The lecture by Anna Di Natale, CSH Vienna will take place at the Complexity Science Hub Vienna.
If you are interested in participating, please email to email@example.com.
Text analysis methods are used in many applications. Hand-crafted databases have been used by both linguistics scholars and data scientists to develop new analysis methods. Although they have been proved to work for extracting meaning, analyzing emotions, performing disambiguations and many other applications, manual and supervised methods lack scalability, while unsupervised methods often are not properly validated or capture patterns without linguistic interpretation. I will introduce and discuss a novel method to analyze texts that uses only translation databases. The method is based on the linguistic phenomenon of colexification, identifying relations between words through their translations.