Hope vs. Hate: Understanding User Interactions with LGBTQ+ News Content in Mainstream US News Media through the Lens of Hope Speech

This paper makes three contributions. First, via a substantial corpus of 1,419,047 comments posted on 3,161 YouTube news videos of major US cable news outlets, we analyze how users engage with LGBTQ+ news content. Our analyses focus both on positive and negative content. In particular, we construct a hope speech classifier that detects positive (hope speech), negative, neutral, and irrelevant content. Second, in consultation with a public health expert specializing on LGBTQ+ health, we conduct an annotation study with a balanced and diverse political representation and release a dataset of 3,750 instances with crowd-sourced labels and detailed annotator demographic information. Finally, beyond providing a vital resource for the LGBTQ+ community, our annotation study and subsequent in-the-wild assessments reveal (1) strong association between rater political beliefs and how they rate content relevant to a marginalized community, (2) models trained on individual political beliefs exhibit considerable in-the-wild disagreement, and (3) zero-shot large language models (LLMs) align more with liberal raters. Trigger Warning: this paper contains offensive material that some may find upsetting. From crowdsourced storymapping projects sharing stories of love, loss, and a sense of belonging (Kirby et al., 2021) to safe, anonymous spaces to seek resources (McInroy et al., 2019) and dating platforms (Blackwell et al., 2015) -the internet and modern technologies play a positive role in the health and well-being of the LGBTQ+ community in various ways. However, cyberbullying (Abreu and Kenny, 2018), exposure to dehumanization through news media (Mendelsohn et al., 2020) , and more recently, homophobic biases in large language models (LLMs) (Dutta et al., 2024a(Dutta et al., , 2025a) -* Ashiqur R. KhudaBukhsh is the corresponding author. are some of the modern technology perils the community grapples with.