WLWilson Lukmanjaya

Wilson Lukmanjaya

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Wilson Lukmanjaya has a total of 23 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Protocol for a Feasibility Study of Computational Text Analysis of Child Protection Intake Reports in South Australia (Preprint)

    by Wilson Lukmanjaya, Sarah Cox, Tony Butler, Oscar Perez-Concha, Leah Bromfield, Olivia Octoman, Amy Bromley, George Karystianis

    UNSTRUCTURED Background: Child maltreatment statistics collected using surveys, in-depth interviews, and manual case reviews are limited in scope due to resource constraints and labour-intensive, non-scalable approaches. The advent of computational advancements such as natural language processing, text mining, and large language models opens up the possibility of rapidly analysing vast numbers of documents from child protection client information systems to generate useful information. However, often due to strict data access protocols, few research efforts have focused on the application of computational text analysis in the child maltreatment area. Objective: This study presents a protocol for the application and evaluation of a text mining method on 10,000 child protection intake reports from South Australia’s Department for Child Protection. Methods: The protocol is split into five phases: 1) Ethics, governance, and data access approvals; 2A) Establish gold standard for the automatic extraction of information from 100 redacted reports using manual expert annotation; 2B) Contextual de-identification to preserve relationships; 3) Text mining method development, validation and evaluation based on 300 reports; 4) Text mining application on large sample; and 5) Evaluation and data analysis. Discussion: This protocol describes a feasibility study applying computational text analysis to highly sensitive child protection reports to automatically extract key information. Key considerations and challenges included governance, ethics, security, and technical requirements across multiple stakeholders involved in the study and adapting the text mining methodology to address the loss of contextual information caused by redaction. Conclusion: Whilst a high level of trust between academics and the government sector and stringent data safety protocols are necessary, text mining child protection intake reports in Australia is possible with the potential to unlock valuable insights.

  • Open Access

    Correction: De-identification of child protection intake reports using relationship-based replacement (DI-REBAR)

    by Wilson Lukmanjaya, Sarah Cox, Oscar Perez-Concha, Tony Butler, Leah Bromfield, George Karystianis

    Correction on: Lukmanjaya W, Cox S, Perez-Concha O, Butler T, Bromfield L and Karystianis G (2026) De-identification of child protection intake reports using relationship-based replacement (DI-REBAR). Front. Digit. Health 8:1949307. doi: 10.3389/fdgth.2026.1949307 Wrong content There was a mistake in Table 1 as published. The column "Examples of redacted notification data" have identifying information examples (i.e., "Jane Doe", "John", and "John Doe Jr") bolded. The correct format is to have them highlighted in black to simulate redaction (i.e., "Jane Doe") or a redacted label as an alternative format (i.e., [REDACTED]). The original version of this article has been updated.

  • Open Access

    De-identification of child protection intake reports using relationship-based replacement (DI-REBAR)

    by Wilson Lukmanjaya, Sarah Cox, Oscar Perez-Concha, Tony Butler, Leah Bromfield, George Karystianis

    Background: Child protection contacts are documented in the form of child protection intake reports detailing the child(ren) suspected to be at risk of harm, the notifier's concerns, the alleged person responsible, and other details. These narrative reports remain untapped for statistical reporting and research purposes due to being text-based as well as containing extremely sensitive content. Applying a contextual de-identification approach to child protection narratives opens up the possibility of large-scale automated analysis by external researchers while preserving data privacy and relational meaning. Data: 10,000 randomly selected South Australian Department for Child Protection intake reports were provided for this study. A total of 300 (200 development, 100 evaluation) were randomly selected, manually reviewed and annotated. Methods: We designed and implemented a context-preserving de-identification pipeline called De-Identification via Relationship-Based Replacement (DI-REBAR) on 10,000 reports while preserving the noted relationships between named individuals. A total of seven indirect identifiers (date, time, school, early learning centre, hospital, prison, sensitive reference numbers) and three direct identifiers (name, address, phone number) were selected for de-identification. A relationship table was temporarily created to map individuals and their relationship to the child of interest, with direct identifiers replaced. Indirect identifiers were replaced by list-based replacement and regular expressions. Results: DI-REBAR evaluation showed promising results in macro precision (>0.98), recall (>0.88), and F1-Score (>0.92) across nine out of the ten identifier classes (prison excluded). Each identifier had a range of precision (0.74-1.00), recall (0.61-1.00), and F1-Score (0.66-1.00). Address, phone number, and date have the best performances (>0.98) across precision, recall, and F1-Score. Conclusion: This is the first Australian study to automatically de-identify sensitive child protection data whilst preserving relationship information, allowing large-scale text analysis by external researchers in a data custodian's controlled environment. This approach can be applied to other areas that rely on unstructured data such as court documents and police reports. However, human reviewers are still needed to ensure identifiable information is not disclosed.

