William L. Hamilton

Learn More
Understanding how words change their meanings over time is key to models of language and cultural evolution, but historical data on meaning is scarce, making theories hard to develop and test. Word embeddings show promise as a diachronic tool, but have not been carefully evaluated. We develop a robust methodology for quantifying semantic change by(More)
Words shift in meaning for many reasons, including cultural factors like new technologies and regular linguistic processes like subjectification. Understanding the evolution of language and culture requires disentangling these underlying causes. Here we show how two different distributional measures can be used to detect two different types of semantic(More)
Probabilistic latent-variable models are a powerful tool for modelling structured data. However, traditional expectation-maximization methods of learning such models are both computationally expensive and prone to local-minima. In contrast to these traditional methods, recently developed learning algorithms based upon the method of moments are both(More)
A word's sentiment depends on the domain in which it is used. Computational social science research thus requires sentiment lexicons that are specific to the domains being studied. We combine domain-specific word embeddings with a label propagation framework to induce accurate domain-specific sentiment lexicons using small sets of seed words. We show that(More)
Predictive state representations (PSRs) offer an expressive framework for modelling partially observable systems. By compactly representing systems as functions of observable quantities, the PSR learning approach avoids using local-minima prone expectationmaximization and instead employs a globally optimal moment-based algorithm. Moreover, since PSRs do not(More)
Efficiently learning accurate models of dynamical systems is of central importance for developing rational agents that can succeed in a wide range of challenging domains. The difficulty of this learning problem is particularly acute in settings with large observation spaces and partial observability. We present a new algorithm, called Compressed Predictive(More)
Computationally modeling the evolution of science by tracking how scientific topics rise and fall over time has important implications for research funding and public policy. However, little is known about the mechanisms underlying topic growth and decline. We investigate the role of rhetorical framing: whether the rhetorical role or function that authors(More)
Low-dimensional embeddings of nodes in large graphs have proved extremely useful in a variety of prediction tasks, from content recommendation to identifying protein functions. However, most existing approaches require that all nodes in the graph are present during training of the embeddings; these previous approaches are inherently transductive and do not(More)
Loyalty is an essential component of multi-community engagement. When users have the choice to engage with a variety of different communities, they often become loyal to just one, focusing on that community at the expense of others. However, it is unclear how loyalty is manifested in user behavior, or whether certain community characteristics encour-
Focal adhesions are macromolecular complexes that connect the actin cytoskeleton to the extracellular matrix. Dynamic turnover of focal adhesions is crucial for cell migration. Paxillin is a multi-adaptor protein that plays an important role in regulating focal adhesion dynamics. Here, we identify TRIM15, a member of the tripartite motif protein family, as(More)