November 18, 2024
Panning for gold: Comparative analysis of cross-platform approaches for automated detection of political content in textual data
This paper compares dictionary-based, conventional machine-learning, and deep-learning methods for detecting political content in German-language online material across platforms.
Abstract
To understand and measure political information consumption in the high-choice media environment, we need new methods to trace individual interactions with online content and novel techniques to analyse and detect politics-related information. In this paper, we report the results of a comparative analysis of the performance of automated content analysis techniques for detecting political content in the German language across different platforms. Using three validation datasets, we compare the performance of three groups of detection techniques relying on dictionaries, classic supervised machine learning, and deep learning. We also examine the impact of different modes of data preprocessing on the low-cost implementations of these techniques using a large set (n = 66) of models. Our results show the limited impact of preprocessing on model performance, with the best results for less noisy data being achieved by deep learning- and classic machine learning-based models, in contrast to the more robust performance of dictionary-based models on noisy data.
To continue reading please visit: https://doi.org/10.1371/journal.pone.0312865
This open access article was published in PLoS ONE on 18 November 2024.
Makhortykh, M., León, E. de, Urman, A., Gil-Lopez, T., Christner, C., Sydorova, M., Adam, S., & Maier, M. (2024). Panning for gold: Comparative analysis of cross-platform approaches for automated detection of political content in textual data. PLOS ONE, 19(11), e0312865. https://doi.org/10.1371/journal.pone.0312865
Keywords: Preprocessing, Language, Social media, Machine learning, Parsers, Supervised machine learning
Author
See also
Classifying TikToks Locally: Political Content Detection with Phi-4 on Android
By Ernesto de León • Fabio Votta • November 30, 2025
Improving the Quality of Individual-Level Web Tracking: Challenges of Existing Approaches and Introduction of a New Content and Long-Tail Sensitive Academic Solution
By Ernesto de León • October 16, 2024
Hyperpartisan, Alternative, and Conspiracy Media Users: An Anti-Establishment Portrait
By Ernesto de León • March 15, 2024
More results /
When Big Tech rules universities: Reclaiming academic freedom through digital sovereignty
By Natali Helberger • June 16, 2026
By José van Dijck • April 30, 2026
By Natali Helberger • January 19, 2026
By Corinne Cath • May 29, 2026
By Magdalena Brewczyńska • April 16, 2026
By Martijn Logtenberg • November 20, 2025
By Jacqueline Kernahan • Richard Bartels • Mark de Reuver • Daniel Oberski • Roel Dobbe • October 20, 2025
Rethinking European media infrastructures
By Corinne Cath • Agustin Ferrari Braun • Seda Gürses • July 13, 2026
By Natali Helberger • June 15, 2026
By Charis Papaevangelou • Sabrina Kutscher • Natali Helberger • José van Dijck • Thomas Poell • June 01, 2026
