Automatically Learning Construction Injury Precursors from Text

07/26/2019
by   Henrietta Baker, et al.
0

In light of the increasing availability of digitally recorded safety reports in the construction industry, it is important to develop methods to exploit these data to improve our understanding of safety incidents and ability to learn from them. In this study, we compare several approaches to automatically learn injury precursors from raw construction accident reports. More precisely, we experiment with two state-of-the-art deep learning architectures for Natural Language Processing (NLP), Convolutional Neural Networks (CNN) and Hierarchical Attention Networks (HAN), and with the established Term Frequency - Inverse Document Frequency representation (TF-IDF) + Support Vector Machine (SVM) approach. For each model, we provide a method to identify (after training) the textual patterns that are, on average, the most predictive of each safety outcome. We show that among those pieces of text, valid injury precursors can be found. The proposed methods can also be used by the user to visualize and understand the models' predictions.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
08/08/2023

A Comparative Study on TF-IDF feature Weighting Method and its Analysis using Unstructured Dataset

Text Classification is the process of categorizing text into the relevan...
research
09/26/2016

Construction Safety Risk Modeling and Simulation

By building on a recently introduced genetic-inspired attribute-based co...
research
08/16/2019

AI Predicts Independent Construction Safety Outcomes from Universal Attributes

This paper significantly improves on, and finishes to validate, the appr...
research
01/16/2014

Cause Identification from Aviation Safety Incident Reports via Weakly Supervised Semantic Lexicon Construction

The Aviation Safety Reporting System collects voluntarily submitted repo...
research
07/09/2015

Data Mining of Causal Relations from Text: Analysing Maritime Accident Investigation Reports

Text mining is a process of extracting information of interest from text...
research
04/10/2018

Deep Learning for Digital Text Analytics: Sentiment Analysis

In today's scenario, imagining a world without negativity is something v...
research
05/08/2023

Dreams Are More "Predictable” Than You Think

A consistent body of evidence suggests that dream reports significantly ...

Please sign up or login with your details

Forgot password? Click here to reset