  • Open Access

    Computational text analysis on unstructured police data: a scoping review

    by Wilson Lukmanjaya, Christina Halmich, Tony Butler, Darren Cook, George Karystianis


  • Open Access

    Leveraging AI to Investigate Child Maltreatment Text Narratives: Promising Benefits and Addressable Risks

    by Wilson Lukmanjaya, Tony Butler, Sarah Cox, Oscar Perez-Concha, Leah Bromfield, George Karystianis

    The trove of information contained in child maltreatment narratives represents an opportunity to strengthen the evidence base for policy reform in this area, yet it remains underutilized by researchers and policy makers. Current research into child maltreatment often involves the use of qualitative methodologies or structured survey data that are either too broad or not representative, thereby limiting the development of effective policy responses and intervention strategies. Artificial intelligence (AI) approaches such as large language models (AI models that understand and generate language) can analyze large volumes of child maltreatment narratives by extracting population-level insights on factors of interest such as mental health and treatment needs. However, when applying such methods, it is useful to have a framework on which to base approaches to the data. We propose a seven step framework: (1) data governance; (2) researcher vetting; (3) data deidentification; (4) data access; (5) feasibility testing of baseline methods; (6) large-scale implementation of black box algorithms; and (7) domain expert result validation for such exercises to ensure careful execution and limit the risk of privacy and security breaches, bias, and unreliable conclusions.


  • Open Access

    Leveraging AI to Investigate Child Maltreatment Text Narratives: Promising Benefits and Addressable Risks (Preprint)

    by Wilson Lukmanjaya, Tony Butler, Sarah Cox, Oscar Perez-Concha, Leah Bromfield, George Karystianis

    UNSTRUCTURED The use of child maltreatment text narratives represents an opportunity to strengthen the evidence base for child policy reform, yet they remain underutilized. Current research into child maltreatment often involves the use of structured data, potentially overlooking key details within the narratives that can be crucial to assist in developing effective interventions. Artificial Intelligence approaches such as large language models can assist in the large-scale analysis of child maltreatment narratives extracting useful population-level insights on indicators of mental health, and treatment needs. However, when applying such methods, a framework of five key steps can assist in their careful implementation to reduce risks of privacy and bias.

  • Open Access

    Population Characteristics in Justice Health Research Based on PubMed Abstracts From 1963 to 2023: Text Mining Study

    by Wilson Lukmanjaya, Tony Butler, Patricia Taflan, Paul Simpson, Natasha Ginnivan, Iain Buchan, Goran Nenadic, George Karystianis

    Background: The field of epidemiological criminology (or justice health research) has emerged in the past decade, studying the intersection between the public health and justice systems. To ensure research efforts are focused and equitable, it is important to reflect on the outputs in this area and address knowledge gaps. Objective: This study aimed to examine the characteristics of populations researched in a large sample of published outputs and identify research gaps and biases. Methods: A rule-based, text mining method was applied to 34,481 PubMed abstracts published from 1963 to 2023 to identify 4 population characteristics (sex, age, offender type, and nationality). Results: We evaluated our method in a random sample of 100 PubMed abstracts. Microprecision was 94.3%, with microrecall at 85.9% and micro–F1-score at 89.9% across the 4 characteristics. Half (n=17,039, 49.4%) of the 34,481 abstracts did not have any characteristic mentions and only 1.3% (n=443) reported sex, age, offender type, and nationality. From the 5170 (14.9%) abstracts that reported age, 3581 (69.3%) mentioned young people (younger than 18 years) and 3037 (58.7%) mentioned adults. Since 1990, studies reporting female-only populations increased, and in 2023, these accounted for almost half (105/216, 48.6%) of the research outputs, as opposed to 33.3% (72/216) for male-only populations. Nordic countries (Sweden, Norway, Finland, and Denmark) had the highest number of abstracts proportional to their incarcerated populations. Offenders with mental illness were the most common group of interest (840/4814, 17.4%), with an increase from 1990 onward. Conclusions: Research reporting on female populations increased, surpassing that involving male individuals, despite female individuals representing 5% of the incarcerated population; this suggests that male prisoners are underresearched. Although calls have been made for the justice health area to focus more on young people, our results showed that among the abstracts reporting age, most mentioned a population aged <18 years, reflecting a rise of youth involvement in the youth justice system. Those convicted of sex offenses and crimes relating to children were not as researched as the existing literature suggests, with a focus instead on populations with mental illness, whose rates rose steadily in the last 30 years. After adjusting for the size of the incarcerated population, Nordic countries have conducted proportionately the most research. Our findings highlight that despite the presence of several research reporting guidelines, justice health abstracts still do not adequately describe the investigated populations. Our study offers new insights in the field of justice health with implications for promoting diversity in the selection of research participants.


