within OHRM, 42 International Journal of Science Annals, Vol. 8, No. 2, 2025 рrint ISSN: 2617-2682; online ISSN: 2707-3637; DOI:10.26697/ijsa despite persistent data quality challenges. Furthermore, and Public Health, 16(7), Article 1138. this study imparts big data quality dimensions and https://doi.org/10.3390/ijerph16071138 sources as crucial factors in BDA for effective decision- Arikekpar, F., & Bestman, A. E. (2023). Data quality making in South African mining sector, Occupational management and responsiveness of indigenous oil Health and Risk Management. This study identifies that and gas companies in rivers state, Nigeria. technological factors that hinder high quality data usage Journal of Office and Information Management in the South African mining sector includes reporting (JOIM), 7(1-2), 301–313. https://www.rsu- systems, OHRM Systems and unnderreporting that is joim.org/journal2.html caused by lack of integrations within the systems to be Aseeri, M., & Kang, K. (2022). Big data-oriented influencing data quality for BDA. However, there is a organizational culture and business performance: need to further analyse this factors individually following A socio-technical approach. Problems and a qualitative method to gather indepht insights and Perspectives in Management, 20(4), 52–66. investigate the level of signficance for the organisational https://doi.org/10.21511/ppm.20(4).2022.05 factors, as it was found not sufficient and that led the Bag, S., Srivastava, G., Gupta, S., & Taiga, S. (2021). hypothesis H2 to be rejected. Diffusion of big data analytics innovation in managing natural resources in the African mining Acknowledgments industry. Journal of Global Information The authors would like to acknowledge the sampled Management, 30(6), 1–21. organization and the study participants for their https://doi.org/10.4018/JGIM.297074 contribution in this study. Bauer, G. R., Churchill, S. M., Mahendran, M., Walwyn, C., Lizotte, D., & Villa-Rueda, A. A. (2021). Ethical Approval Intersectionality in quantitative research: A The study obtained ethical clearance from the systematic review of its emergence and institution’s Ethics Committee under applications of theory and methods. SSM – Ref. No. HREC2024=08=001 (ICT). Population Health, 14, Article 100798. https://doi.org/10.1016/j.ssmph.2021.100798 Funding Source Bisschoff, R., & Grobbelaar, S. (2022). Evaluation of The present study was funded by Tshwane University of data-driven decision-making implementation in Technology. the mining industry. South African Journal of Industrial Engineering, 33(3), 218–232. References https://doi.org/10.7166/33-3-2799 Abburi, C. K. (2024). Optimizing big data quality Brouwer, D. H., & Rees, D. (2020). Can the South management for national-scale projects: African milestones for reducing exposure to Strategies and frameworks. International Journal respirable crystalline silica and silicosis be of Intelligent Systems and Applications in achieved and reliably monitored? Frontiers in Engineering, 12(4), 4811–4815. Public Health, 8, Article 107. https://doi.org/10.2139/ssrn.5118713 https://doi.org/10.3389/fpubh.2020.00107 Abd Karim, A. T., & Sejati, A. E. (2021). Evaluation of Cai, L., & Zhu, Y. (2015). The challenges of data quality mining safety management system and data quality assessment in the big data era. implementation in PT. ANTAM UBPN Sultra. Data Science Journal, 14, Article 2. Jurnal Ekonomi, 26(2), 223–238. https://doi.org/10.5334/dsj-2015-002 https://doi.org/10.24912/je.v26i2.747 Chikosi, L. C., & Mutezo, A. T. (2023). Managerial Albers, M. J. (2017). Quantitative data analysis – In the ownership, board gender diversity, occupational graduate curriculum. Journal of Technical health, and safety risk management in an Writing and Communication, 47(2), 215–233. emerging economy. Journal of Governance and https://doi.org/10.1177/0047281617692067 Regulation, 12(1), 230–241. Alnefaie, A., Albogami, S., Asiri, Y., Ahmad, T., https://doi.org/10.22495/jgrv12i1siart3 Alotaibi, S. S., Al-Sanea, M. M., & Althobaiti, H. Chukwuere, J. E. (2021). Theoretical and conceptual (2022). Chimeric antigen receptor T-cells: An framework: A critical part of information systems overview of concepts, applications, limitations, research process and writing. Review of and proposed solutions. Frontiers in International Geographical Education Online, Bioengineering and Biotechnology, 10, Article 11(9), 2678–2683. 