arXiv subjects

Morgan Wack

Publications and source records attributed to Morgan Wack.

5 recordsLinked to original sources

arXiv2026

Researchers waste 80% of LLM annotation costs by classifying one text at a time

Large language models (LLMs) are increasingly being used for text classification across the social sciences, yet researchers overwhelmingly classify one text per variable per prompt. Coding 100,000 texts on four variables requires 400,000 API calls. Batching 25 items and stacking all variables into a single prompt reduces this to 4,000 calls, cutting token costs by over 80%. Whether this degrades coding quality is unknown. We tested eight production LLMs from four providers on 3,962 expert-coded tweets across four tasks, varying batch size from 1 to 1,000 items and stacking up to 25 coding dimensions per prompt. Six of eight models maintained accuracy within 2 pp of the single-item baseline through batch sizes of 100. Variable stacking with up to 10 dimensions produced results comparable to single-variable coding, with degradation driven by task complexity rather than prompt length. Within this safe operating range, the measurement error from batching and stacking is smaller than typical inter-coder disagreement in the ground-truth data.

cs.CL↗

arXiv2026

The Laziness of the Crowd: Effort Aversion Among Raters Risks Undermining the Efficacy of X's Community Notes Program

Crowdsourced moderation systems like Twitter/X's Community Notes program have been proposed as scalable alternatives to professional fact-checkers for combating online misinformation. While prior research has examined the effectiveness of such systems in reducing engagement with false content and their vulnerability to partisan bias, we identify a previously untested mechanism linking fact-check difficulty to systematic non-participation by crowdsourced raters. We hypothesize that claims requiring less cognitive effort to evaluate, specifically, those that are obviously false and easy to refute, are more likely to receive public notes than claims that are more plausible and require greater effort to debunk. Using eighteen months of vaccine-related Community Notes data (2,250 posts) and ratings from 382 survey participants, we show that claims perceived as more difficult to fact-check are significantly less likely to receive notes that achieve ``helpful''/public status. Following the conduct of additional analyses and a fact-checking process utilizing an LLM pipeline to help rule out alternative explanations, we interpret this pattern as consistent with an unwillingness among raters to invest the mental effort required to evaluate and rate notes for more plausible misinformation. These findings suggest that crowdsourced moderation may systematically fail to address the forms of plausible misinformation which are most likely to deceive. We discuss implications for platform design and propose mechanisms to mitigate this difficulty penalty in crowdsourced content moderation systems.

cs.HC↗

arXiv2024

Political Fact-Checking Efforts are Constrained by Deficiencies in Coverage, Speed, and Reach

Fact-checking has been promoted as a key method for combating political misinformation. Comparing the spread of election-related misinformation narratives along with their relevant political fact-checks, this study provides the most comprehensive assessment to date of the real-world limitations faced by political fact-checking efforts. To examine barriers to impact, this study extends recent work from laboratory and experimental settings to the wider online information ecosystem present during the 2022 U.S. midterm elections. From analyses conducted within this context, we find that fact-checks as currently developed and distributed are severely inhibited in election contexts by constraints on their i. coverage, ii. speed, and, iii. reach. Specifically, we provide evidence that fewer than half of all prominent election-related misinformation narratives were fact-checked. Within the subset of fact-checked claims, we find that the median fact-check was released a full four days after the initial appearance of a narrative. Using network analysis to estimate user partisanship and dynamics of information spread, we additionally find evidence that fact-checks make up less than 1.2\% of narrative conversations and that even when shared, fact-checks are nearly always shared within,rather than between, partisan communities. Furthermore, we provide empirical evidence which runs contrary to the assumption that misinformation moderation is politically biased against the political right. In full, through this assessment of the real-world influence of political fact-checking efforts, our findings underscore how limitations in coverage, speed, and reach necessitate further examination of the potential use of fact-checks as the primary method for combating the spread of political misinformation.

cs.SI↗

arXiv2024

ElectionRumors2022: A Dataset of Election Rumors on Twitter During the 2022 US Midterms

Understanding the spread of online rumors is a pressing societal challenge and an active area of research across domains. In the context of the 2022 U.S. midterm elections, one influential social media platform for sharing information -- including rumors that may be false, misleading, or unsubstantiated -- was Twitter (now renamed X). To increase understanding of the dynamics of online rumors about elections, we present and analyze a dataset of 1.81 million Twitter posts corresponding to 135 distinct rumors which spread online during the midterm election season (September 5 to December 1, 2022). We describe how this data was collected, compiled, and supplemented, and provide a series of exploratory analyses along with comparisons to a previously-published dataset on 2020 election rumors. We also conduct a mixed-methods analysis of three distinct rumors about the election in Arizona, a particularly prominent focus of 2022 election rumoring. Finally, we provide a set of potential future directions for how this dataset could be used to facilitate future research into online rumors, misinformation, and disinformation.

cs.SI↗

arXiv2023

Followback Clusters, Satellite Audiences, and Bridge Nodes: Coengagement Networks for the 2020 US Election

The 2020 United States presidential election was, and has continued to be, the focus of pervasive and persistent mis- and disinformation spreading through our media ecosystems, including social media. This event has driven the collection and analysis of large, directed social network datasets, but such datasets can resist intuitive understanding. In such large datasets, the overwhelming number of nodes and edges present in typical representations create visual artifacts, such as densely overlapping edges and tightly-packed formations of low-degree nodes, which obscure many features of more practical interest. We apply a method, coengagement transformations, to convert such networks of social data into tractable images. Intuitively, this approach allows for parameterized network visualizations that make shared audiences of engaged viewers salient to viewers. Using the interpretative capabilities of this method, we perform an extensive case study of the 2020 United States presidential election on Twitter, contributing an empirical analysis of coengagement. By creating and contrasting different networks at different parameter sets, we define and characterize several structures in this discourse network, including bridging accounts, satellite audiences, and followback communities. We discuss the importance and implications of these empirical network features in this context. In addition, we release open-source code for creating coengagement networks from Twitter and other structured interaction data.

cs.SI↗