Reproducible extraction of cross-lingual topics (rectr)

Chan, Chung-hong ; Zeng, Jing ; Wessler, Hartmut ; Jungblut, Marc ; Welbers, Kasper ; Bajjalieh, Joseph W. ; Atteveldt, Wouter van ; Althaus, Scott L.

DOI:	https://doi.org/10.1080/19312458.2020.1812555
URL:	https://www.tandfonline.com/doi/abs/10.1080/193124...
Weitere URL:	https://www.researchgate.net/publication/344685521...
Dokumenttyp:	Zeitschriftenartikel
Erscheinungsjahr:	2020
Titel einer Zeitschrift oder einer Reihe:	Communication Methods and Measures
Band/Volume:	14
Heft/Issue:	4
Seitenbereich:	285-305
Ort der Veröffentlichung:	Philadelphia, PA
Verlag:	Routledge, Taylor & Francis Group
ISSN:	1931-2458 , 1931-2466
Sprache der Veröffentlichung:	Englisch
Einrichtung:	Außerfakultäre Einrichtungen > MZES - Arbeitsbereich B Philosophische Fakultät > Medien- und Kommunikationswissenschaft (Wessler 2007-)
Fachgebiet:	320 Politik
Abstract:	With global media content databases and online content being available, analyzing topical structures in different languages simultaneously has become an urgent computational task. Some previous studies have analyzed topics in a multilingual corpus by translating all items into a single language using a machine translation service, such as Google Translate. We argue that this method is not reproducible in the long run and proposes a new method – Reproducible Extraction of Cross-lingual Topics Using R (rectr). Our method utilizes open-source-aligned word embeddings to understand the cross-lingual meanings of words and has a mechanism to normalize residual influence from language differences. We present a benchmark that compares the topics extracted from a corpus of English, German, and French news using our method with methods used in the literature. We show that our method is not only reproducible but can also generate high-quality cross-lingual topics. We demonstrate how our method can be applied in tracking news topics across time and languages.