Blake Stephen Howald

On the explicit and implicit spatiotemporal architecture of narratives of personal experience

Expanding on recent research into the predictability of explicit linguistic spatial information relative to features of discourse structure, we present the results of several machine learning studies which leverage rhetorical relations, events, temporal information, text sequence, and both explicit and implicit linguistic spatial information in three different corpora of narrative discourses. On average, classifiers predict figure, ground, spatial verb and preposition and frame of reference to 75% accuracy, rhetorical relations to 72% accuracy, and events to 76% accuracy (all values have statistical significance above majority class baselines). These results hold independent of the number of authors, subject matter, length and density of spatial and temporal information. Consequently, we argue for a generalized model of spatiotemporal information in narrative discourse, which not only provides a deeper understanding of the semantics and pragmatics of discourse structure, but also alternative robust approaches to analysis.

Modeling Company Risk and Importance in Supply Graphs

Managing one’s supply chain is a key task in the operational risk management for any business. Human procurement officers can manage only a limited number of key suppliers directly, yet global companies often have thousands of suppliers part of a wider ecosystem, which makes overall risk exposure hard to track. To this end, we present an industrial graph database application to account for direct and indirect (transitive) supplier risk and importance, based on a weighted set of measures: criticality, replaceability, centrality and distance. We describe an implementation of our graph-based model as an interactive and visual supply chain risk and importance explorer. Using a supply network (comprised of approximately 98, 000 companies and 220, 000 relations) induced from textual data by applying text mining techniques to news stories, we investigate whether our scores may function as a proxy for actual supplier importance, which is generally not known, as supply chain relationships are typically closely guarded trade secrets. To our knowledge, this is the largest-scale graph database and analysis on real supply relations reported to date.