Algorithms of online platforms are required under the Digital Services Act (DSA) to comply with specific obligations concerning algorithmic transparency, user protection and privacy. To verify compliance with these requirements, DSA mandates platforms to undergo independent audits. Little is known about current auditing practices and their effectiveness in ensuring such compliance. To this end, we bridge regulatory and technical perspectives by critically examining selected audit reports across three critical algorithmic-related provisions: restrictions on profiling minors, transparency in recommender systems, and limitations on targeted advertising using sensitive data. Our analysis shows significant inconsistencies in methodologies and lack of technical depth when evaluating AI-powered systems. To enhance the depth, scale, and independence of compliance assessments, we propose to employ algorithmic auditing – a process of behavioural assessment of AI algorithms by means of simulating user behaviour, observing algorithm responses and analysing them for audited phenomena.

Social media platforms have become an integral part of everyday life, serving as a primary source of news and information for many users. These platforms increasingly rely on personalised recommendation systems that shape what users see and engage with. While these systems are optimised for engagement, concerns have emerged that they may also drive users toward more polarised perspectives, particularly in contested domains such as politics, climate change, vaccines, and conspiracy theories. In this paper, we present an algorithmic audit of personalisation drift on TikTok in these polarising topics. Using controlled accounts designed to simulate users with interests aligned with or opposed to different polarising topics, we systematically measure the extent to which TikTok steers content exposure toward specific topics and polarities over time. Specifically, we investigated: 1) a preference-aligned drift (showing a strong personalisation towards user interests), 2) a polarisation-topic drift (showing a strong neutralising effect for misinformation-themed topics, and a high preference and reinforcement of interest of US politic topic); and 3) a polarisation-stance drift (showing a preference of oppose stance towards US politics topic and a general reinforcement of users’ stance by recommending items aligned with their stance towards polarising topics). Overall, our findings provide evidence that recommendation trajectories differ markedly across topics, with some pathways amplifying polarised viewpoints more strongly than others and offer insights for platform governance, transparency and user awareness.

When solving NLP tasks with limited labelled data, researchers typically either use a general large language model without further update, or use a small number of labelled samples to tune a specialised smaller model.In this work, we answer an important question -how many labelled samples are required for the specialised small models to outperform general large models, while taking the performance variance into consideration.By observing the behaviour of fine-tuning, instruction-tuning, prompting and in-context learning on 8 language models, we identify such performance break-even points across 8 representative text classification tasks of varying characteristics.We show that the specialised models often need only few samples (on average 100) to be on par or better than the general ones.At the same time, the number of required labels strongly depends on the dataset or task characteristics, with fine-tuning on binary datasets requiring significantly more samples.When performance variance is taken into consideration, the number of required labels increases on average by 100 -200%.Finally, larger models do not consistently lead to better performance and lower variance, with 4-bit quantisation having negligible impact.

Social media platforms are constantly shifting towards algorithmically curated content based on implicit or explicit user feedback. Regulators, as well as researchers, are calling for systematic social media algorithmic audits as this shift leads to enclosing users in filter bubbles and leading them to more problematic content. An important aspect of such audits is the reproducibility and generalisability of their findings, as it allows to draw verifiable conclusions and audit potential changes in algorithms over time. In this work, we study the reproducibility of the existing sockpuppeting audits of TikTok recommender systems, and the generalizability of their findings. In our efforts to reproduce the previous works, we find multiple challenges stemming from social media platform changes and content evolution, but also the research works themselves. These drawbacks limit the audit reproducibility and require an extensive effort altogether with inevitable adjustments to the auditing methodology. Our experiments also reveal that these one-shot audit findings often hold only in the short term, implying that the reproducibility and generalizability of the audits heavily depend on the methodological choices and the state of algorithms and content on the platform. This highlights the importance of reproducible audits that allow us to determine how the situation changes in time.

Jan Cegin, Branislav Pecher, Jakub Simko, Ivan Srba, Maria Bielikova, Peter Brusilovsky. Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2024.

While learning with limited labelled data can effectively deal with a lack of labels, it is also sensitive to the effects of uncontrolled randomness introduced by so-called randomness factors (i.e., non-deterministic decisions such as choice or order of samples).We propose and formalise a method to systematically investigate the effects of individual randomness factors while taking the interactions (dependence) between them into consideration.To this end, our method mitigates the effects of other factors while observing how the performance varies across multiple runs.Applying our method to multiple randomness factors across in-context learning and fine-tuning approaches on 7 representative text classification tasks and metalearning on 3 tasks, we show that: 1) disregarding interactions between randomness factors in existing works led to inconsistent findings due to incorrect attribution of the effects of randomness factors, such as disproving the consistent sensitivity of in-context learning to sample order even with random sample selection; and 2) besides mutual interactions, the effects of randomness factors, especially sample order, are also dependent on more systematic choices unexplored in existing works, such as number of classes, samples per class or choice of prompt format.