  • Open Access

    Population characteristics in justice health research based on PubMed abstracts from 1963 to 2023: text mining study

    by Wilson Lukmanjaya, Tony Butler, Patricia Taflan, Paul Simpson, Natasha Ginnivan, Iain Buchan, Goran Nenadic, George Karystianis

    BACKGROUND The field of epidemiological criminology (or justice health research) has emerged in the past decade, studying the intersection between the public health and justice systems. To ensure research efforts are focused and equitable, it is important to reflect on the outputs in this area and address knowledge gaps. OBJECTIVE This study aimed to examine the characteristics of populations researched in a large sample of published outputs and identify research gaps and biases. METHODS A rule-based, text mining method was applied to 34,481 PubMed abstracts published from 1963 to 2023 to identify 4 population characteristics (sex, age, offender type, and nationality). RESULTS We evaluated our method in a random sample of 100 PubMed abstracts. Microprecision was 94.3%, with microrecall at 85.9% and micro–F1-score at 89.9% across the 4 characteristics. Half (n=17,039, 49.4%) of the 34,481 abstracts did not have any characteristic mentions and only 1.3% (n=443) reported sex, age, offender type, and nationality. From the 5170 (14.9%) abstracts that reported age, 3581 (69.3%) mentioned young people (younger than 18 years) and 3037 (58.7%) mentioned adults. Since 1990, studies reporting female-only populations increased, and in 2023, these accounted for almost half (105/216, 48.6%) of the research outputs, as opposed to 33.3% (72/216) for male-only populations. Nordic countries (Sweden, Norway, Finland, and Denmark) had the highest number of abstracts proportional to their incarcerated populations. Offenders with mental illness were the most common group of interest (840/4814, 17.4%), with an increase from 1990 onward. CONCLUSIONS Research reporting on female populations increased, surpassing that involving male individuals, despite female individuals representing 5% of the incarcerated population; this suggests that male prisoners are underresearched. Although calls have been made for the justice health area to focus more on young people, our results showed that among the abstracts reporting age, most mentioned a population aged <18 years, reflecting a rise of youth involvement in the youth justice system. Those convicted of sex offenses and crimes relating to children were not as researched as the existing literature suggests, with a focus instead on populations with mental illness, whose rates rose steadily in the last 30 years. After adjusting for the size of the incarcerated population, Nordic countries have conducted proportionately the most research. Our findings highlight that despite the presence of several research reporting guidelines, justice health abstracts still do not adequately describe the investigated populations. Our study offers new insights in the field of justice health with implications for promoting diversity in the selection of research participants.

  • Open Access

    Automatic extraction of research themes in epidemiological criminology from PubMed abstracts from 1946 to 2020: text mining study

    by George Karystianis, Paul Simpson, Wilson Lukmanjaya, Natasha Ginnivan, Goran Nenadic, Iain Buchan, Tony Butler

