arXiv subjects

Rasmus K. Rendsvig

Publications and source records attributed to Rasmus K. Rendsvig.

12 recordsLinked to original sources

arXiv2023

Friction Interventions to Curb the Spread of Misinformation on Social Media

Social media has enabled the spread of information at unprecedented speeds and scales, and with it the proliferation of high-engagement, low-quality content. *Friction* -- behavioral design measures that make the sharing of content more cumbersome -- might be a way to raise the quality of what is spread online. Here, we study the effects of friction with and without quality-recognition learning. Experiments from an agent-based model suggest that friction alone decreases the number of posts without improving their quality. A small amount of friction combined with learning, however, increases the average quality of posts significantly. Based on this preliminary evidence, we propose a friction intervention with a learning component about the platform's community standards, to be tested via a field experiment. The proposed intervention would have minimal effects on engagement and may easily be deployed at scale.

cs.SI↗

arXiv2023

Danish National Election 2022 Twitter Data on Likes, Retweets, and Botscores for the Purpose of Exploring Coordinated Inauthenthic Behavior

This note describes code and experiments related to a Twitter dataset on the Danish National Election 2022, available at Harvard Dataverse (doi.org/10.7910/DVN/RWPZUN). We cluster Twitter users into bins of users that showed exactly the same liking/retweeting behavior over a month-long period during which the Danish National Election took place. To investigate whether any of these bins exhibited coordinated inauthentic behavior, we were interested in whether bin size correlated with user account deletions/suspensions and/or high bot scores from Botometer / Botometer Lite. We did not find significant correlations (also neither between Botometer and Botometer Lite scores). This note primarily contains the README.md from the GitHub repository LJ-9/Danish-Election-2022-Twitter-Likes-Retweets-Botscores-Inauthentic-Coordinated-Behavior of the same name, with a few additional comments and references. We upload the note for visibility, hoping that other researchers may find the data of use.

cs.SI↗

arXiv2023

Detecting Coordinated Inauthentic Behavior in Likes on Social Media: Proof of Concept

Coordinated inauthentic behavior is used as a tool on social media to shape public opinion by elevating or suppressing topics using systematic engagements -- e.g. through *likes* or similar reactions. In an honest world, reactions may be informative to users when selecting on what to spend their attention: through the wisdom of crowds, summed reactions may help identifying relevant and high-quality content. This is nullified by coordinated inauthentic liking. To restore wisdom-of-crowds effects, it is therefore desirable to separate the inauthentic agents from the wise crowd, and use only the latter as a voting *jury* on the relevance of a post. To this end, we design two *jury selection procedures* (JSPs) that discard agents classified as inauthentic. Using machine learning techniques, both cluster on binary vote data -- one using a Gaussian Mixture Model (GMM JSP), one the k-means algorithm (KM JSP) -- and label agents by logistic regression. We evaluate the jury selection procedures with an agent-based model, and show that the GMM JSP detects more inauthentic agents, but both JSPs select juries with vastly increased correctness of vote by majority. This proof of concept provides an argument for the release of reactions data from social media platforms through a direct use-case in the fight against online misinformation.

cs.CY↗

arXiv2023

Towards Detecting Inauthentic Coordination in Twitter Likes Data

Social media feeds typically favor posts according to user engagement. The most ubiquitous type of engagement (and the type we study) is *likes*. Users customarily take engagement metrics such as likes as a neutral proxy for quality and authority. This incentivizes like manipulation to influence public opinion through *coordinated inauthentic behavior* (CIB). CIB targeted at likes is largely unstudied as collecting suitable data about users' liking behavior is non-trivial. This paper contributes a scripted algorithm to collect suitable liking data from Twitter and a collected 30 day dataset of liking data from the Danish political Twittersphere #dkpol, over which we analyze the script's performance. Using only the binary matrix of users and the tweets they liked, we identify large clusters of perfectly correlated users, and discuss our findings in relation to CIB.

cs.SI↗

arXiv2021

Awareness Logic: Kripke Lattices as a Middle Ground between Syntactic and Semantic Models

