Aleksandra Urman

Mykola Makhortykh, Ernesto de León, Aleksandra Urman et al.

The growing availability of data about online information behaviour enables new possibilities for political communication research. However, the volume and variety of these data makes them difficult to analyse and prompts the need for developing automated content approaches relying on a broad range of natural language processing techniques (e.g. machine learning- or neural network-based ones). In this paper, we discuss how these techniques can be used to detect political content across different platforms. Using three validation datasets, which include a variety of political and non-political textual documents from online platforms, we systematically compare the performance of three groups of detection techniques relying on dictionaries, supervised machine learning, or neural networks. We also examine the impact of different modes of data preprocessing (e.g. stemming and stopword removal) on the low-cost implementations of these techniques using a large set (n = 66) of detection models. Our results show the limited impact of preprocessing on model performance, with the best results for less noisy data being achieved by neural network- and machine-learning-based models, in contrast to the more robust performance of dictionary-based models on noisy data.

Elizaveta Kuznetsova, Mykola Makhortykh, Victoria Vziatysheva et al.

This article presents a comparative analysis of the ability of two large language model (LLM)-based chatbots, ChatGPT and Bing Chat, recently rebranded to Microsoft Copilot, to detect veracity of political information. We use AI auditing methodology to investigate how chatbots evaluate true, false, and borderline statements on five topics: COVID-19, Russian aggression against Ukraine, the Holocaust, climate change, and LGBTQ+ related debates. We compare how the chatbots perform in high- and low-resource languages by using prompts in English, Russian, and Ukrainian. Furthermore, we explore the ability of chatbots to evaluate statements according to political communication concepts of disinformation, misinformation, and conspiracy theory, using definition-oriented prompts. We also systematically test how such evaluations are influenced by source bias which we model by attributing specific claims to various political and social actors. The results show high performance of ChatGPT for the baseline veracity evaluation task, with 72 percent of the cases evaluated correctly on average across languages without pre-training. Bing Chat performed worse with a 67 percent accuracy. We observe significant disparities in how chatbots evaluate prompts in high- and low-resource languages and how they adapt their evaluations to political communication concepts with ChatGPT providing more nuanced outputs than Bing Chat. Finally, we find that for some veracity detection-related tasks, the performance of chatbots varied depending on the topic of the statement or the source to which it is attributed. These findings highlight the potential of LLM-based chatbots in tackling different forms of false information in online environments, but also points to the substantial variation in terms of how such potential is realized due to specific factors, such as language of the prompt or the topic.

Aleksandra Urman, Anikó Hannák, Joachim Baumann

GoogleTrendArchive is a comprehensive archive of Google Trending Now data spanning over one year (from November 28, 2024 to January 3, 2026) across 125 countries and 1,358 locations. Unlike Google Trends, which requires specifying search terms in advance, Trending Now captures search queries experiencing real-time surges, offering a way to inductively discover trending patterns across regions for studying collective attention dynamics. However, Google does not provide historical access to this data beyond seven days. Our dataset addresses this gap by presenting an archive of Trending Now data. The dataset contains over 7.6 million trend episodes. Each record includes the trend identifier, search volume bucket, precise timestamps, duration, geographic location, and related query clusters. This dataset, among other, enables systematic studies of information diffusion patterns, cross-cultural attention dynamics, crisis responses, and the temporal evolution of collective information-seeking at a global scale. The comprehensive geographic coverage facilitates fine-grained cross-country or cross-regional comparative analyses.

Joachim Baumann, Paul Röttger, Aleksandra Urman et al.

Large language models are rapidly transforming social science research by enabling the automation of labor-intensive tasks like data annotation and text analysis. However, LLM outputs vary significantly depending on the implementation choices made by researchers (e.g., model selection or prompting strategy). Such variation can introduce systematic biases and random errors, which propagate to downstream analyses and cause Type I (false positive), Type II (false negative), Type S (wrong sign), or Type M (exaggerated effect) errors. We call this phenomenon where configuration choices lead to incorrect conclusions LLM hacking. We find that intentional LLM hacking is strikingly simple. By replicating 37 data annotation tasks from 21 published social science studies, we show that, with just a handful of prompt paraphrases, virtually anything can be presented as statistically significant. Beyond intentional manipulation, our analysis of 13 million labels from 18 different LLMs across 2361 realistic hypotheses shows that there is also a high risk of accidental LLM hacking, even when following standard research practices. We find incorrect conclusions in approximately 31% of hypotheses for state-of-the-art LLMs, and in half the hypotheses for smaller language models. While higher task performance and stronger general model capabilities reduce LLM hacking risk, even highly accurate models remain susceptible. The risk of LLM hacking decreases as effect sizes increase, indicating the need for more rigorous verification of LLM-based findings near significance thresholds. We analyze 21 mitigation techniques and find that human annotations provide crucial protection against false positives. Common regression estimator correction techniques can restore valid inference but trade off Type I vs. Type II errors. We publish a list of practical recommendations to prevent LLM hacking.

Desheng Hu, Joachim Baumann, Aleksandra Urman et al.

Google Search increasingly surfaces AI-generated content through features like AI Overviews (AIO) and Featured Snippets (FS), which users frequently rely on despite having no control over their presentation. Through a systematic algorithm audit of 1,508 real baby care and pregnancy-related queries, we evaluate the quality and consistency of these information displays. Our robust evaluation framework assesses multiple quality dimensions, including answer consistency, relevance, presence of medical safeguards, source categories, and sentiment alignment. Our results reveal concerning gaps in information consistency, with information in AIO and FS displayed on the same search result page being inconsistent with each other in 33% of cases. Despite high relevance scores, both features critically lack medical safeguards (present in just 11% of AIO and 7% of FS responses). While health and wellness websites dominate source categories for both, AIO and FS, FS also often link to commercial sources. These findings have important implications for public health information access and demonstrate the need for stronger quality controls in AI-mediated health information. Our methodology provides a transferable framework for auditing AI systems across high-stakes domains where information quality directly impacts user well-being.