    Background: The emerging field of epidemiological criminology studies the intersection between public health and justice systems. To increase the value of and reduce waste in research activities in this area, it is important to perform transparent research priority setting considering the needs of research beneficiaries and end users along with a systematic assessment of the existing research activities to address gaps and harness opportunities. Objective: In this study, we aimed to examine published research outputs in epidemiological criminology to assess gaps between published outputs and current research priorities identified by prison stakeholders. Methods: A rule-based method was applied to 23,904 PubMed epidemiological criminology abstracts to extract the study determinants and outcomes (ie, “themes”). These were mapped against the research priorities identified by Australian prison stakeholders to assess the differences from research outputs. The income level of the affiliation country of the first authors was also identified to compare the ranking of research priorities in countries categorized by income levels. Results: On an evaluation set of 100 abstracts, the identification of themes returned an F1-score of 90%, indicating reliable performance. More than 53.3% (11,927/22,361) of the articles had at least 1 extracted theme; the most common was substance use (1533/11,814, 12.97%), followed by HIV (1493/11,814, 12.64%). The infectious disease category (2949/11,814, 24.96%) was the most common research priority category, followed by mental health (2840/11,814, 24.04%) and alcohol and other drug use (2433/11,814, 20.59%). A comparison between the extracted themes and the stakeholder priorities showed an alignment for mental health, infectious diseases, and alcohol and other drug use. Although behavior- and juvenile-related themes were common, they did not feature as prison priorities. Most studies were conducted in high-income countries (10,083/11,814, 85.35%), while countries with the lowest income status focused half of their research on infectious diseases (47/91, 52%). Conclusions: The identification of research themes from PubMed epidemiological criminology research abstracts is possible through the application of a rule-based text mining method. The frequency of the investigated themes may reflect historical developments concerning disease prevalence, treatment advances, and the social understanding of illness and incarcerated populations. The differences between income status groups are likely to be explained by local health priorities and immediate health risks. Notable gaps between stakeholder research priorities and research outputs concerned themes that were more focused on social factors and systems and may reflect publication bias or self-publication selection, highlighting the need for further research on prison health services and the social determinants of health. Different jurisdictions, countries, and regions should undertake similar systematic and transparent research priority–setting processes.


  • Open Access

    Automatic extraction of research themes in epidemiological criminology from PubMed abstracts from 1946 to 2020: text mining study

    by George Karystianis, Paul Simpson, Wilson Lukmanjaya, Natasha Ginnivan, Goran Nenadic, Iain Buchan, Tony Butler

    BACKGROUND The emerging field of epidemiological criminology studies the intersection between public health and justice systems. To increase the value of and reduce waste in research activities in this area, it is important to perform transparent research priority setting considering the needs of research beneficiaries and end users along with a systematic assessment of the existing research activities to address gaps and harness opportunities. OBJECTIVE In this study, we aimed to examine published research outputs in epidemiological criminology to assess gaps between published outputs and current research priorities identified by prison stakeholders. METHODS A rule-based method was applied to 23,904 PubMed epidemiological criminology abstracts to extract the study determinants and outcomes (ie, “themes”). These were mapped against the research priorities identified by Australian prison stakeholders to assess the differences from research outputs. The income level of the affiliation country of the first authors was also identified to compare the ranking of research priorities in countries categorized by income levels. RESULTS On an evaluation set of 100 abstracts, the identification of themes returned an F1-score of 90%, indicating reliable performance. More than 53.3% (11,927/22,361) of the articles had at least 1 extracted theme; the most common was substance use (1533/11,814, 12.97%), followed by HIV (1493/11,814, 12.64%). The infectious disease category (2949/11,814, 24.96%) was the most common research priority category, followed by mental health (2840/11,814, 24.04%) and alcohol and other drug use (2433/11,814, 20.59%). A comparison between the extracted themes and the stakeholder priorities showed an alignment for mental health, infectious diseases, and alcohol and other drug use. Although behavior- and juvenile-related themes were common, they did not feature as prison priorities. Most studies were conducted in high-income countries (10,083/11,814, 85.35%), while countries with the lowest income status focused half of their research on infectious diseases (47/91, 52%). CONCLUSIONS The identification of research themes from PubMed epidemiological criminology research abstracts is possible through the application of a rule-based text mining method. The frequency of the investigated themes may reflect historical developments concerning disease prevalence, treatment advances, and the social understanding of illness and incarcerated populations. The differences between income status groups are likely to be explained by local health priorities and immediate health risks. Notable gaps between stakeholder research priorities and research outputs concerned themes that were more focused on social factors and systems and may reflect publication bias or self-publication selection, highlighting the need for further research on prison health services and the social determinants of health. Different jurisdictions, countries, and regions should undertake similar systematic and transparent research priority–setting processes. CLINICALTRIAL