Digital deliberation has expanded democratic participation, yet challenges remain. This includes processing information at scale, moderating discussions, fact-checking, or attracting people to participate. Recent advances in artificial intelligence (AI) offer potential solutions, but public perceptions of AI's role in deliberation remain underexplored. Beyond efficiency, democratic deliberation is about voice and recognition. If AI is integrated into deliberation, public trust, acceptance, and willingness to participate may be affected. We conducted a preregistered survey experiment with a representative sample in Germany (n=1850) to examine how information about AI-enabled deliberation influences willingness to participate and perceptions of deliberative quality. Respondents were randomly assigned to treatments that provided them information about deliberative tasks facilitated by either AI or humans. Our findings reveal a significant AI-penalty. Participants were less willing to engage in AI-facilitated deliberation and rated its quality lower than human-led formats. These effects were moderated by individual predispositions. Perceptions of AI's societal benefits and anthropomorphization of AI showed positive interaction effects on people's interest to participate in AI-enabled deliberative formats and positive quality assessments, while AI risk assessments showed negative interactions with information about AI-enabled deliberation. These results suggest AI-enabled deliberation faces substantial public skepticism, potentially even introducing a new deliberative divide. Unlike traditional participation gaps based on education or demographics, this divide is shaped by attitudes toward AI. As democratic engagement increasingly moves online, ensuring AI's role in deliberation does not discourage participation or deepen inequalities will be a key challenge for future research and policy.

Measuring the quality of contributions in political online discussions is crucial in deliberation research and computer science. Research has identified various indicators to assess online discussion quality, and with deep learning advancements, automating these measures has become feasible. While some studies focus on analyzing specific quality indicators, a comprehensive quality score incorporating various deliberative aspects is often preferred. In this work, we introduce AQuA, an additive score that calculates a unified deliberative quality score from multiple indices for each discussion post. Unlike other singular scores, AQuA preserves information on the deliberative aspects present in comments, enhancing model transparency. We develop adapter models for 20 deliberative indices, and calculate correlation coefficients between experts' annotations and the perceived deliberativeness by non-experts to weigh the individual indices into a single deliberative score. We demonstrate that the AQuA score can be computed easily from pre-trained adapters and aligns well with annotations on other datasets that have not be seen during training. The analysis of experts' vs. non-experts' annotations confirms theoretical findings in the social science literature.