Modeling Voters in Multi-Winner Approval Voting
Authors: Jaelle Scheuerman, Jason Harman, Nicholas Mattei, K. Brent Venable5709-5716
AAAI 2021 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | In this paper, we examine voting behavior in single-winner and multi-winner approval voting scenarios with varying degrees of uncertainty using behavioral data obtained from Mechanical Turk. |
| Researcher Affiliation | Collaboration | 1 U.S. Naval Research Laboratory, Stennis Space Center, MS, USA 2 Louisiana State University, Baton Rouge, LA, USA 3 Tulane University, New Orleans, LA, USA 4 University of West Florida and Institute for Human and Machine Cognition, Pensacola, FL, USA |
| Pseudocode | No | The paper describes mathematical formulas and heuristics but does not include any explicitly labeled pseudocode or algorithm blocks. |
| Open Source Code | No | The paper does not provide an explicit statement or a direct link to the source code for the methodology described in this paper. Citations to prior work and a third-party library are present, but not the code for this specific research. |
| Open Datasets | No | The paper states, 'Our behavioral study aimed at investigating approval voting heuristics and included 104 participants recruited through Mechanical Turk.' It does not provide concrete access information (link, citation for public dataset, etc.) to this collected behavioral data. |
| Dataset Splits | Yes | We use five of these observations to train the parameters of the AU or AUT model and predict the sixth. Using a leave-one-out methodology, we do this for all possible splits of the data. We compute the accuracy over these six splits for each individual. |
| Hardware Specification | No | The paper does not explicitly describe the hardware used to run its experiments. |
| Software Dependencies | No | The paper does not provide specific version numbers for any software dependencies used in the experiments. |
| Experiment Setup | Yes | Using a grid search, we fit α {0, 1, 2} and β {1, 2, . . . , 32}. ... we choose to set α = 1 and fit only β and τ. Using a grid search, we tested values for β {1, 2, . . . , 32} and τ {0, 0.0005, . . . , 0.10}. |