Wisdom Of Crowds Research Articles

Ensembles of multiple models for soil moisture retrieval from remote sensing data over agricultural areas: A deep learning-based framework

In agricultural areas, most surface soil moisture (SM) retrieval models are unstable in terms of their accuracy and performance during crop growth. As a result, there is no consensus on which model performs optimally during the agricultural season. This is because of the uncertainties associated with model physics, initial conditions, model inversion processes, input data, vegetation attenuation and soil characteristics. To better deal with these practical concerns, we propose a simple, but robust SM retrieval method of using combination of multiple models based on deep learning and multi-model ensemble approach, called the DL-MME method, which makes use of the ‘collective intelligence’ and ‘wisdom of crowds’ concepts. The advantages of this method are: (1) robustness to model selection, and (2) robustness to model calibration during the growing season. In addition, this method is less dependent on one type of data across various agricultural areas compared to the single model approach. Firstly, the coupled water cloud model (WCM) and soil backscattering models (Oh model or advanced integral equation model (AIEM)) with different vegetation descriptors were calibrated and validated during the growing season in sugarcane and winter wheat fields for Sentinel-1 backscattering coefficients (VV and VH). SM was also retrieved by employing the trapezoid model (OPTRAM) with different parameters from Sentinel-2 images. To optimize SM retrieval computations, we used the outputs from optical and SAR models, auxiliary features, and reliable in situ SM measurements as inputs to a deep learning convolutional neural network (DL-CNN). For sugarcane and wheat fields in the early stages of crop growth, WCM models retrieved more accurate time-series SM than optical models. OPTRAM soil moisture retrievals showed greater accuracy in the late crop growing season. Time-series SM retrieval accuracy using DL-MME was higher than for the optical and semi-empirical SAR models. According to the results of the in situ validation for wheat (sugarcane) fields, the minimum MAE by an optimal combination of models was around 0.01 (0.02) m3m−3 (RMSE = 0.036 (0.074) m3m−3; R = 0.87 (0.71)). The findings demonstrate that our method is reliable and feasible for SM retrieval. Additionally, our method provides a way to select an optimal model for retrieving time-series SM during the crop growing season.

Conventional and frugal methods of estimating COVID-19-related excess deaths and undercount factors

Across the world, the officially reported number of COVID-19 deaths is likely an undercount. Establishing true mortality is key to improving data transparency and strengthening public health systems to tackle future disease outbreaks. In this study, we estimated excess deaths during the COVID-19 pandemic in the Pune region of India. Excess deaths are defined as the number of additional deaths relative to those expected from pre-COVID-19-pandemic trends. We integrated data from: (a) epidemiological modeling using pre-pandemic all-cause mortality data, (b) discrepancies between media-reported death compensation claims and official reported mortality, and (c) the “wisdom of crowds” public surveying. Our results point to an estimated 14,770 excess deaths [95% CI 9820–22,790] in Pune from March 2020 to December 2021, of which 9093 were officially counted as COVID-19 deaths. We further calculated the undercount factor—the ratio of excess deaths to officially reported COVID-19 deaths. Our results point to an estimated undercount factor of 1.6 [95% CI 1.1–2.5]. Besides providing similar conclusions about excess deaths estimates across different methods, our study demonstrates the utility of frugal methods such as the analysis of death compensation claims and the wisdom of crowds in estimating excess mortality.

Speaker identification in courtroom contexts – Part III: Groups of collaborating listeners compared to forensic voice comparison based on automatic-speaker-recognition technology

Expert testimony is only admissible in common-law systems if it will potentially assist the trier of fact. In order for a forensic-voice-comparison expert’s testimony to assist a trier of fact, the expert’s forensic voice comparison should be more accurate than the trier of fact’s speaker identification. “Speaker identification in courtroom contexts – Part I” addressed the question of whether speaker identification by an individual lay listener (such as a judge) would be more or less accurate than the output of a forensic-voice-comparison system that is based on state-of-the-art automatic-speaker-recognition technology. The present paper addresses the question of whether speaker identification by a group of collaborating lay listeners (such as a jury) would be more or less accurate than the output of such a forensic-voice-comparison system. As members of collaborating groups, participants listen to pairs of recordings reflecting the conditions of the questioned- and known-speaker recordings in an actual case, confer, and make a probabilistic consensus judgement on each pair of recordings. The present paper also compares group-consensus responses with “wisdom of the crowd” which uses the average of the responses from multiple independent individual listeners.

