[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-1-en-105":3,"doc-seo-253435-105":53,"doc-detail-253435-en":127},{"code":4,"msg":5,"data":6},0,"success",[7,14,19,24,29,34,39,44,49],{"id":8,"doc_module":9,"doc_module_name":10,"category_name":11,"show_sort_weight":12,"slug":13},11,1,"Template","Presentations",90,"presentations",{"id":15,"doc_module":9,"doc_module_name":10,"category_name":16,"show_sort_weight":17,"slug":18},12,"Resumes",80,"resumes",{"id":20,"doc_module":9,"doc_module_name":10,"category_name":21,"show_sort_weight":22,"slug":23},14,"Invoices",70,"invoices",{"id":25,"doc_module":9,"doc_module_name":10,"category_name":26,"show_sort_weight":27,"slug":28},15,"Posters",60,"posters",{"id":30,"doc_module":9,"doc_module_name":10,"category_name":31,"show_sort_weight":32,"slug":33},16,"Social Media",50,"social-media",{"id":35,"doc_module":9,"doc_module_name":10,"category_name":36,"show_sort_weight":37,"slug":38},17,"Forms",40,"forms",{"id":40,"doc_module":9,"doc_module_name":10,"category_name":41,"show_sort_weight":42,"slug":43},18,"Letters",30,"letters",{"id":45,"doc_module":9,"doc_module_name":10,"category_name":46,"show_sort_weight":47,"slug":48},21,"Paper Templates",5,"papers-templates",{"id":50,"doc_module":9,"doc_module_name":10,"category_name":51,"show_sort_weight":4,"slug":52},158,"General","general-158",{"code":4,"msg":54,"data":55},"ok",{"site_id":56,"language":57,"slug":58,"title":59,"keywords":60,"description":61,"schema_data":62,"social_meta":120,"head_meta":122,"extra_data":124,"updated_unix":126},105,"en","safety-report-topic-classification-with-transformer-based-data-augmentation","Safety Report Topic Classification with Transformer-based Data Augmentation","","Safety Leading Indicators (SLIs) are incident traits, often called weak signals, that enable organizations to take proactive actions by continuously tracking them. This research develops an implementation approach using topic classification of safety reports without enforcing a mandatory reporting format, reducing complexity and limiting opportunities for KPI exploitation or manipulation. The method supports low-resource, unlabelled settings, is independent of reporting systems and taxonomies, and uses rule-based multi-label SLI categorization followed by Transformer-based data augmentation and Bi-LSTM training to improve topic classification accuracy.",{"@graph":63,"@context":119},[64,80,102],{"@type":65,"itemListElement":66},"BreadcrumbList",[67,71,74,77],{"item":68,"name":69,"@type":70,"position":9},"https://docshare.wps.com","Home","ListItem",{"item":72,"name":10,"@type":70,"position":73},"https://docshare.wps.com/template/",2,{"item":75,"name":11,"@type":70,"position":76},"https://docshare.wps.com/template/presentations/",3,{"item":78,"name":59,"@type":70,"position":79},"https://docshare.wps.com/template/safety-report-topic-classification-with-transformer-based-data-augmentation/253435/",4,{"url":78,"name":59,"@type":81,"image":82,"author":87,"headline":59,"publisher":90,"fileFormat":93,"inLanguage":57,"description":61,"dateModified":94,"datePublished":95,"encodingFormat":93,"isAccessibleForFree":96,"interactionStatistic":97},"DigitalDocument",{"url":83,"@type":84,"width":85,"height":86},"https://docshare.wps.com/thumbnails/safety-report-topic-classification-with-transformer-based-data-augmentation/253435.png","ImageObject",442,249,{"name":88,"@type":89},"Bintang","Person",{"url":68,"name":91,"@type":92},"DocShare","Organization","application/pdf","2026-10-30","2026-09-13",true,{"@type":98,"interactionType":99,"userInteractionCount":101},"InteractionCounter",{"@type":100},"ViewAction",6,{"@type":103,"mainEntity":104},"FAQPage",[105,111,115],{"name":106,"@type":107,"acceptedAnswer":108},"What problem does the research address in safety reporting?","Question",{"text":109,"@type":110},"The work targets the challenge of detecting Safety Leading Indicators (SLIs) from free-text safety/incident reports, where reporting formats and topic categories are not standardized.","Answer",{"name":112,"@type":107,"acceptedAnswer":113},"How does the proposed method implement SLI detection without labeled data?",{"text":114,"@type":110},"It first creates labeled SLI categories using a new multi-label rule-based approach on unlabelled reports, then fine-tunes pre-trained language models and trains supervised topic classifiers using Transformer-based Data Augmentation combined with conventional text augmentation.",{"name":116,"@type":107,"acceptedAnswer":117},"Why is Transformer-based Data Augmentation important in this project?",{"text":118,"@type":110},"Transformer-based Data Augmentation (TrDA) helps generate improved training data for supervised topic classifiers in low and unlabelled data regimes, leading to better performance on unseen safety reports than the upstream rule-based methods.","https://schema.org",{"og:url":78,"og:type":121,"og:title":59,"og:site_name":91,"og:description":61},"article",{"robots":123,"canonical":78},"index,follow",{"doc_id":125,"site_id":56},253435,1792342644,{"code":4,"msg":5,"data":128},{"doc_id":125,"user_id":129,"nickname":88,"user_avatar":130,"doc_module":9,"category_id":8,"category_name":11,"doc_title":59,"doc_description":61,"doc_content":131,"file_id":132,"file_url":133,"file_type":134,"file_size":135,"view_count":101,"is_deleted":4,"is_public":9,"is_downloadable":9,"audit_status":9,"page_count":136,"language":137,"language_code":57,"site_id":56,"html_lang":57,"table_of_contents":138,"faqs":139,"seo_title":140,"seo_description":61,"update_tm":141,"read_time":142},962085564381,"https://ap-avatar.wpscdn.com/davatar_6f874abed73319feea01a86fa6f0fab8","Safety