797440. https://doi.org/10.3389/fbioe.2022.797440 https://doi.org/10.48047/rigeo.11.09.234 Andrews, R., Wynn, M. T., Vallmuur, K., ter Hofstede, Cresswell, K., Claire, R., Avsar, T. S., Hudson, T., A. H. M., Bosley, E., Elcock, M., & Rashford, S. Purcell, R., Peeters, R., … Colvin, H. (2024). (2019). Leveraging data quality to better prepare PD137 reviewing the health technology for process mining: An approach illustrated assessment and regulatory policy landscape on through analysing road trauma pre-hospital acceptability standards for real-world evidence - retrieval and transport processes in Queensland. Initial findings. International Journal of International Journal of Environmental Research Technology Assessment in Health Care, 40(S1), 43 International Journal of Science Annals, Vol. 8, No. 2, 2025 рrint ISSN: 2617-2682; online ISSN: 2707-3637; DOI:10.26697/ijsa S147–S147. Johnson, D. S., Sihi, D., & Muzellec, L. (2021). https://doi.org/10.1017/S026646232400374X Implementing big data analytics in marketing Declerck, J., Kalra, D., Vander Stichele, R., & Coorevits, departments: Mixing organic and administered P. (2024). Frameworks, dimensions, definitions of approaches to increase data-driven decision aspects, and assessment methods for the appraisal making. Informatics, 8(4), 66. of quality of health data for secondary use: https://doi.org/10.3390/informatics8040066 Comprehensive overview of reviews. JMIR Kivunja, C., & Kuyini, A. B. (2017). Understanding and Medical Informatics, 12, Article e51560. applying research paradigms in educational https://doi.org/10.2196/51560 contexts. International Journal of Higher Donkor, P., Siabi, E. K., Frimpong, K., Mensah, S. K., Education, 6(5), 26–41. Siabi, E. S., & Vuu, C. (2023). Socio- https://doi.org/10.5430/ijhe.v6n5p26 demographic effects on role assignment and Krejcie, R. V., & Morgan, D. W. (1970). Determining associated occupational health and safety issues in sample size for research activities. Educational artisanal and small-scale gold mining in Ghana. and Psychological Measurement, 30(3), 607–610. Heliyon, 9(1), Article e13741. https://doi.org/10.1177/001316447003000308 https://doi.org/10.1016/j.heliyon.2023.e13741 Kumar, D., & Bhattacharjee, R. M. (2023). Reducing Famure, O., Anderson, B. K., Atienza, J., Lena, E. R., & workplace unsafe behaviour using risk Singh, S. K. (2019). Standardization and classification, profiling, risk tolerance approach. alignment of data capture practices to clinical Heliyon, 9(3), Article e13969. processes in the evaluation of living kidney donor https://doi.org/10.1016/j.heliyon.2023.e13969 candidates. Healthcare Management Forum, Kuo, M. H., Sahama, T., Kushniruk, A. W., Borycki, E. 32(4), 202–207. M., & Grunwell, D. K. (2014). Health big data https://doi.org/10.1177/0840470419843672 analytics: Current perspectives, challenges and Feng, M., Zheng, J., Ren, J., Hussain, A., Li, X., Xi, Y., potential solutions. International Journal of Big & Liu, Q. (2019). Big data analytics and mining Data Intelligence, 1(1), 114–126. for effective visualization and trends forecasting https://doi.org/10.1504/IJBDI.2014.063835 of crime data. IEEE Access, 7, 106111–106123. Li, H., Huang, W., Zha, Z., & Yang, J. (2021). https://doi.org/10.1109/ACCESS.2019.2930410 Application and platform design of geospatial big Feng, T., Zhang, X., Tan, L., Su, Y., & Liu, H. (2022). data. International Archives of the Near-miss organizational learning in nursing Photogrammetry, Remote Sensing and Spatial within a tertiary hospital: A mixed methods study. Information Sciences, XLIII-B4-2021, 293–300. BMC Nursing, 21(1), Article 315. https://doi.org/10.5194/isprs-archives-XLIII-B4- https://doi.org/10.1186/s12912-022-01071-1 2021-293-2021 Franke, F., & Hiebl, M. R. W. (2022). Big data and Lim, S., Saldanha, T. J. V., Malladi, S., & Melville, N. P. decision quality: The role of management (2013). Theories used in information systems accountants’ data analytics skills. International research: Insights from complex network Journal of Accounting & Information analysis. Journal of Information Technology Management, 31(1), 