Joachim Baumann, Aleksandra Urman, Ulrich Leicht-Deobald et al.

The rapid adoption of generative artificial intelligence (GenAI) technologies has led many organizations to integrate AI into their products and services, often without considering user preferences. Yet, public attitudes toward AI use, especially in impactful decision-making scenarios, are underexplored. Using a large-scale two-wave survey study (n_wave1=1514, n_wave2=1488) representative of the Swiss population, we examine shifts in public attitudes toward AI before and after the launch of ChatGPT. We find that the GenAI boom is significantly associated with reduced public acceptance of AI (see Figure 1) and increased demand for human oversight in various decision-making contexts. The proportion of respondents finding AI "not acceptable at all" increased from 23% to 30%, while support for human-only decision-making rose from 18% to 26%. These shifts have amplified existing social inequalities in terms of widened educational, linguistic, and gender gaps post-boom. Our findings challenge industry assumptions about public readiness for AI deployment and highlight the critical importance of aligning technological development with evolving public preferences.

Maximilian Boeker, Aleksandra Urman

TikTok currently is the fastest growing social media platform with over 1 billion active monthly users of which the majority is from generation Z. Arguably, its most important success driver is its recommendation system. Despite the importance of TikTok's algorithm to the platform's success and content distribution, little work has been done on the empirical analysis of the algorithm. Our work lays the foundation to fill this research gap. Using a sock-puppet audit methodology with a custom algorithm developed by us, we tested and analysed the effect of the language and location used to access TikTok, follow- and like-feature, as well as how the recommended content changes as a user watches certain posts longer than others. We provide evidence that all the tested factors influence the content recommended to TikTok users. Further, we identified that the follow-feature has the strongest influence, followed by the like-feature and video view rate. We also discuss the implications of our findings in the context of the formation of filter bubbles on TikTok and the proliferation of problematic content.

Aleksandra Urman, Mykola Makhortykh, Roberto Ulloa et al.

Web search engines are important online information intermediaries that are frequently used and highly trusted by the public despite multiple evidence of their outputs being subjected to inaccuracies and biases. One form of such inaccuracy, which so far received little scholarly attention, is the presence of conspiratorial information, namely pages promoting conspiracy theories. We address this gap by conducting a comparative algorithm audit to examine the distribution of conspiratorial information in search results across five search engines: Google, Bing, DuckDuckGo, Yahoo and Yandex. Using a virtual agent-based infrastructure, we systematically collect search outputs for six conspiracy theory-related queries (flat earth, new world order, qanon, 9/11, illuminati, george soros) across three locations (two in the US and one in the UK) and two observation periods (March and May 2021). We find that all search engines except Google consistently displayed conspiracy-promoting results and returned links to conspiracy-dedicated websites in their top results, although the share of such content varied across queries. Most conspiracy-promoting results came from social media and conspiracy-dedicated websites while conspiracy-debunking information was shared by scientific websites and, to a lesser extent, legacy media. The fact that these observations are consistent across different locations and time periods highlight the possibility of some search engines systematically prioritizing conspiracy-promoting content and, thus, amplifying their distribution in the online environments.

Mykola Makhortykh, Aleksandra Urman, Roberto Ulloa

Web search engines influence perception of social reality by filtering and ranking information. However, their outputs are often subjected to bias that can lead to skewed representation of subjects such as professional occupations or gender. In our paper, we use a mixed-method approach to investigate presence of race and gender bias in representation of artificial intelligence (AI) in image search results coming from six different search engines. Our findings show that search engines prioritize anthropomorphic images of AI that portray it as white, whereas non-white images of AI are present only in non-Western search engines. By contrast, gender representation of AI is more diverse and less skewed towards a specific gender that can be attributed to higher awareness about gender bias in search outputs. Our observations indicate both the the need and the possibility for addressing bias in representation of societally relevant subjects, such as technological innovation, and emphasize the importance of designing new approaches for detecting bias in information retrieval systems.

Aleksandra Urman, Mykola Makhortykh, Roberto Ulloa

We audit the presence of domain-level source diversity bias in video search results. Using a virtual agent-based approach, we compare outputs of four Western and one non-Western search engines for English and Russian queries. Our findings highlight that source diversity varies substantially depending on the language with English queries returning more diverse outputs. We also find disproportionately high presence of a single platform, YouTube, in top search outputs for all Western search engines except Google. At the same time, we observe that Youtube's major competitors such as Vimeo or Dailymotion do not appear in the sampled Google's video search results. This finding suggests that Google might be downgrading the results from the main competitors of Google-owned Youtube and highlights the necessity for further studies focusing on the presence of own-content bias in Google's search results.

Aleksandra Urman, Mykola Makhortykh

We conduct a comparative analysis of desktop web search behaviour of users from Germany (n=558) and Switzerland (n=563) based on a combination of web tracking and survey data. We find that web search accounts for 13% of all desktop browsing, with the share being higher in Switzerland than in Germany. We find that in over 50% of cases users clicked on the first search result, with over 97% of all clicks being made on the first page of search outputs. Most users rely on Google when conducting searches, and users preferences for other engines are related to their demographics. We also test relationships between user demographics and daily number of searches, average share of search activities among tracked events by user as well as the tendency to click on higher- or lower-ranked results. We find differences in such relationships between the two countries that highlights the importance of comparative research in this domain. Further, we observe differences in the temporal patterns of web search use between women and men, marking the necessity of disaggregating data by gender in observational studies regarding online information behaviour.