Is this project an undergraduate, graduate, or faculty project?
Graduate
Project Type
group
Campus
Daytona Beach
Authors' Class Standing
Stephanie Ramsey, Graduate student Katherine Hoffsetz, Graduate student Madeline Gorman, Graduate student Logan Lambeth, Graduate student
Lead Presenter's Name
Stephanie Ramsey
Lead Presenter's College
DB College of Arts and Sciences
Faculty Mentor Name
Dr. Gamage Dumindu Samaraweera
Abstract
Understanding the complex causal relationships underlying aviation accidents is critical for improving safety and preventing future incidents. However, much of this information exists in unstructured narrative reports, making large-scale analysis difficult. This project aims to automatically extract and model causal chains from National Transportation Safety Board (NTSB) accident narratives using a combination of traditional natural language processing (NLP) techniques, transformer-based architectures, and graph-based knowledge representation. Traditional NLP methods, including named entity recognition, dependency parsing, and rule-based pattern matching, will be used to identify structured cause–effect relationships. These approaches will be compared with transformer-based models, including a lightweight encoder for classification and embedding generation, as well as large language models for prompt-based causal extraction. The extracted relationships will be used to construct a knowledge graph in Neo4j, enabling visualization and querying of accident pathways and contributing factors such as weather conditions and human error. Preliminary work focuses on data preprocessing and model design, with evaluation comparing extraction accuracy, computational efficiency, and scalability across methods. This research is expected to provide insights into the effectiveness of different NLP and machine learning approaches for causal reasoning in unstructured text, ultimately contributing to improved understanding of accident dynamics and supporting advancements in aviation safety analysis.
Did this research project receive funding support (Spark, SURF, Research Abroad, Student Internal Grants, Collaborative, Climbing, or Ignite Grants) from the Office of Undergraduate Research?
No
Included in
Learning Casual Structures from Aviation Accident Narratives Using Natural Language Processing and Graph-Based Knowledge Representation
Understanding the complex causal relationships underlying aviation accidents is critical for improving safety and preventing future incidents. However, much of this information exists in unstructured narrative reports, making large-scale analysis difficult. This project aims to automatically extract and model causal chains from National Transportation Safety Board (NTSB) accident narratives using a combination of traditional natural language processing (NLP) techniques, transformer-based architectures, and graph-based knowledge representation. Traditional NLP methods, including named entity recognition, dependency parsing, and rule-based pattern matching, will be used to identify structured cause–effect relationships. These approaches will be compared with transformer-based models, including a lightweight encoder for classification and embedding generation, as well as large language models for prompt-based causal extraction. The extracted relationships will be used to construct a knowledge graph in Neo4j, enabling visualization and querying of accident pathways and contributing factors such as weather conditions and human error. Preliminary work focuses on data preprocessing and model design, with evaluation comparing extraction accuracy, computational efficiency, and scalability across methods. This research is expected to provide insights into the effectiveness of different NLP and machine learning approaches for causal reasoning in unstructured text, ultimately contributing to improved understanding of accident dynamics and supporting advancements in aviation safety analysis.