93–127. Theory and Application, 14(2), 5–46. https://doi.org/10.1108/IJAIM-12-2021-0246 https://aisel.aisnet.org/jitta/vol14/iss2/2 Gheorghe, G. C., Manrique-Hernandez, E. F., & Idrovo, Luo, N., Yu, H., You, Z., Li, Y., Zhou, T., Jiao, Y., Han, A. J. (2022). Injuries and fatalities in Colombian N., Liu, C., Jiang, Z., & Qiao, S. (2023). Fuzzy mining emergencies (2005–2018): A logic- and neural network-based risk assessment retrospective ecological study. Revista Brasileira model for import and export enterprises: A de Medicina do Trabalho, 20(4), 591–598. review. Journal of Data Science and Intelligent https://doi.org/10.47626/1679-4435-2022-799 Systems, 1(1), 2-11. Haas, E. J. (2020). The role of supervisory support on https://doi.org/10.47852/bonviewJDSIS32021078 workers’ health and safety performance. Health Maroun, W. (2019). Exploring the rationale for Communication, 35(3), 364–374. integrated report assurance. Accounting, Auditing https://doi.org/10.1080/10410236.2018.1563033 & Accountability Journal, 32(6), 1826–1854. Hariri, R. H., Fredericks, E. M., & Bowers, K. M. (2019). https://doi.org/10.1108/AAAJ-04-2018-3463 Uncertainty in big data analytics: Survey, Mishra, P. C., & Mishra, P. K. (2023). Challenges and opportunities, and challenges. Journal of Big opportunities of big data analytics for human Data, 6(1), 1-16. https://doi.org/10.1186/s40537- resource management in mining and metal 019-0206-3 industries. Journal of Mines, Metals and Fuels, Hermanus, M. (2007). Occupational health and safety in 71(10), 1747–1753. mining – Status, new developments, and https://doi.org/10.18311/jmmf/2023/35858 concerns. Journal of the Southern African Montisci, A., Palmieri, V., Vietri, M. T., Sala, S., Institute of Mining and Metallurgy, 107(8), 531– Maiello, C., Donatelli, F., & Napoli, C. (2022). 538. https://hdl.handle.net/10520/AJA0038223X_3 Big data in cardiac surgery: Real world and 264 perspectives. Journal of Cardiothoracic Surgery, 44 International Journal of Science Annals, Vol. 8, No. 2, 2025 рrint ISSN: 2617-2682; online ISSN: 2707-3637; DOI:10.26697/ijsa 17(1), Article 277. Science, 150(2), Article 105707. https://doi.org/10.1186/s13019-022-02025-z https://doi.org/10.1016/j.ssci.2022.105707 Moroe, N., Khoza-Shangase, K., Madahana, M., & Sarstedt, M., & Mooi, E. (2018). A concise guide to Nyandoro, O. (2019). A proposed preliminary market research: The process, data, and methods model for monitoring hearing conservation using IBM SPSS Statistics. Springer. programmes in the mining sector in South Africa. https://doi.org/10.1007/978-3-642-12541-6 Journal of the Southern African Institute of Segooa, A. M., & Kalema, B. M. (2024). Big data Mining and Metallurgy, 119(7), 671-679. analytics artefact for outcome-based funding https://doi.org/10.17159/2411-9717/18/016/2019 prediction in South African public universities. Muhunzi, D., Kitambala, L., & Mashauri, H. (2023). Big International Journal of Service Science, data analytics in the healthcare sector: Management, Engineering, and Technology, Opportunities and challenges in developing 15(1), 1–27. countries: A literature review. Health Informatics https://doi.org/10.4018/IJSSMET.334220 Journal, 30(4). Stojanović, A., Milošević, I., & Nikolić, Đ. (2024). https://doi.org/10.1177/14604582241294217 Developing a novel quantitative approach to Musiałek, M., & Maksymowicz, M. (2024). Remote evaluate the organizational factors affecting sensing in mining: A brief overview and occupational health and safety in the mining examples. Górnictwo Odkrywkowe – Opencast industry. In XIX International May Conference on Mining, 65(3), 4–14. Strategic Management – IMCSM24 Proceedings, https://doi.org/10.5604/01.3001.0055.0491 20(1), 60–68. Muthelo, L., Mothiba, T. M., Malema, N. R., Mbombi, https://doi.org/10.5937/IMCSM24006S M. O., & Mphekgwana, P. M. (2022). Exploring Taber, K. S. (2018). The use of Cronbach’s alpha when occupational health and safety standards developing and reporting research instruments in compliance in the South African mining industry, science education. Research in Science Limpopo Province, using principal component Education, 48(6), 1273–1296. analysis. International Journal of Environmental https://doi.org/10.1007/s11165-016-9602-2 Research and Public Health, 19(16), Article