NLP Coding Libraries and Network Analysis for Text Corpora

The 3-day workshop offers a quick and effective intro to natural language processing (NLP) and textual corpus network visualization and analysis. We will be doing coding in Python and learning how to use (and compare) certain relevant libraries such as Scikit-learn, NLTK, FastText, Gensim plus word2vec & doc2vec, SpaCy, TextStat, LexicalRichness, and NetworkX. We will apply those packages in computationally analyzing texts and textual corpora, representing the corpora as networks, and thus finding out unexpected if not amazing things about the texts they contain. The knowledge and skills acquired—alongside our in-class applications—will be useful in education and research in NLP, automated text and corpus analysis, network science and graph theory applications, computational literary analysis and criticism, computational linguistics, and vector space (and topic) modeling for the humanities. On the fourth day, everybody will have the opportunity to participate in the #GraphPoem event that will involve some of the Python scripts developed during the workshop. We will run those and other scripts live (on JupyterHub) on ready-made and individually/collaboratively assembled and expanded corpora, thus feeding into a hypermedia performance involving a Twitter bot and a cross-artform live stream.