Abstract
The study of data quality in crowdsourcing campaigns is currently a prominent research topic, given the diverse range of participants involved. A potential solution to enhancing data quality processes in crowdsourcing is cognitive personalization, which involves appropriately adapting or assigning tasks based on a crowd worker's cognitive profile. There are two common methods for assessing a crowd worker's cognitive profile: administering online cognitive tests, and inferring behavior from task fingerprinting based on user interaction log events. This article presents the findings of a study that investigated the complementarity of both approaches in a microtask scenario, focusing on personalizing task design. The study involved 134 unique crowd workers recruited from a crowdsourcing marketplace. The main objective was to examine how the administration of cognitive ability tests can be used to allocate crowd workers to microtasks with varying levels of difficulty, including the development of a deep learning model. Another goal was to investigate if task fingerprinting can be used to allocate crowd workers to different microtasks in a personalized manner. The results indicated that both objectives were accomplished, validating the usage of cognitive tests and task fingerprinting as effective mechanisms for microtask personalization, including the development of a deep learning model with 95% accuracy in predicting the accuracy of the microtasks. While we achieved an accuracy of 95%, it is important to note that the small dataset size may have limited the model's performance.

Abstract

Abstract
Online microtask labor has increased its role in the last few years and has provided the possibility of people who were usually excluded from the labor market to work anytime and without geographical barriers. While this brings new opportunities for people to work remotely, it can also pose challenges regarding the difficulty of assigning tasks to workers according to their abilities. To this end, cognitive personalization can be used to assess the cognitive profile of each worker and subsequently match those workers to the most appropriate type of work that is available on the digital labor market. In this regard, we believe that the time is ripe for a review of the current state of research on cognitive personalization for digital labor. The present study was conducted by following the recommended guidelines for the software engineering domain through a systematic literature review that led to the analysis of 20 primary studies published from 2010 to 2020. The results report the application of several cognition theories derived from the field of psychology, which in turn revealed an apparent presence of studies indicating accurate levels of cognitive personalization in digital labor in addition to a potential increase in the worker's performance, most frequently investigated in crowdsourcing settings. In view of this, the present essay seeks to contribute to the identification of several gaps and opportunities for future research in order to enhance the personalization of online labor, which has the potential of increasing both worker motivation and the quality of digital work.

Abstract
Extreme weather events, such as windstorms, hurricanes, and heat waves, exert a significant impact on global natural catastrophes and pose substantial challenges for weather forecasting systems. To enhance the accuracy and preparedness for extreme weather events, this study explores the potential of using expert crowdsourcing in storm forecasting research through the application of stigmergic collaboration. We present the development and implementation of an expert Crowdsourcing for Semantic Annotation of Atmospheric Phenomena (eCSAAP) system, designed to leverage the collective knowledge and experience of meteorological experts. Through a participatory co-creation process, we iteratively developed a web-based annotation tool capable of capturing multi-faceted insights from weather data and generating visualizations for expert crowdsourcing campaigns. In this context, this article investigates the intrinsic coordination among experts engaged in crowdsourcing tasks focused on the semantic annotation of extreme weather events. The study brings insights about the behavior of expert crowds by considering the cognitive biases and highlighting the impact of existing annotations on the quality of data gathered from the crowd and the collective knowledge generated. The insights regarding the crowdsourcing dynamics, particularly stigmergy, offer a promising starting point for utilizing stigmergic collaboration as an effective coordination mechanism for weather experts in crowdsourcing platforms but also in other domains requiring expertise-driven collective intelligence.

Abstract
Visualizing and examining the intellectual landscape and evolution of scientific communities to support collaboration is crucial for multiple research purposes. In some cases, measuring similarities and matching patterns between research publication document sets can help to identify people with similar interests for building research collaboration networks and university-industry linkages. The premise of this work is assessing feasibility for resolving ambiguous cases in similarity detection to determine authorship with natural language processing (NLP) techniques so that crowdsourcing is applied only in instances that require human judgment. Using an NLP-crowdsourcing convergence strategy, we can reduce the costs of microtask crowdsourcing while saving time and maintaining disambiguation accuracy over large datasets. This article contributes a next-gen crowd-artificial intelligence framework that used an ensemble of term frequency-inverse document frequency and bidirectional encoder representation from transformers to obtain similarity rankings for pairs of scientific documents. A sequence of content-based similarity tasks was created using a crowd-powered interface for solving disambiguation problems. Our experimental results suggest that an adaptive NLP-crowdsourcing hybrid framework has advantages for inter-researcher similarity detection tasks where fully automatic algorithms provide unsatisfactory results, with the goal of helping researchers discover potential collaborators using data-driven approaches.