An online software for statistical analyses of text data based on natural language processing

Forskningsoutput: Kapitel i bok/rapport/Conference proceedingKapitel samlingsverk


The overall aim of this chapter is to present a guide in how to efficiently measure and statistically analyze text and numerical data using the online software; we will focus on the following main functions: 1. Computing semantic similarity scores between the semantic representations of two sets of texts. 2. Testing whether the semantic representations of two sets of texts statistically differ using a paired semantic t-test. 3. Train the semantic representations to predict numerical values. 4. Predicting numerical values from the semantic representations of texts by applying a semantic trained (valence) model. 5. Visualize words based on statistically significant relationships along y and x-axes. Exercises are provided for you to practice on in the end.


Enheter & grupper

Ämnesklassifikation (UKÄ) – OBLIGATORISK

  • Tvärvetenskapliga studier
Titel på värdpublikationStatistical Semantics
Undertitel på gästpublikationMethods and Applications
FörlagSpringer International Publishing
Antal sidor17
ISBN (elektroniskt)9783030372507
ISBN (tryckt)9783030372491
StatusPublished - 2020
Peer review utfördJa