Manoel Horta Ribeiro

Manoel Horta Ribeiro

Auto-generated profile, based on publicly available information

Manoel Horta Ribeiro

Princeton University, Princeton, USA

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
19 May 2025 in Nature Human Behaviour
Verified
Journal Article
Open access
PDF file
FSFrancesco Salvi
Francesco Salvi
MRManoel Horta Ribeiro
Manoel Horta Ribeiro
RGRiccardo Gallotti
Riccardo Gallotti
RWRobert West
Robert West
Early work has found that large language models (LLMs) can generate persuasive content. However, evidence on whether they can also personalize arguments to individual attributes remains limited, despite being crucial for assessing misuse. This preregistered study examines AI-driven persuasion in a controlled setting, where participants engaged in short multiround debates. Participants were randomly assigned to 1 of 12 conditions in a 2 × 2 × 3 design: (1) human or GPT-4 debate opponent; (2) opponent with or without access to sociodemographic participant data; (3) debate topic of low, medium or high opinion strength. In debate pairs where AI and humans were not equally persuasive, GPT-4 with personalization was more persuasive 64.4% of the time (81.2% relative increase in odds of higher post-debate agreement; 95% confidence interval [+26.0%, +160.7%], P < 0.01; N = 900). Our findings highlight the power of LLM-based persuasion and have implications for the governance and design of online platforms.

5 June 2024 in Research Square
Verified
Preprint
Open access
PDF file
FSFrancesco Salvi
Francesco Salvi
MRManoel Horta Ribeiro
Manoel Horta Ribeiro
RGRiccardo Gallotti
Riccardo Gallotti
RWRobert West
Robert West
Can large language models (LLMs) create tailor-made, convincing arguments to promote false or misleading narratives online? Early work has found that LLMs can generate content perceived on par with, or even more persuasive than, human-written messages. However, there is still limited evidence regarding LLMs' persuasive capabilities in direct conversations with humans—the scenario these models are usually deployed at. In this pre-registered study, we analyze the power of AI-driven persuasion in a controlled, harmless setting. To this end, we created a web-based platform where human participants engaged in short, multi-round debates with either human or LLM opponents. Each participant was randomly assigned to one of four treatment conditions in a two-by-two factorial design: (1) the conversation partner was either another human or an LLM; (2) the conversation partner either had or did not have access to basic sociodemographic information about their opponent (and thus arguments could be personalized). We find that 64.4% of the time, personalized LLM debaters were more persuasive than humans, given that they were not equally persuasive (81.2% relative increase in the odds of higher post-debate agreement; p < 0.01; N=900). Without personalization, GPT-4 still outperformed humans, but the effect was lower and not statistically significant (p=0.30). Further, our analysis suggests that LLMs use different strategies from human debaters: their texts are harder to read and have more markers associated with logical and analytical reasoning. Overall, our results suggest that concerns around LLM-based persuasion are meaningful and have important implications for social media governance and the design of new online environments.

13 February 2024 in Proceedings of the National Academy of Sciences
Verified
Journal Article
Open access
HHHoma Hosseinmardi
Homa Hosseinmardi
AGAmir Ghasemian
Amir Ghasemian
MRMiguel Rivera-Lanas
Miguel Rivera-Lanas
MRManoel Horta Ribeiro
Manoel Horta Ribeiro
RWRobert West
Robert West
DWDuncan J. Watts
Duncan J. Watts
In recent years, critics of online platforms have raised concerns about the ability of recommendation algorithms to amplify problematic content, with potentially radicalizing consequences. However, attempts to evaluate the effect of recommenders have suffered from a lack of appropriate counterfactuals—what a user would have viewed in the absence of algorithmic recommendations—and hence cannot disentangle the effects of the algorithm from a user’s intentions. Here we propose a method that we call “counterfactual bots” to causally estimate the role of algorithmic recommendations on the consumption of highly partisan content on YouTube. By comparing bots that replicate real users’ consumption patterns with “counterfactual” bots that follow rule-based trajectories, we show that, on average, relying exclusively on the YouTube recommender results in less partisan consumption, where the effect is most pronounced for heavy partisan consumers. Following a similar method, we also show that if partisan consumers switch to moderate content, YouTube’s sidebar recommender “forgets” their partisan preference within roughly 30 videos regardless of their prior history, while homepage recommendations shift more gradually toward moderate content. Overall, our findings indicate that, at least since the algorithm changes that YouTube implemented in 2019, individual consumption patterns mostly reflect individual preferences, where algorithmic recommendations play, if anything, a moderating role.

