Using the appropriate style is key for writing a high-quality text. Reliable computational style analysis is hence essential for the automation of nearly all kinds of text synthesis tasks. Research on style analysis focuses on recognition problems such as authorship identification; the respective technology (e.g., n-gram distribution divergence quantification) showed to be effective for discrimination, but inappropriate for text synthesis since the “essence of a style” remains implicit. This paper contributes right here: it studies the automatic analysis of style at the knowledge-level based on rhetorical devices. To this end, we developed and evaluated a grammar-based approach for identifying 26 syntax-based devices. Then, we employed that approach to distinguish various patterns of style in selected sets of argumentative articles and presidential debates. The patterns reveal several insights into the style used there, while being adequate for integration in text synthesis systems.

Computational argumentation is expected to play a critical role in the future of web search. To make this happen, many search-related questions must be revisited, such as how people query for arguments, how to mine arguments from the web, or how to rank them. In this paper, we develop an argument search framework for studying these and further questions. The framework allows for the composition of approaches to acquiring, mining, assessing, indexing, querying, retrieving, ranking, and presenting arguments while relying on standard infrastructure and interfaces. Based on the framework, we build a prototype search engine, called args, that relies on an initial, freely accessible index of nearly 300k arguments crawled from reliable web resources. The framework and the argument search engine are intended as an environment for collaborative research on computational argumentation and its practical evaluation.