Machine learning approaches to analysing textual injury surveillance data: A systematic review

Objective To synthesise recent research on the use of machine learning approaches to mining textual injury surveillance data. Design Systematic review. Data sources The electronic databases which were searched included PubMed, Cinahl, Medline, Google Scholar, and Proquest. The bibliography of all relevant articles was examined and associated articles were identified using a snowballing technique. Selection criteria For inclusion, articles were required to meet the following criteria: (a) used a health-related database, (b) focused on injury-related cases, AND used machine learning approaches to analyse textual data. Methods The papers identified through the search were screened resulting in 16 papers selected for review. Articles were reviewed to describe the databases and methodology used, the strength and limitations of different techniques, and quality assurance approaches used. Due to heterogeneity between studies meta-analysis was not performed. Results Occupational injuries were the focus of half of the machine learning studies and the most common methods described were Bayesian probability or Bayesian network based methods to either predict injury categories or extract common injury scenarios. Models were evaluated through either comparison with gold standard data or content expert evaluation or statistical measures of quality. Machine learning was found to provide high precision and accuracy when predicting a small number of categories, was valuable for visualisation of injury patterns and prediction of future outcomes. However, difficulties related to generalizability, source data quality, complexity of models and integration of content and technical knowledge were discussed. Conclusions The use of narrative text for injury surveillance has grown in popularity, complexity and quality over recent years. With advances in data mining techniques, increased capacity for analysis of large databases, and involvement of computer scientists in the injury prevention field, along with more comprehensive use and description of quality assurance methods in text mining approaches, it is likely that we will see a continued growth and advancement in knowledge of text mining in the injury field.

Insights into students' conceptual understanding using textual analysis: A case study in signal processing

Concept inventory tests are one method to evaluate conceptual understanding and identify possible misconceptions. The multiple-choice question format, offering a choice between a correct selection and common misconceptions, can provide an assessment of students' conceptual understanding in various dimensions. Misconceptions of some engineering concepts exist due to a lack of mental frameworks, or schemas, for these types of concepts or conceptual areas. This study incorporated an open textual response component in a multiple-choice concept inventory test to capture written explanations of students' selections. The study's goal was to identify, through text analysis of student responses, the types and categorizations of concepts in these explanations that had not been uncovered by the distractor selections. The analysis of the textual explanations of a subset of the discrete-time signals and systems concept inventory questions revealed that students have difficulty conceptually explaining several dimensions of signal processing. This contributed to their inability to provide a clear explanation of the underlying concepts, such as mathematical concepts. The methods used in this study evaluate students' understanding of signals and systems concepts through their ability to express understanding in written text. This may present a bias for students with strong written communication skills. This study presents a framework for extracting and identifying the types of concepts students use to express their reasoning when answering conceptual questions.