Search

found 2 results

Research papers, University of Canterbury Library

Natural disasters are highly traumatic for those who experience them, and they can have an immense and often lasting emotional impact (Cox et al., 2008). Emotion has been studied in linguistics through its enactment in language, and this field of research has increased over the past decades. Despite this, the expression of emotion in post-disaster narratives is a largely unexplored field of research. This thesis investigates how emotion is expressed in narratives taken from the QuakeBox corpus (Walsh et al., 2013), recorded, following the Christchurch earthquakes, in 2012 and rerecorded in 2019. I take a mixed methods approach, combining computer-based emotion recognition software and discourse analytic techniques, to explore the expression of emotion at both a broad and narrow level. Two emotion recognition programs, Empath (Fast et al., 2016) and Speechbrain (Ravanelli et al., 2021), are employed to measure the levels of positive and negative emotion detected in a wide dataset of participants, which are investigated in relation to the gender and age of participants, and the temporal difference between the first and second QuakeBox recordings. In a second phase, a subset of these participants’ narratives was analysed qualitatively, exploring the co-construction of emotion and identity through a social constructionist lens and examining the societal Discourses present in the earthquake narratives. The findings highlight the relevance of gender in the expression of emotion. Female speakers have higher levels of positive emotion than non-female speakers in the findings of both emotion recognition programs, and there is a clear gendered difference in the construction of identity in the narratives, influencing the expression of emotion. The expression of emotion also appears to be mediated by New Zealand culture. Within this, a Discourse of the Christchurch earthquakes emerges, with motifs of luck, gratitude, and community, which reflects the values of the people of Christchurch at the time. Findings reinforced in both phases of the analysis also indicate differences between the lexical content and acoustic features in the emotion expressions, supporting previous research that argues that the expression of emotion, as a performative act, does not reflect the speaker’s inner state directly. This research adds a new dimension to (socio)linguistic research on emotion, as well as providing insight into how crisis survivors display emotion in their post-disaster narratives.

Research papers, The University of Auckland Library

The rapid classification of building damage states or placards after an earthquake is vital for enabling an efficient emergency response and informed decision-making for rehabilitation and recovery purposes. Traditional methods rely heavily on inspector-led on-site surveys, which are often time-consuming, resource-intensive, and susceptible to human error. This study introduces a machine learning-supported surrogate model designed to streamline the assessment of building damage, focusing on the automated assignment of damage placards within the context of New Zealand's post-earthquake evaluation frameworks. The study evaluates two key safety evaluation protocols—Rapid Building Assessment (RBA) and Detailed Damage Evaluation (DDE)—and integrates corresponding databases derived from the 2010–2011 Canterbury Earthquake Sequence (CES) in Christchurch. Six ML classifiers—Multilayer Perceptron (MLP), Random Forest (RF), Support Vector Machine (SVM), K-Nearest Neighbours (KNN), Gradient Boosting Classifier (GBC), and Gradient Bagging (GBag)—were rigorously tested across both databases. The results indicate that the RF-based surrogate model outperforms the other classifiers across both RBA and DDE protocols. Two distinct sets of critical predictors have been further identified for each protocol, allowing for the rapid retrieval of essential data for future on-site surveys, while retaining the RF model's predictive accuracy. The developed surrogate model provides a pragmatic tool for practising engineers to rapidly assign placards to damaged structures and for policymakers and building owners to make informed recovery decisions for earthquake-affected buildings