Romy Ghanem (English) and Liz Lane (English)
Drs. Romy Ghanem and Liz Lane talk about corpus linguistics tools for digital humanities research. Corpus linguistics explores variations in language in context. It uses large bodies of texts for a more accurate representation of word use and patterns than what is available from the study of less representative corpora. There are two essential steps in corpus linguistics projects: 1) creating or finding a corpus that is well thought out and well defined, and 2) using text analysis/ mining software to answer particular research questions about that corpus. Free corpora available online on the University of Memphis campus include BYU Corpora, Corpus of Contemporary English, Corpus of Historical American English, and the British National Corpus. AntConc is a free text-mining tool that reads text files and converts books to text. Netylic is a free tool for visualizing and organizing social media posts with the option of using available data sets or creating your own.
Summary and video by Claire Yasmin Khokhar