Welcome to netts
Network of Transcript Semantics (netts) creates networks capturing the semantic content of speech.
Network of Transcript Semantics
Source Code: https://github.com/alan-turing-institute/netts
Netts is package for analysing the content of natural speech. It maps the content of speech as a network and analyses the network using graph theory. The networks are referred to as semantic speech networks. This is novel analysis method for speech data has provided new insight on speech alterations in psychiatric conditions.
Netts uses Natural Language Processing (NLP) to construct speech networks from transcripts of spoken text (e.g. I see a man). Nodes represent entities (e.g. I, man) and edges represent relations between nodes (e.g. see).
The tool is freely available as a python package and accessible online. It can be installed from the python package index PyPI, see Getting Started for installation instructions. Netts can be used to construct a semantic speech network from a text file with a single command. See CLI usage for a user guide. For a detailed explanation of the processing pipeline, see Pipeline.
Netts was written by Caroline Nettekoven in collaboration with Sarah Morgan.
Netts was packaged in collaboration with Oscar Giles, Iain Stenson and Helen Duncan.