Report Topic Classification with Transformer-based Data Augmentation  \nMSc Research Project Data Analytics  \nJason Payne  \nStudent ID: 2018543  \nSchool of Computing National College of Ireland  \nSupervisor: Muhammad Zahid Iqbal  \nNational College of Ireland Project Submission Sheet School of Computing  \n| Student Name: | Jason Payne |\n| --- | --- |\n| Student ID: | 2018543 |\n| Programme: | Data Analytics |\n| Year: | 2022 |\n| Module: | MSc Research Project |\n| Supervisor: | Muhammad Zahid Iqbal |\n| Submission Due Date: | 15/12/2022 |\n| Project Title: | Safety Report Topic Classification with Transformer-based Data Augmentation |\n| Word Count: | 6,582 |\n| Page Count: | 23 |\n\nI hereby certify that the information contained in this (my submission) is information pertaining to research I conducted for this project. All information other than my own contribution will be fully referenced and listed in the relevant bibliography section at the rear of the project.  \nALL internet material must be referenced in the bibliography section. Students are required to use the Referencing Standard specified in the report template. To use other author’s written or electronic work is illegal (plagiarism) and may result in disciplinary action.  \n\n| Signature: | |\n| --- | --- |\n| Date: | 13th December 2022 |\n\nPLEASE READ THE FOLLOWING INSTRUCTIONS AND CHECKLIST:  \n\n| Attach a completed copy of this sheet to each project (including multiple copies) . | ⇤ |\n| --- | --- |\n| Attach a Moodle submission receipt of the online project submission, to each project (including multiple copies) . | ⇤ |\n| You must ensure that you retain a HARD COPY of the project, both foryour own reference and in case a project is lost or mislaid. It is not sufficient to keep a copy on computer. | ⇤ |\n\nAssignments that are submitted to the Programme Coordinator office must be placed into the assignment box located outside the office.  \n\n| Office Use Only |  |\n| --- | --- |\n| Signature: |  |\n| Date: |  |\n| Penalty Applied (if applicable): |  |\n\nSafety Report Topic Classification with Transformer-based Data Augmentation  \nJason Payne  \n2018543  \nAbstract  \nSafety Leading Indicators (SLIs) are incident traits, sometimes referred to as weak signals, that, when tracked, enable organisations to proactively plan actions to mitigate significant incident occurrences. This research presents an implementation method for SLIs based on topic classification of safety reports. Rather than imposing a mandatory reporting format, indirect implementation based on text/content analysis significantly reduces implementation complexity and potential for KPI exploitation/manipulation. The method works in low and unlabelled data regimes and is independent of reporting systems, formats and taxonomies. A new multi-label rule-based approach was developed to assign crafted SLI categories to unlabeled safety reports. This labelled data was then used to fine-tune pre-trained Language Models (LMs) for advanced Transformer-based Data Augmentation (TrDA) . TrDA was combined with conventional text augmentation techniques to train performant supervised topic classifiers using Bidirectional LSTM (Bi-LSTM) models. The Bi-LSTM models were shown to outperform the upstream rule-based methods on new/unseen data. The proposed methodology is organisation and process agnostic, and the solution is practically deployable via commonly available cloud services.  \n1 Introduction  \nIn the construction industry, safety/incident reports are formal records of HSE-related accidents, incidents or near-misses in the workplace. Reports aim to capture the pertinent aspects of incidents so that root cause analysis can be performed and the organisation’s safety performance can be documented per relevant regulatory requirements. Reports are collected digitally, either using proprietary software applications or spreadsheets. While format varies, and no standard categories are applied, common elements of each report include incident contextual informat","cbCais0kVHABBmjF","https://ap.wps.com/l/cbCais0kVHABBmjF","pdf",2995319,25,"English","# Abstract\n## Introduction\n## Research Question, Objectives and Contributions","[{\"question\":\"What problem does the research address in safety reporting?\",\"answer\":\"The work targets the challenge of detecting Safety Leading Indicators (SLIs) from free-text safety/incident reports, where reporting formats and topic categories are not standardized.\"},{\"question\":\"How does the proposed method implement SLI detection without labeled data?\",\"answer\":\"It first creates labeled SLI categories using a new multi-label rule-based approach on unlabelled reports, then fine-tunes pre-trained language models and trains supervised topic classifiers using Transformer-based Data Augmentation combined with conventional text augmentation.\"},{\"question\":\"Why is Transformer-based Data Augmentation important in this project?\",\"answer\":\"Transformer-based Data Augmentation (TrDA) helps generate improved training data for supervised topic classifiers in low and unlabelled data regimes, leading to better performance on unseen safety reports than the upstream rule-based methods.\"}]","Safety Report Topic Classification with Transformer-based Data Augmentation | PDF",1789266019,9]