The financial dimension of football injuries according to the wisdom of crowds

ABSTRACT Research question How football players’ injuries and consequent days missed on the pitch affect their market values is an under-researched topic. In this study, we thus examine this association for a large sample of football players. Research methods We use an OLS regression model, where the dependent variable is the footballers’ market value provided by Transfermarkt over time for 9,230 observations from 2006-2020. Results Our findings show that an injured player’s market value drops by 0.08% for each day out of the game and training. When the injury is severe (more than 28 days of absence) the fall increases to 11.2% of market values. These drops depend on player type (famous or non-famous), injury type (muscles, ligaments, bones, and others) and its severity. Implications Quantifying the impact of injuries on football clubs’ intangible capital is crucial for effective risk management and strategic sporting planning.

Herding the crowds: how sentiment affects crowdsourced earnings estimates

AbstractThis study investigates the impact of firm-level investor sentiment derived from Twitter and news media on herding behavior among contributors on Estimize, a leading platform for crowdsourced earnings forecasts. The findings show that sentiment gleaned from tweets and news media content positively influences herding among Estimize contributors. Notably, herding intensifies when Twitter and news sentiment polarities align, while divergent sentiment polarities diminish this herding effect. Additionally, the analysis indicates that firms with investment-grade ratings and those characterized by low valuation uncertainty are particularly prone to sentiment-driven herding. Importantly, positive sentiment is identified as having a more potent influence on herding behavior than negative sentiment. By focusing on Estimize contributors, this study offers insights into how firm-level sentiment cues shape the crowd’s herding behavior, offering new perspectives on how different media sources shape the wisdom of the crowd.

WoFS and the Wisdom of the Crowd: The Impact of the Warn-on-Forecast System on Hourly Forecasts during the 2021 NOAA Hazardous Weather Testbed Spring Forecasting Experiment

Abstract During the 2021 Spring Forecasting Experiment (SFE), the usefulness of the experimental Warn-on-Forecast System (WoFS) ensemble guidance was tested with the issuance of short-term probabilistic hazard forecasts. One group of participants used the WoFS guidance, while another group did not. Individual forecasts issued by two NWS participants in each group were evaluated alongside a consensus forecast from the remaining participants. Participant forecasts of tornadoes, hail, and wind at lead times of ∼2–3 h and valid at 2200–2300, 2300–0000, and 0000–0100 UTC were evaluated subjectively during the SFE by participants the day after issuance, and objectively after the SFE concluded. These forecasts exist between the watch and the warning time frame, where WoFS is anticipated to be particularly impactful. The hourly probabilistic forecasts were skillful according to objective metrics like the fractions skill score. While the tornado forecasts were more reliable than the other hazards, there was no clear indication of any one hazard scoring highest across all metrics. WoFS availability improved the hourly probabilistic forecasts as measured by the subjective ratings and several objective metrics, including increased POD and decreased FAR at high probability thresholds. Generally, expert forecasts performed better than consensus forecasts, though expert forecasts overforecasted. Finally, this work explored the appropriate construction of practically perfect fields used during subjective verification, which participants frequently found to be too small and precise. Using a Gaussian smoother with σ = 70 km is recommended to create hourly practically perfect fields in future experiments. Significance Statement This work explores the impact of cutting-edge numerical weather prediction ensemble guidance (the Warn-on-Forecast System) on severe thunderstorm hazard outlooks at watch-to-warning time scales, typically between 1 and 6 h of lead time. Real-time forecast products in this time frame are currently provided on an as-needed basis, and the transition to continuous probabilistic forecast products across scales requires targeted research. Results showed that hourly probabilistic participant forecasts were skillful subjectively and statistically, and that the experimental guidance improved the forecasts. These results are promising for the implementation and value of the Warn-on-Forecast System to provide improved hazard timing and location guidance within severe weather watches. Suggestions are made to aid future subjective evaluations of watch-to-warning-scale probabilistic forecasts.

How Text-to-Image Generative AI Is Transforming Mediated Action.

