Media bias is an enduring feature of news dissemination, reflecting the subjective perspectives of its creators across history. From archaic records like "The Victory Stele of Naram-Sin" to contemporary news channels, bias permeates media, influencing political, social, and public health narratives. This research aims to investigate the persistent phenomenon of media bias and the potential of large language models (LLMs)(Kojima et al., 2022) in its detection and classification, in order to deploy publicly available software tools aiming to enhance media literacy among news consumers.

Traditionally, media bias served the interests of ruling powers; even with the rise of modern journalism, objectivity is often compromised by commercial pressures and inherent human biases. (Rodrigo-Ginés et al., 2024). As media landscapes evolve, bias continues to shape public opinion, impacting democratic processes and public health perceptions—evident during the COVID-19 pandemic, where polarized media narratives swayed public health decisions and fueled misinformation. (Recio-Román et al., 2023)

Current research on the effects of labeling media bias or propaganda, whether automatically or with human involvement, highlights the complexity of the issue. Depending on different circumstances, labeling can lead to negative outcomes (such as reinforcing filter bubbles by providing means to avoid news with a different perspective), no change in news consumption behavior at all, or, in some cases, an actual improvement in media literacy as intended (Zavolokina et al., 2024).

This research aims to develop a technical solution for the automatic labeling of biased media content, emphasizing several proposals that we hope will lead to a positive effect on media literacy among those presented with the system’s assessments.

These proposals include using a fine-grained taxonomy of bias types rather than a simple binary left/right labeling, focusing on detailed explanations for each model decision in natural language, marking bias at the sentence level rather than at the article or publication level to provide more insights, fine-tuning autoregressive models like GPT-3.5 or Mistral with high-quality examples instead of using “simple” bidirectional models like BERT(Brown et al., 2020) or non-finetuned models, and focusing on the German language, which has not yet been properly explored for such systems.

Understanding readers' perceptions when exposed to bias-labeled content is another facet of this research. It will explore how bias labeling influences readers' views on credibility and neutrality and whether real-time bias indicators affect news consumption behaviors. As mentioned, practical applications serve as a cornerstone of this research. One aim is to implement bias detection systems in real-world settings, such as search engines and news aggregators, to promote balanced information consumption. The development of user tools, like browser extensions highlighting media bias, intends to address public need for transparent information evaluation.

In essence, this research contributes to media literacy enhancement by demystifying media bias through advanced computational methods. By refining detection mechanisms, classifying bias more effectively, and implementing practical tools, it aims to fortify democratic discourse and public understanding, thereby addressing the pervasive influence of media bias in today’s interconnected world.

References

Brown, T. B., Mann, B., Ryder, N., Subbiah, M., Kaplan, J., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., Agarwal, S., Herbert-Voss, A., Krueger, G., Henighan, T., Child, R., Ramesh, A., Ziegler, D. M., Wu, J., Winter, C., … Amodei, D. (2020). Language Models are Few-Shot Learners. In H. Larochelle, M. Ranzato, R. Hadsell, M. F. Balcan, & H. Lin (Eds.), Advances in Neural Information Processing Systems (Vol. 33, pp. 1877–1901). Curran.

Kojima, T., Gu, S. S., Reid, M., Matsuo, Y., & Iwasawa, Y. (2022). Large language models are zero-shot reasoners. Advances in Neural Information Processing Systems, 35, 22199–22213.

Recio-Román, A., Recio-Menéndez, M., & Román-González, M. V. (2023). Influence of Media Information Sources on Vaccine Uptake: The Full and Inconsistent Mediating Role of Vaccine Hesitancy. Computation (Basel). https://doi.org/10.3390/computation11100208

Rodrigo-Ginés, F.-J., Carrillo-de-Albornoz, J., & Plaza, L. (2024). A systematic review on media bias detection: What is media bias, how it is expressed, and how to detect it. Expert Systems with Applications, 237, 121641.