In this article, we present results of an auditing study performed over YouTube aimed at investigating how fast a user can get into a misinformation filter bubble, but also what it takes to “burst the bubble,” i.e., revert the bubble enclosure. We employ a sock puppet audit methodology, in which pre-programmed agents (acting as YouTube users) delve into misinformation filter bubbles by watching misinformation-promoting content. Then they try to burst the bubbles and reach more balanced recommendations by watching misinformation-debunking content. We record search results, home page results, and recommendations for the watched videos. Overall, we recorded 17,405 unique videos, out of which we manually annotated 2,914 for the presence of misinformation. The labeled data was used to train a machine learning model classifying videos into three classes (promoting, debunking, neutral) with the accuracy of 0.82. We use the trained model to classify the remaining videos that would not be feasible to annotate manually. Using both the manually and automatically annotated data, we observe the misinformation bubble dynamics for a range of audited topics. Our key finding is that even though filter bubbles do not appear in some situations, when they do, it is possible to burst them by watching misinformation-debunking content (albeit it manifests differently from topic to topic). We also observe a sudden decrease of misinformation filter bubble effect when misinformation-debunking videos are watched after misinformation-promoting videos, suggesting a strong contextuality of recommendations. Finally, when comparing our results with a previous similar study, we do not observe significant improvements in the overall quantity of recommended misinformation content.

We focus on learning with limited labelled data (especially meta-learning) in conjunction with so-far under-researched multilingual textual document classification. The core principle in such learning is to achieve transferability of learned knowledge to new datasets and tasks. Currently, factors influencing the success of transfer remain mostly unclear. Their identification from experiments is challenging due to small amounts of labels making results considerably unstable. When instability of the investigated models is not explicitly taken into consideration (as is common in existing benchmarking studies), it may result in randomness possibly even invalidating the findings. We want to remedy this by in-depth exploration of factors that influence the stability and the transferability of learning with limited labelled data in multilingual textual documents classification, such as misinformation detection.

In this paper, we describe a black-box sockpuppeting audit which we carried out to investigate the creation and bursting dynamics of misinformation filter bubbles on YouTube. Pre-programmed agents acting as YouTube users stimulated YouTube's recommender systems: they first watched a series of misinformation promoting videos (bubble creation) and then a series of misinformation debunking videos (bubble bursting). Meanwhile, agents logged videos recommended to them by YouTube. After manually annotating these recommendations, we were able to quantify the portion of misinformative videos among them. The results confirm the creation of filter bubbles (albeit not in all situations) and show that these bubbles can be bursted by watching credible content. Drawing a direct comparison with a previous study, we do not see improvements in overall quantities of misinformation recommended.

False information has a significant negative influence on individuals as well as on the whole society. Especially in the current COVID-19 era, we witness an unprecedented growth of medical misinformation. To help tackle this problem with machine learning approaches, we are publishing a feature-rich dataset of approx. 317k medical news articles/blogs and 3.5k fact-checked claims. It also contains 573 manually and more than 51k automatically labelled mappings between claims and articles. Mappings consist of claim presence, i.e., whether a claim is contained in a given article, and article stance towards the claim. We provide several baselines for these two tasks and evaluate them on the manually labelled part of the dataset. The dataset enables a number of additional tasks related to medical misinformation, such as misinformation characterisation studies or studies of misinformation diffusion between sources.

The negative effects of misinformation filter bubbles in adaptive systems have been known to researchers for some time. Several studies investigated, most prominently on YouTube, how fast a user can get into a misinformation filter bubble simply by selecting “wrong choices” from the items offered. Yet, no studies so far have investigated what it takes to “burst the bubble”, i.e., revert the bubble enclosure. We present a study in which pre-programmed agents (acting as YouTube users) delve into misinformation filter bubbles by watching misinformation promoting content (for various topics). Then, by watching misinformation debunking content, the agents try to burst the bubbles and reach more balanced recommendation mixes. We recorded the search results and recommendations, which the agents encountered, and analyzed them for the presence of misinformation. Our key finding is that bursting of a filter bubble is possible, albeit it manifests differently from topic to topic. Moreover, we observe that filter bubbles do not truly appear in some situations. We also draw a direct comparison with a previous study. Sadly, we did not find much improvements in misinformation occurrences, despite recent pledges by YouTube.