This article examines the intricate relationship between humans and text-to-image generative models (generative artificial intelligence/genAI) in the realm of art. The article frames that relationship in the theory of mediated action-a well-established theory that conceptualizes how tools shape human thoughts and actions. The article describes genAI systems as learning, cocreating, and communicating, multimodally capable hybrid systems that distill and rely on the wisdom and creativity of massive crowds of people and can sometimes surpass them. Those systems elude the theoretical description of the role of tools and locus of control in mediated action. The article asks how well the theory can accommodate both the transformative potential of genAI tools in creative fields and art, and the ethics of the emergent social dynamics it generates. The article concludes by discussing the fundamental changes and broader implications that genAI brings to the realm of mediated action and, ultimately, to the very fabric of our daily lives.

Avoidance, confusion or solitude? Modelling how noise pollution affects whale migration

Many baleen whales are renowned for their acoustic communication. Under pristine conditions, this communication can plausibly occur across hundreds of kilometres. Frequent vocalisations may allow a dispersed migrating group to maintain contact, and therefore benefit from improved navigation via the “wisdom of the crowd”. Human activities have considerably inflated ocean noise levels. Here we develop a data-driven mathematical model to investigate how ambient noise levels may inhibit whale migration. Mathematical models allow us to simultaneously simulate collective whale migration behaviour, auditory cue detection, and noise propagation. Rising ambient noise levels are hypothesised to influence navigation through three mechanisms: (i) diminished communication space; (ii) reduced ability to hear external sound cues and; (iii) triggering noise avoidance behaviour. Comparing pristine and current soundscapes, we observe navigation impairment that ranges from mild (increased journey time) to extreme (failed navigation). Notably, the three mechanisms induce qualitatively different impacts on migration behaviour. We demonstrate the model’s potential predictive power, exploring the extent to which migration may be altered under future shipping and construction scenarios.

Distilling wisdom of crowds in online communities: A novel prediction market constructed with comment posters

Aggregating the wisdom of crowds from user-generated content in the online community can be valuable for decision-making. However, low-quality comments pose significant challenges for traditional wisdom extraction algorithms, such as prediction polls. Therefore, to extract the wisdom of online crowds effectively, we propose a novel artificial prediction market that can dynamically filter out low-quality comments using the market mechanism. Unlike traditional prediction markets where real human traders participate in contract trading, traders in the proposed market, referred to as artificial human traders, are constructed with posters’ online comments. We constructed artificial human traders using the comment data from the Eastmoney stock forum. Then, we validated the effectiveness of the proposed market in predicting the price movements of the constituent stocks in the Shanghai Stock Exchange 50 Index. Experimental results demonstrate that the proposed market excels in extracting the wisdom of crowds from online communities for stock price movement predictions and conducting investment portfolios based on these prediction results. Additionally, to investigate the factors contributing to the superior performance of the proposed artificial prediction market, we compare it with the prediction poll, a well-known opinion aggregation algorithm. The results indicate that the artificial prediction market performs better in assessing the quality of comments compared with the prediction poll.

Datification of the wisdom of the crowd: a comparative analysis of innovation strategies in four European crowdfunding platforms

Crowdfunding is a business model where diverse stakeholders operate in a context considered an example of innovation in value co-creation. Based on literature about service ecosystems and value co-creation this study adopts the platformization of society as critical theoretical approach and analytical framework to study the relations between human and technological agents within four crowdfunding ecosystems in Europe. Conceiving Crowdfunding Service Providers (CSPs) as specialized organizations, regulated to operate multi-sided markets and to serve roles as ecosystems’ coordinators, we aim to identify the innovation strategies adopted by CSPs platforms from Italy, France, Spain and Portugal to support their core functions related to governance mechanisms, business models and infrastructural components. To understand the motives for innovation implementation and to compare the competitive adaptation from an ecosystemic perspective, we triangulate qualitative data from multiple sources to explain how and why these strategic choices affect the dynamics of value co-creation. The multiple cases-study systematizes and discusses similarities and differences, particularly as concerns the capacity of CFPs to orchestrate their governance and ICT components to innovate and take advantage of algorithms and AI implementation, collecting more data and money from user interactions. Conclusions highlight the non-neutrality of CSPs, which act as data analysts and translators, adopting more preventive, proactive or reactive strategies of usage and redistribution of the value, created, acquired and aggregated through data. Each CSP can be characterized by its infrastructure and data management approach, metaphorically being more eco-centred or ego-centred.