Keywords: Media Bias, Large Language Models, Bias Detection, Natural Language Processing, Journalism, Public Opinion, Taxonomy

The textual realm and the geographic/spatial realm intersect when we use human language to talk about geographic space. Various terms have been used to talk about this intersection (“geoparsing”, “georeferencing”, “toponym resolution”, “spatial grounding” etc.) and related applications such as geographic information retrieval. In this keynote, I will review some things that the community has accomplished since 2003, what occupies people’s minds at the moment, and I will raise a few research questions that would be interesting to answer, or that would unlock the potential for new kinds of applications. I conclude with some personal conjectures about how one version of the future might look like.

Virtual reality (VR) technologies are increasingly used in neuropsychological assessment of various cognitive functions. Compared to traditional laboratory studies, VR allows for a more natural environment and more complex task-related movements with a high degree of control over the environment. However, there are still few studies that transfer well-established paradigms for measuring attentional distraction by novel sounds in laboratory settings to virtual environments and sports activities. In this study, the oddball paradigm, which is well established in laboratory settings for studying attention, is transferred to table tennis in a virtual environment. While 33 subjects played virtual table tennis, they were presented with a task-irrelevant sequence of frequent standard sounds and infrequent novel sounds. Trials in which an unexpected novel sound preceded the ball’s appearance resulted in a delayed racket movement compared to trials in which a standard sound was presented. This distraction effect was observed in the first part of the experiment but disappeared with increasing exposure. The results suggest that unexpected and task-irrelevant novel sounds can initially distract attention and impair performance on a complex movement task in a rich environment. The results demonstrate that versions of the well-established oddball distraction paradigm can be used to study attentional distraction, its dynamics, and its effects on complex movements in naturalistic environments.

Hintergrund: Bis dato befassen sich die meisten Forschungsvorhaben im Bereich der KB mit Wirkungsforschung, wobei Nachweise von Wirkungen durch KB aufgrund von komplexen und auch multikausalen Wirkzusammenhängen nicht vorbehaltlos zu erbringen sind. Forschung im Bereich der Kulturellen Bildung (KB), die dazu beiträgt, den Begriff KB, die zugrundeliegende Theorie, den Praxisbereich und auch die Angebote von KB zu verstehen und einzuordnen, ist hingegen eher rar. Die Potenziale der KB unterstreichen jedoch den Bedarf der Weiterentwicklung und theoretisch-methodischen Fundierung der KB. Es wird also Forschung gebraucht, die einen Beitrag zur evidenzbasierten Qualitätsverbesserung und -sicherung leistet. Mit der vorliegenden Erhebung bei wichtigen Akteur:innen der KB soll das Verständnis von KB in der Europäischen Metropolregion Nürnberg (EMN) abgebildet werden.

Methodik: Es wurde eine quantitative Querschnittsstudie in Form einer Online-Befragung durchgeführt, und es bestand die Möglichkeit der Beantwortung der Fragen via paper+pencil. Es wurden vorrangig quantitative Daten erhoben, in geringem Ausmaß auch qualitative Daten in Form von Antwortmöglichkeiten unter Sonstiges und Freitextfragen. Eine Orientierung bezüglich zentraler inhaltlicher Aussagen und daraus entwickelter Kategorien gab eine qualitative Vorstudie (siehe: Hamani et al. 2023).

Ergebnisse: Die Stichprobe bestand aus 73 Akteur:innen im Bereich der KB in der EMN. Die Ergebnisse wurden deskriptivstatistisch ausgewertet. Die qualitativen Antworten in den Feldern Sonstiges und zu den Freitextfragen wurden in induktiv gebildete Kategorien eingeordnet. Auch wurden explorative Analysen durchgeführt.

Diskussion und Fazit: Die vielschichtigen Erkenntnisse aus der Befragung unterstreichen die Komplexität von KB und verdichten sich bezüglich mancher Handlungs- und Inhaltsdimensionen. Hierfür hat die Studie Kategorisierungsmöglichkeiten entwickelt und durch handelnde Akteur:innen gewichten lassen.