I present a couple of active research projects of my Information Access Research Group (IARG) that include work on the detection, sub- classification and explaining of sentence-level news bias, methodology support for machine learning projects, as well as RAG chatbots that assist with areas ranging from machine learning project work in a company to students learning about artificial intelligence; I conclude with some thoughts on evaluation.

Die Rolle des Denkens im KI-Zeitalter

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

Learning is at the heart of every progress the human species makes. It is most effective when it considers who we are as individuals, what learning approach we prefer and what we already know to begin with. In the digital age, we strive to capture such information in the form of a digital representation -- the so-called learner model --, to tailor learning-related systems to this information and build upon it to create more personalised learning experiences. Over recent years, the proliferation of diverse models across various educational applications and disciplines has made it challenging to access targeted research.

In this survey, we aim to address this gap, reviewing the latest advances in learner modelling and conducting a comprehensive analysis of the existing approaches, focusing on developments from 2014 to 2023. With the help of a systematic literature review, we want to provide designers and developers of learner models with a structured overview and simplified entrance into the topic and the field of learner models. We investigate the question: What do learner models look like and how are they filled, kept up-to-date, and used?

To this end, we analyse and classify existing approaches. Our findings provide a comprehensive and structured overview of the field of learner modelling, allowing researchers to navigate and understand the diverse approaches more easily and providing developers of learner models or adaptive systems with a practical tool to access relevant information according to their needs.

The increasing consumption of news online in the 21st century coincided with increased publication of disinformation, biased reporting, hate speech and other unwanted Web content.

We describe BiasScanner, an application that aims to strengthen democracy by supporting news consumers with scrutinizing news articles they are reading online. BiasScanner contains a server-side pre-trained large language model to identify biased sentences of news articles and a front-end Web browser plug-in. BiasScanner can identify and classify more than two dozen types of media bias at the sentence level, making it the most fine-grained model and only automatic application deployed as a browser plug-in. One special feature is the high-quality, LLM-generated explanations of the model’s decisions.

While prior research has addressed news bias detection, we are not aware of any automatic work that resulted in a deployed browser plug-in (c.f. also biasscanner.org for a Web demo).

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.

In modern education, individualized learning environments play a vital role by allowing learners to tailor their learning paths based on personal needs, interests, and abilities. Achieving effective individualization relies on dynamic adaptation of the learning path, typically facilitated by recommender systems. These systems offer personalized suggestions, commonly employing content-based or collaborative filtering approaches. However, traditional recommender systems often lack consideration of the semantics of learning elements. To address this limitation, ontology-based recommender systems integrate semantic modeling, establishing additional connections within a domain to enhance precision and context in recommendations. Notably, these systems mitigate the cold start problem and are particularly advantageous in learning environments with limited data. While videos are prevalent in learning platforms, their unstructured nature poses challenges for processing. This paper introduces an innovative approach, leveraging Large Language Models, specifically GPT, to extract metadata from learning videos. The proposed method intelligently augments videos and links them to a domain ontology, enabling the integration of videos into ontology-based recommender systems. The application of this approach is demonstrated through a case study in software engineering education, showcasing its potential to enhance individualized learning experiences in specific domains. The presented method offers an automated alternative to manual video processing, aligning with the evolving landscape of education technology.

Students in higher education tend to become increasingly heterogeneous groups of learners. This is due to different levels of prior knowledge or competences, diverse
learning styles, differing affinity to (digital) media, and other factors. Learner-centred education needs to cope with that heterogeneity in order to make specific learning offers to the
individual learner. This is difficult in physical classes where the coaching effort cannot be increased without limitation. This paper presents an individualized digital learning environment, iLE, that is intended to be used as an additional learning aid that supplements physical classes. iLE provides recommendations of learning material such as learning videos targeted to the specific needs of individual learners. The paper presents the technical approach behind iLE, in particular a combination of data- and knowledge-driven artificial intelligence techniques, as well as the didactical underpinning of iLE.

Die präzise Erkennung von Clear-Sky-Momenten ist für die Überwachung und Effizienzana-lyse von Photovoltaikanlagen von zentraler Bedeutung, da zu diesen Zeitpunkten definierte und model-lierbare Einstrahlungsverhältnisse herrschen. Es wird ein hybrides Modell zur verbesserten Erkennung von Clear-Sky-Momenten auf Basis von Einstrahlungsdaten vorgestellt. Hierfür wurden zunächst ma-nuell, dann mithilfe eines CNNs Merkmale aus den Einstrahlungsdaten gebildet. Eine Falls tudie mit Referenzdaten belegt, dass durch die Kombination dieser wissens-und datengetriebenen Methoden Clear-Sky-Momente zuverlässiger identifiziert werden können. Dadurch können Analysemethoden schneller und zuverlässiger Aussagen über die untersuchten PV-Anlagen treffen.