Das Leibniz-Institut für Psychologie (ZPID) lädt Interessierte im Rahmen seiner Kolloquiumsreihe herzlich ein. Am 7. Dezember 2022 von 13-14 Uhr spricht Jonas Rieger (TU Dortmund / Leibniz Institute for Media Research | Hans-Bredow-Institut (HBI), Hamburg) zum Thema "Keep rollin'! The abilities for monitoring growing corpora using RollingLDA". Das Kolloquium findet in englischer Sprache statt.
Nach der Anmeldung unter events(at)leibniz-psychology.org versenden wir gerne den Link zur-Online-Veranstaltung.
The Leibniz Institute for Psychology (ZPID) is happy to announce Jonas Rieger as upcoming speaker in the ZPID Colloquium Series. In our era of digitalization and Big Data, computational methods are essential for dealing with large text collections. In particular, topic modeling has become a popular method for the automated identification of underlying themes in texts. However, continuously growing text collections (e.g., Twitter, research publications) pose a challenge to traditional topic modeling approaches. Jonas Rieger's work addresses this issue, and ZPID invites everyone interested in text mining, social media, inflation and the influence on economic uncertainty to join this colloquium and meet the expert.
Keep rollin'! The abilities for monitoring growing corpora using RollingLDA
In this talk he will show the advantages of modeling growing text corpora using RollingLDA and present some example applications, e.g., the uncertainty perception and inflation perception indicators, PsychTopics as well as various change detection and monitoring scenarios.
Jonas Rieger is Postdoc at TU Dortmund University (Chair of Business and Social Statistics, Department of Statistics) and at the Leibniz Institute for Media Research | Hans-Bredow-Institut (HBI) in Hamburg. He completed his degree in Statistics in Dortmund in 2016 and worked as a doctoral student and research associate at the chair of Business and Social Statistics at TU Dortmund University until September 2022.
His research interests are mainly focused on topic models. They cover the evaluation, model selection and parameter tuning as well as update algorithms for topic models. Besides, he is interested in the identification of changes, events, and narratives in corpora, the exploitation of specific corpora for indices, and content analyses of political text data.