Tylečková, E., & Noskievičová, D. (2020). The role of 10241. https://doi.org/10.3390/ijerph191610241 big data in Industry 4.0 in the mining industry in Nazari, E., Ebnehoseini, Z., Agharezaei, Z., & Tabesh, Serbia. System Safety: Human – Technical H. (2020). Knowledge, attitude, and challenges of Facility – Environment, 2(1), 166–173. big data analytics based on IT staffs point of view https://doi.org/10.2478/czoto-2020-0020 in a developing country. Frontiers in Health Ullah, F., Qayyum, S., Thaheem, M. J., Al-Turjman, F., Informatics, 9(1), Article 36. & Sepasgozar, S. M. E. (2021). Risk management https://doi.org/10.30699/fhi.v9i1.225 in sustainable smart cities governance: A TOE Ntlhakana, L., Nelson, G., Khoza-Shangase, K., & framework. Technological Forecasting and Dorkin, E. (2021). Occupational hearing loss for Social Change, 167, Article 120743. platinum miners in South Africa: A case study of https://doi.org/10.1016/j.techfore.2021.120743 data sharing practices and ethical challenges in the Van Rensburg, H. M. M. J., Gous, A. G. S., Vosloo, J. mining industry. International Journal of C., & Van Heerden, M. (2019). Improving data Environmental Research and Public Health, management for environmental reporting in the 19(1), Article 1. gold mining industry. South African Journal of https://doi.org/10.3390/ijerph19010001 Industrial Engineering, 30(3), 163–173. Pypenko, I. S. (2019). Digital product: The essence of the https://doi.org/10.7166/30-3-2236 concept and scopes. International Journal of Vassakis, K., Petrakis, E., & Kopanakis, I. (2018). Big Education and Science, 2(4), 56. data analytics: Applications, prospects and https://doi.org/10.26697/ijes.2019.4.41 challenges. In G. Skourletopoulos, G. Mastorakis, Pypenko, I. S., & Melnyk, Yu. B. (2021). Principles of C. Mavromoustakis, C. Dobre, & E. Pallis (Eds.), digitalisation of the state economy. International Mobile Big Data: Lecture Notes on Data Journal of Education and Science, 4(1), 42-50. Engineering and Communications Technologies, https://doi.org/10.26697/ijes.2021.1.5 10 (pp. 3–20). Springer. Rangineni, S., Bhanushali, A., Suryadevara, M., https://doi.org/10.1007/978-3-319-67925-9_1 Venkata, S., & Peddireddy, K. (2023). A review Wang, J., Liu, Y., Li, P., Lin, Z., Sindakis, S., & on enhancing data quality for optimal data Aggarwal, S. (2023). Overview of data quality: analytics performance. International Journal of Examining the dimensions, antecedents, and Computer Sciences and Engineering, 11(10), 51– impacts of data quality. Journal of the Knowledge 58. https://doi.org/10.26438/ijcse/v11i10.5158 Economy, 15, 1159–1178. Rikhotso, O., Morodi, T. J., & Masekameni, D. M. https://doi.org/10.1007/s13132-022-01096-6 (2022). Health risk management cost items Wardhani, M. K., Setioko, B., & Pandelaki, E. E. (2021). imposed by occupational health and safety Village spatial planning based on its potential as regulations: A South African perspective. Safety guidelines for guided and sustainable village 45 International Journal of Science Annals, Vol. 8, No. 2, 2025 рrint ISSN: 2617-2682; online ISSN: 2707-3637; DOI:10.26697/ijsa development. Tataloka, 23(2), 171–182. Zhou, L. J., Cao, Q. G., Yu, K., Wang, L. L., & Wang, H. https://doi.org/10.14710/tataloka.23.2.171-182 B. (2018). Research on occupational safety, health Yang, L., Birhane, G. E., Zhu, J., & Geng, J. (2021). management and risk control technology in coal Mining employees’ safety and the application of mines. International Journal of Environmental information technology in coal mining: Review. Research and Public Health, 15(5), Article 868. Frontiers in Public Health, 9, Article 709987. https://doi.org/10.3390/ijerph15050868 https://doi.org/10.3389/fpubh.2021.709987 Cite this article as: Lephoto, N., Segooa, M. A., Motjolopane, I., & Seaba, T. R. (2025). Data quality factors for big data analytics in occupational health and risk management. International Journal of Science Annals, 8(2), 36–46. https://doi.org/10.26697/ijsa.2025.2.5 The electronic version of this article is complete. It can be found online in the IJSA Archive https://ijsa.culturehealth.org/en/arhiv This is an Open Access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited (http://creativecommons.org/licenses/by/4.0/deed.en). 46