Using Online Implicit Association Tests in Opinion Polling
- URL: http://arxiv.org/abs/2007.04183v1
- Date: Wed, 8 Jul 2020 15:16:15 GMT
- Title: Using Online Implicit Association Tests in Opinion Polling
- Authors: Alan Smeaton and Hyowon Lee and Niamh Morris and David Hanley
- Abstract summary: We analyse the phenomenon of socially desirable responding (shy voters) which has emerged as one of the reasons for modern day inaccurate polling.
We argue for inclusion of IATs in traditional polling and point to the fact that these can be conducted accurately online.
- Score: 2.102846336724103
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Opinion polls have now become a very important component of society because
they are now a defacto component of our daily news cycle and because their
results influence governments and business in ways which are not always obvious
to us. However, polling is not always accurate and there have been some really
inaccurate polling results which have had major influences on the world going
back to the 1930s but also as recently as just the last 3 or 4 years. In this
paper we analyse the phenomenon of socially desirable responding (shy voters)
which has emerged as one of the reasons for modern day inaccurate polling. We
describe how it can be exposed through implicit association tests (IATs) and we
demonstrate the shy voter effect in a small survey on opinions in Ireland
towards the United Kingdom. We argue for inclusion of IATs in traditional
polling and point to the fact that these can be conducted accurately online,
which also allows polling to reach a larger and more diverse sample of
respondents in the days of Covid-19 restrictions which restricts the
opportunities for poll sampling from the general public.
Related papers
- Representation Bias in Political Sample Simulations with Large Language Models [54.48283690603358]
This study seeks to identify and quantify biases in simulating political samples with Large Language Models.
Using the GPT-3.5-Turbo model, we leverage data from the American National Election Studies, German Longitudinal Election Study, Zuobiao dataset, and China Family Panel Studies.
arXiv Detail & Related papers (2024-07-16T05:52:26Z) - Analyzing and Estimating Support for U.S. Presidential Candidates in Twitter Polls [1.71952017922628]
We examine nearly two thousand Twitter polls gauging support for U.S. presidential candidates during the 2016 and 2020 election campaigns.
Our findings reveal that Twitter polls are biased in various ways, starting from the position of the presidential candidates.
The 2016 and 2020 polls were predominantly crafted by older males and manifested a pronounced bias favoring candidate Donald Trump.
arXiv Detail & Related papers (2024-06-05T14:57:29Z) - Election Polls on Social Media: Prevalence, Biases, and Voter Fraud Beliefs [5.772751069162341]
This study focuses on the 2020 presidential elections in the U.S.
We find that Twitter polls are disproportionately authored by older males and exhibit a large bias towards candidate Donald Trump.
We also find that Twitter accounts participating in election polls are more likely to be bots, and election poll outcomes tend to be more biased, before the election day than after.
arXiv Detail & Related papers (2024-05-18T02:29:35Z) - Political Compass or Spinning Arrow? Towards More Meaningful Evaluations for Values and Opinions in Large Language Models [61.45529177682614]
We challenge the prevailing constrained evaluation paradigm for values and opinions in large language models.
We show that models give substantively different answers when not forced.
We distill these findings into recommendations and open challenges in evaluating values and opinions in LLMs.
arXiv Detail & Related papers (2024-02-26T18:00:49Z) - Whose Opinions Do Language Models Reflect? [88.35520051971538]
We investigate the opinions reflected by language models (LMs) by leveraging high-quality public opinion polls and their associated human responses.
We find substantial misalignment between the views reflected by current LMs and those of US demographic groups.
Our analysis confirms prior observations about the left-leaning tendencies of some human feedback-tuned LMs.
arXiv Detail & Related papers (2023-03-30T17:17:08Z) - Design and analysis of tweet-based election models for the 2021 Mexican
legislative election [55.41644538483948]
We use a dataset of 15 million election-related tweets in the six months preceding election day.
We find that models using data with geographical attributes determine the results of the election with better precision and accuracy than conventional polling methods.
arXiv Detail & Related papers (2023-01-02T12:40:05Z) - Correcting public opinion trends through Bayesian data assimilation [8.406968279478347]
Measuring public opinion is a key focus during democratic elections.
Traditional survey polling remains the most popular estimation technique.
Twitter opinion mining has attempted to combat these issues.
arXiv Detail & Related papers (2021-05-29T11:39:56Z) - Mundus vult decipi, ergo decipiatur: Visual Communication of Uncertainty
in Election Polls [56.8172499765118]
We discuss potential sources of bias in nowcasting and forecasting.
Concepts are presented to attenuate the issue of falsely perceived accuracy.
One key idea is the use of Probabilities of Events instead of party shares.
arXiv Detail & Related papers (2021-04-28T07:02:24Z) - How Twitter Data Sampling Biases U.S. Voter Behavior Characterizations [6.364128212193265]
Recent studies reveal the existence of inauthentic actors such as malicious social bots and trolls.
In this paper, we aim to close this gap using Twitter data from the 2018 U.S. midterm elections.
We show that hyperactive accounts are more likely to exhibit various suspicious behaviors and share low-credibility information.
arXiv Detail & Related papers (2020-06-02T08:33:30Z) - Electoral Forecasting Using a Novel Temporal Attenuation Model:
Predicting the US Presidential Elections [91.3755431537592]
We develop a novel macro-scale temporal attenuation (TA) model, which uses pre-election poll data to improve forecasting accuracy.
Our hypothesis is that the timing of publicizing opinion polls plays a significant role in how opinion oscillates, especially right before elections.
We present two different implementations of the TA model, which accumulate an average forecasting error of 2.8-3.28 points over the 48-year period.
arXiv Detail & Related papers (2020-04-30T09:21:52Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.