Scarecrows in Oz: The Use of Large Language Models in HRI

The proliferation of Large Language Models (LLMs) presents both a critical design challenge and a remarkable opportunity for the field of Human–Robot Interaction (HRI). While the direct deployment of LLMs on interactive robots may be unsuitable for reasons of ethics, safety, and control, LLMs might nevertheless provide a promising baseline technique for many elements of HRI. Specifically, in this article, we argue for the use of LLMs as Scarecrows : “brainless,” straw-man black-box modules integrated into robot architectures for the purpose of quickly enabling full-pipeline solutions, much like the use of “Wizard of Oz” (WoZ) and other human-in-the-loop approaches. We explicitly acknowledge that these Scarecrows, rather than providing a satisfying or scientifically complete solution, incorporate a form of the wisdom of the crowd and, in at least some cases, will ultimately need to be replaced or supplemented by a robust and theoretically motivated solution. We provide examples of how Scarecrows could be used in language-capable robot architectures as useful placeholders and suggest initial reporting guidelines for authors, mirroring existing guidelines for the use and reporting of WoZ techniques.

Financing Organic Farming through Crowdfunding: Is the Wisdom of Crowds More Supportive for Mixed Gender Teams?

Financing Organic Farming through Crowdfunding: Is the Wisdom of Crowds More Supportive for Mixed Gender Teams?

Do Crowds Validate False Data? Systematic Distortion and Affective Polarization

This research note examines how socio-cognitive influences can systematically distort crowdsourced ground truth in event-centric data through subgroups. The "wisdom of the crowd" is based on the assumption that consensus drives accuracy. While existing research addresses tendencies of the overall crowd, this research note shows identifiable subgroups within the crowd can systematically influence crowdsource validation. We conducted an immersive experiment to investigate whether crowd consensus can be systematically distorted by subgroup-based socio-cognitive influences, such as affective polarization. In the experiment, raters from a range of subgroups with varying levels of affective polarization were asked to view and validate crisis data from a violent public riot in the year 2020. Relying in part on double debiased machine learning techniques, we analyze heterogeneous treatment effects across subgroups. The results show that affective polarization and more extreme raters, via the constructs of loyalty and betrayal, distort consensus-based ground truth in different ways. This research note demonstrates how subgroup-based socio-cognitive influences can systematically distort the results of consensus-based crowdsourced validation. Additionally, it provides guidance for research and practice on how to account for identifiable subgroups in the crowd. These findings challenge key assumptions about the wisdom of crowds and the accuracy of crowdsourced ground truth in event-centric situations.

Introduction to the special issue on judgment and decision research on the wisdom of the crowds.

Introduction to the special issue on judgment and decision research on the wisdom of the crowds.

How people use information about the number and distribution of judgments when tapping into the wisdom of the crowds.

How people use information about the number and distribution of judgments when tapping into the wisdom of the crowds.

Wisdom of crowds as a verification tool in bank lending: Evidence from borrowers’ customer tweets

Wisdom of crowds as a verification tool in bank lending: Evidence from borrowers’ customer tweets

Harnessing the wisdom of the confident crowd in medical image decision-making.

Harnessing the wisdom of the confident crowd in medical image decision-making.

The Wisdom of Electronic Employee Crowds -Employee Reviews as a Data Source in Finance, Accounting, Economics and Management Research: Systematic Literature Review

The Wisdom of Electronic Employee Crowds -Employee Reviews as a Data Source in Finance, Accounting, Economics and Management Research: Systematic Literature Review

Leveraging Advice-taking and Kernel Density Estimation to Identify A Cluster of Experts and Improve Wisdom of Crowds

Leveraging Advice-taking and Kernel Density Estimation to Identify A Cluster of Experts and Improve Wisdom of Crowds

Supplemental Material for Automated Update Tools to Augment the Wisdom of Crowds in Geopolitical Forecasting

Supplemental Material for Automated Update Tools to Augment the Wisdom of Crowds in Geopolitical Forecasting