The literature on awareness modeling includes both syntax-free and syntax-based frameworks. Heifetz, Meier \& Schipper (HMS) propose a lattice model of awareness that is syntax-free. While their lattice approach is elegant and intuitive, it precludes the simple option of relying on formal language to induce lattices, and does not explicitly distinguish uncertainty from unawareness. Contra this, the most prominent syntax-based solution, the Fagin-Halpern (FH) model, accounts for this distinction and offers a simple representation of awareness, but lacks the intuitiveness of the lattice structure. Here, we combine these two approaches by providing a lattice of Kripke models, induced by atom subset inclusion, in which uncertainty and unawareness are separate. We show our model equivalent to both HMS and FH models by defining transformations between them which preserve satisfaction of formulas of a language for explicit knowledge, and obtain completeness through our and HMS' results. Lastly, we prove that the Kripke lattice model can be shown equivalent to the FH model (when awareness is propositionally determined) also with respect to the language of the Logic of General Awareness, for which the FH model where originally proposed.

cs.AI↗

arXiv2021

Epistemic Planning with Attention as a Bounded Resource

Where information grows abundant, attention becomes a scarce resource. As a result, agents must plan wisely how to allocate their attention in order to achieve epistemic efficiency. Here, we present a framework for multi-agent epistemic planning with attention, based on Dynamic Epistemic Logic (DEL, a powerful formalism for epistemic planning). We identify the framework as a fragment of standard DEL, and consider its plan existence problem. While in the general case undecidable, we show that when attention is required for learning, all instances of the problem are decidable.

cs.AI↗

arXiv2020

Awareness Logic: A Kripke-based Rendition of the Heifetz-Meier-Schipper Model

Heifetz, Meier and Schipper (HMS) present a lattice model of awareness. The HMS model is syntax-free, which precludes the simple option to rely on formal language to induce lattices, and represents uncertainty and unawareness with one entangled construct, making it difficult to assess the properties of either. Here, we present a model based on a lattice of Kripke models, induced by atom subset inclusion, in which uncertainty and unawareness are separate. We show the models to be equivalent by defining transformations between them which preserve formula satisfaction, and obtain completeness through our and HMS' results.

cs.AI↗

arXiv2019

Dynamic Term-Modal Logic for Epistemic Social Network Dynamics (Extended Version)

Logics for social networks have been studied in recent literature. This paper presents a framework based on *dynamic term-modal logic* (DTML), a quantified variant of dynamic epistemic logic (DEL). In contrast with DEL where it is commonly known to whom agent names refer, DTML can represent dynamics with uncertainty about agent identity. We exemplify dynamics where such uncertainty and de re/de dicto distinctions are key to social network epistemics. Technically, we show that DTML semantics can represent a popular class of hybrid logic epistemic social network models. We also show that DTML can encode previously discussed dynamics for which finding a complete logic was left open. As complete reduction axioms systems exist for DTML, this yields a complete system for the dynamics in question.

cs.MA↗

arXiv2017

Convergence, Continuity and Recurrence in Dynamic Epistemic Logic

The paper analyzes dynamic epistemic logic from a topological perspective. The main contribution consists of a framework in which dynamic epistemic logic satisfies the requirements for being a topological dynamical system thus interfacing discrete dynamic logics with continuous mappings of dynamical systems. The setting is based on a notion of logical convergence, demonstratively equivalent with convergence in Stone topology. Presented is a flexible, parametrized family of metrics inducing the latter, used as an analytical aid. We show maps induced by action model transformations continuous with respect to the Stone topology and present results on the recurrent behavior of said maps.

cs.LO↗

arXiv2017

Metrics for Formal Structures, with an Application to Kripke Models and their Dynamics

This report introduces and investigates a family of metrics on sets of pointed Kripke models. The metrics are generalizations of the Hamming distance applicable to countably infinite binary strings and, by extension, logical theories or semantic structures. We first study the topological properties of the resulting metric spaces. A key result provides sufficient conditions for spaces having the Stone property, i.e., being compact, totally disconnected and Hausdorff. Second, we turn to mappings, where it is shown that a widely used type of model transformations, product updates, give rise to continuous maps in the induced topology.

math.LO↗

arXiv2017

Diffusion, Influence and Best-Response Dynamics in Networks: An Action Model Approach

Threshold models and their dynamics may be used to model the spread of `behaviors' in social networks. Regarding such from a modal logical perspective, it is shown how standard update mechanisms may be emulated using action models -- graphs encoding agents' decision rules. A small class of action models capturing the possible sets of decision rules suitable for threshold models is identified, and shown to include models characterizing best-response dynamics of both coordination and anti-coordination games played on graphs.

cs.GT↗

arXiv2017

Turing Completeness of Finite, Epistemic Programs

In this note, we show the class of finite, epistemic programs to be Turing complete. Epistemic programs is a widely used update mechanism used in epistemic logic, where it such are a special type of action models: One which does not contain postconditions.

cs.FL↗