Corpora are widely used in linguistics, but not always wisely. This book attempts to frame corpus linguistics systematically as a variant of the observational method. The first part introduces the reader to the general methodological discussions surrounding corpus data as well as the practice of doing corpus linguistics, including issues such as the scientific research cycle, research design, extraction of corpus data and statistical evaluation. The second part consists of a number of case studies from the main areas of corpus linguistics (lexical associations, morphology, grammar, text and metaphor), surveying the range of issues studied in corpus linguistics while at the same time showing how they fit into the methodology outlined in the first part.

Anatol Stefanowitsch is Professor of English Linguistics at the Freie Universität Berlin. His research focuses on the quantitative, corpus-based analysis of English and other languages from a cognitive-linguistic perspective. His main interest is the interaction of lexis with grammatical constructions, linguistic and conceptual metaphors, and text. He is also a well-known public educator about language, writing and speaking about topics like linguistic purism, linguistic discrimination and language ideologies.