Abstract:The content moderation systems used by social media sites are a topic of widespread interest and research, but less is known about the use of similar systems by web search engines. For example, Google Search attempts to help its users navigate three distinct types of data voids--when the available search results are deemed low-quality, low-relevance, or rapidly-changing--by placing one of three corresponding warning banners at the top of the search page. Here we collected 1.4M unique search queries shared on social media to surface Google's warning banners, examine when and why those banners were applied, and train deep learning models to identify data voids beyond Google's classifications. Across three data collection waves (Oct 2023, Mar 2024, Sept 2024), we found that Google returned a warning banner for about 1% of our search queries, with substantial churn in the set of queries that received a banner across waves. The low-quality banners, which warn users that their results "may not have reliable information on this topic," were especially rare, and their presence was associated with low-quality domains in the search results and conspiracy-related keywords in the search query. Low-quality banner presence was also inconsistent over short time spans, even when returning highly similar search results. In August 2024, low-quality banners stopped appearing on the SERPs we collected, but average search result quality remained largely unchanged, suggesting they may have been discontinued by Google. Using our deep learning models to analyze both queries and search results in context, we identify 29 to 58 times more low-quality data voids than there were low-quality banners, and find a similar number after the banners had disappeared. Our findings point to the need for greater transparency on search engines' content moderation practices, especially around important events like elections.
Abstract:In an attempt to mimic the complex paths through which unreliable content spreads between search engines and social media, we explore the impact of incorporating both webgraph and large-scale social media contexts into website credibility classification and discovery systems. We further explore the usage of what we define as \textit{dredge words} on social media -- terms or phrases for which unreliable domains rank highly. Through comprehensive graph neural network ablations, we demonstrate that curriculum-based heterogeneous graph models that leverage context from both webgraphs and social media data outperform homogeneous and single-mode approaches. We further demonstrate that the incorporation of dredge words into our model strongly associates unreliable websites with social media and online commerce platforms. Finally, we show our heterogeneous model greatly outperforms competing systems in the top-k identification of unlabeled unreliable websites. We demonstrate the strong unreliability signals present in the diverse paths that users follow to uncover unreliable content, and we release a novel dataset of dredge words.
Abstract:We evaluate the zero-shot ability of GPT-4 and LLaVa to perform simple Visual Network Analysis (VNA) tasks on small-scale graphs. We evaluate the Vision Language Models (VLMs) on 5 tasks related to three foundational network science concepts: identifying nodes of maximal degree on a rendered graph, identifying whether signed triads are balanced or unbalanced, and counting components. The tasks are structured to be easy for a human who understands the underlying graph theoretic concepts, and can all be solved by counting the appropriate elements in graphs. We find that while GPT-4 consistently outperforms LLaVa, both models struggle with every visual network analysis task we propose. We publicly release the first benchmark for the evaluation of VLMs on foundational VNA tasks.
Abstract:The proliferation of unreliable news domains on the internet has had wide-reaching negative impacts on society. We introduce and evaluate interventions aimed at reducing traffic to unreliable news domains from search engines while maintaining traffic to reliable domains. We build these interventions on the principles of fairness (penalize sites for what is in their control), generality (label/fact-check agnostic), targeted (increase the cost of adversarial behavior), and scalability (works at webscale). We refine our methods on small-scale webdata as a testbed and then generalize the interventions to a large-scale webgraph containing 93.9M domains and 1.6B edges. We demonstrate that our methods penalize unreliable domains far more than reliable domains in both settings and we explore multiple avenues to mitigate unintended effects on both the small-scale and large-scale webgraph experiments. These results indicate the potential of our approach to reduce the spread of misinformation and foster a more reliable online information ecosystem. This research contributes to the development of targeted strategies to enhance the trustworthiness and quality of search engine results, ultimately benefiting users and the broader digital community.