Larry S. Yaeger

Sentiment Mining Using Ensemble Classification Models

We live in the information age, where the amount of data readily available already overwhelms our capacity to analyze and absorb it without help from our machines. In particular, there is a wealth of text written in natural language available online that would become much more useful to us were we able to effectively aggregate and process it automatically. In this paper, we consider the problem of automatically classifying human sentiment from natural language written text. In this sentiment mining domain, we compare the accuracy of ensemble models, which take advantage of groups of learners to yield greater performance. We show that these ensemble machine learning models can significantly improve sentiment classification for free-form text.

How evolution guides complexity.

Long‐standing debates about the role of natural selection in the growth of biological complexity over geological time scales are difficult to resolve from the paleobiological record. Using an evolutionary model—a computational ecosystem subjected to natural selection—we investigate evolutionary trends in an information‐theoretic measure of the complexity of the neural dynamics of artificial agents inhabiting the model. Our results suggest that evolution always guides complexity change, just not in a single direction. We also demonstrate that neural complexity correlates well with behavioral adaptation but only when complexity increases are achieved through natural selection (as opposed to increases generated randomly or optimized via a genetic algorithm). We conclude with a suggested research direction that might be able to use the artificial neural data generated in these experiments to determine which aspects of network structure give rise to evolutionarily meaningful neural complexity.