Purpose:Black men have the highest incidence and mortality from prostate cancer (PCa) and lower quality of life compared to other U.S. racial groups. Additionally, more Latinx men are diagnosed with advanced disease and fewer receive guideline-concordant care. As many men seek medical information online, high-quality information targeting diverse populations may mitigate disparities. We examined racial/ethnic representation and information quality in online PCa content.Materials and Methods:We retrieved 150 websites and 150 videos about “prostate cancer” using the most widely used search engine (Google) and social network (YouTube). We assessed quality of health information, reading level, perceived race/ethnicity of people featured in the content and discussion of racial/ethnic disparities.Results:Among 81 websites and 127 videos featuring people, 37% and 24% had perceived Black representation, and racial/ethnic disparities were discussed in 27% and 17%, respectively. Among 1,526 people featured, 9% and 1% were perceived as Black and Latinx, respectively. No content with Black or Latinx representation was high quality, understandable, actionable and at the recommended reading level.Conclusions:Black and Latinx adults are underrepresented in online PCa content. Online media have significant potential for public education and combating health disparities. However, most PCa content lacks diversity and is not readily understandable.

We introduce Biased TextRank, a graph-based content extraction method inspired by the popular TextRank algorithm that ranks text spans according to their importance for language processing tasks and according to their relevance to an input "focus." Biased TextRank enables focused content extraction for text by modifying the random restarts in the execution of TextRank. The random restart probabilities are assigned based on the relevance of the graph nodes to the focus of the task. We present two applications of Biased TextRank: focused summarization and explanation extraction, and show that our algorithm leads to improved performance on two different datasets by significant ROUGE-N score margins. Much like its predecessor, Biased TextRank is unsupervised, easy to implement and orders of magnitude faster and lighter than current state-ofthe-art Natural Language Processing methods for similar tasks.

Manual fact-checking does not scale well to serve the needs of the internet. This issue is further compounded in non-English contexts. In this paper, we discuss claim matching as a possible solution to scale fact-checking. We define claim matching as the task of identifying pairs of textual messages containing claims that can be served with one fact-check. We construct a novel dataset of WhatsApp tipline and public group messages alongside fact-checked claims that are first annotated for containing "claim-like statements" and then matched with potentially similar items and annotated for claim matching. Our dataset contains content in high-resource (English, Hindi) and lower-resource (Bengali, Malayalam, Tamil) languages. We train our own embedding model using knowledge distillation and a high-quality "teacher" model in order to address the imbalance in embedding quality between the low-and high-resource languages in our dataset. We provide evaluations on the performance of our solution and compare with baselines and existing state-of-the-art multilingual embedding models, namely LASER and LaBSE. We demonstrate that our performance exceeds LASER and LaBSE in all settings. We release our annotated datasets 1 , codebooks, and trained embedding model 2 to allow for further research.

There is currently no easy way to discover potentially problematic content on WhatsApp and other end-to-end encrypted platforms at scale. In this paper, we analyze the usefulness of a crowd-sourced tipline through which users can submit content (“tips”) that they want fact-checked. We compared the tips sent to a WhatsApp tipline run during the 2019 Indian general election with the messages circulating in large, public groups on WhatsApp and other social media platforms during the same period. We found that tiplines are a very useful lens into WhatsApp conversations: a significant fraction of messages and images sent to the tipline match with the content being shared on public WhatsApp groups and other social media. Our analysis also shows that tiplines cover the most popular content well, and a majority of such content is often shared to the tipline before appearing in large, public WhatsApp groups. Overall, our findings suggest tiplines can be an effective source for discovering potentially misleading content.

No abstract