16 October 2025 in Proceedings of the ACM on Human-Computer Interaction
Verified
Journal Article
Open access
GRGiuseppe Russo
Giuseppe Russo
MRManoel Horta Ribeiro
Manoel Horta Ribeiro
TDTim Ruben Davidson
Tim Ruben Davidson
VVVeniamin Veselovsky
Veniamin Veselovsky
RWRobert West
Robert West
Journals and conferences worry that peer reviews assisted by artificial intelligence (AI), in particular, large language models (LLMs), may negatively influence the validity and fairness of the peer-review system, a cornerstone of modern science. In this work, we address this concern with a study of the prevalence and impact of AI-assisted peer reviews in the context of the 2024 International Conference on Learning Representations (ICLR), a large and prestigious machine-learning conference. Our contributions are threefold. Firstly, we obtain a lower bound for the prevalence of AI-assisted reviews at ICLR 2024 using the closed- and open-source LLM detectors, estimating that at least 15.8% of reviews were written with AI assistance. Secondly, we estimate the impact of AI-assisted reviews on submission scores. Considering pairs of reviews with different scores assigned to the same paper, we find that in 53.4% of pairs, the AI-assisted review scores higher than the human review (p = 0.002; relative difference in probability of scoring higher: +14.4% in favor of AI-assisted reviews). Thirdly, we assess the impact of receiving an AI-assisted peer review on submission acceptance. In a matched study, submissions near the acceptance threshold that received an AI-assisted peer review were 4.9 percentage points (p = 0.024) more likely to be accepted than submissions that did not. Overall, we show that AI-assisted reviews are consequential to the peer-review process and offer a discussion on future implications of current trends.

1 March 2023 in PNAS Nexus
Verified
Journal Article
Open access
PDF file
MRManoel Horta Ribeiro
Manoel Horta Ribeiro
HHHoma Hosseinmardi
Homa Hosseinmardi
RWRobert West
Robert West
DWDuncan J Watts
Duncan J Watts
Online platforms have banned (“deplatformed”) influencers, communities, and even entire websites to reduce content deemed harmful. Deplatformed users often migrate to alternative platforms, which raises concerns about the effectiveness of deplatforming. Here, we study the deplatforming of Parler, a fringe social media platform, between 2020 January 11 and 2021 February 25, in the aftermath of the US Capitol riot. Using two large panels that capture longitudinal user-level activity across mainstream and fringe social media content (N = 112, 705, adjusted to be representative of US desktop and mobile users), we find that other fringe social media, such as Gab and Rumble, prospered after Parler’s deplatforming. Further, the overall activity on fringe social media increased while Parler was offline. Using a difference-in-differences analysis (N = 996), we then identify the causal effect of deplatforming on active Parler users, finding that deplatforming increased the probability of daily activity across other fringe social media in early 2021 by 10.9 percentage points (pp) (95% CI [5.9 pp, 15.9 pp]) on desktop devices, and by 15.9 pp (95% CI [10.2 pp, 21.7 pp]) on mobile devices, without decreasing activity on fringe social media in general (including Parler). Our results indicate that the isolated deplatforming of a major fringe platform was ineffective at reducing overall user activity on fringe social media.

30 April 2023
Verified
Conference Paper
Open access
MRManoel Horta Ribeiro
Manoel Horta Ribeiro
JCJustin Cheng
Justin Cheng
RWRobert West
Robert West
Online social media platforms use automated moderation systems to remove or reduce the visibility of rule-breaking content. While previous work has documented the importance of manual content moderation, the effects of automated content moderation remain largely unknown. Here, in a large study of Facebook comments (n = 412M), we used a fuzzy regression discontinuity design to measure the impact of automated content moderation on subsequent rule-breaking behavior (number of comments hidden/deleted) and engagement (number of additional comments posted). We found that comment deletion decreased subsequent rule-breaking behavior in shorter threads (20 or fewer comments), even among other participants, suggesting that the intervention prevented conversations from derailing. Further, the effect of deletion on the affected user’s subsequent rule-breaking behavior was longer-lived than its effect on reducing commenting in general, suggesting that users were deterred from rule-breaking but not from commenting. In contrast, hiding (rather than deleting) content had small and statistically insignificant effects. Our results suggest that automated content moderation increases adherence to community guidelines.