Textual data transformations using natural language processing for risk assessment

Underlying information about failure, including observations made in free text, can be a good source for understanding, analyzing, and extracting meaningful information for determining causation. The unstructured nature of natural language expression demands advanced methodology to identify its underlying features. There is no available solution to utilize unstructured data for risk assessment purposes. Due to the scarcity of relevant data, textual data can be a vital learning source for developing a risk assessment methodology. This work addresses the knowledge gap in extracting relevant features from textual data to develop cause–effect scenarios with minimal manual interpretation. This study applies natural language processing and text-mining techniques to extract features from past accident reports. The extracted features are transformed into parametric form with the help of fuzzy set theory and utilized in Bayesian networks as prior probabilities for risk assessment. An application of the proposed methodology is shown in microbiologically influenced corrosion-related incident reports available from the Pipeline and Hazardous Material Safety Administration database. In addition, the trained named entity recognition (NER) model is verified on eight incidents, showing a promising preliminary result for identifying all relevant features from textual data and demonstrating the robustness and applicability of the NER method. The proposed methodology can be used in domain-specific risk assessment to analyze, predict, and prevent future mishaps, ameliorating overall process safety.     

Going to pieces: narrative disintegration in Nuruddin Farah’s Crossbones

This paper examines Nuruddin Farah’s 2011 novel Crossbones. It argues that Farah subverts the techniques of crime fiction in order to emphasise the difficulty of describing Somalia in terms of a single narrative, and that the novel’s chaotic “unfinished” form represents a resistance to binary and Orientalist media discourses about the country. It demonstrates that the dissolution of structure, characterisation and the generic expectations of crime fiction in the novel represents a resistance to the idea of the outlaw state. The paper discusses the text’s use of rumours, the role and efficacy of the text’s “detective” figures in post-collapse Somalia, and the novel’s treatment of piracy. It argues that the novel’s detective figures represent national allegories within the text, and that their frustration and breakdown suggests the elusiveness and complexity of Somali identity in the postcolonial and post-collapse era.     

Changes through time in soil Collembola communities exposed to urbanization

The study aimed to assess if long-term exposure to urbanization changes the structure and composition of soil collembolan communities in urban green components (street lawns and park lawns) and in all urban green. Species diversity metrics, rarefaction, species richness estimators (Chao 1 and ACE) and multivariate analysis were used for the comparison of changes in community structure and diversity pattern over ca 30 years’ time span. Our results clearly demonstrate a shift, through time, in Collembola community composition and structure in an urban ecosystem and confirm that there is a linkage between long-term exposure to urbanization and changes in collembolan communities. Long-term urbanization led to erosion in species diversity and the formation of species-poor communities, species replacement, loss of specialized forms and promoted the invasion of exotic species. However, we show that the time span considered produced significant differences in diversity attribute values for the collembolan communities from street lawns and insignificant differences in park lawns, also we noted lack of significant differences in collembolan abundance across the two urban green components. The observed temporal changes in collembolan communities indicate that their response to disturbances in urban settings and selecting species is shaped by multiple processes. We conclude that more resistant collembolan communities were found over time in less stressed urban greening components such as park lawn soils compared to street lawn soils.