Résultats de recherche pour « Data-based »

Much of the literature on value creation in social media-based infrastructures has largely neglected the pivotal role of data and their processes. This paper tries to move beyond this limitation and discusses data-based value creation in data-intensive infrastructures, such as social media, by focusing on processes of data generation, use and reuse, and on infrastructure development activities. Building on current debates in value theory, the paper develops a multidimensional value framework to interrogate the data collected in an embedded ethnographical case study of the development of PatientsLikeMe, a social media network for patients. It asks when, and where, value is created from the data, and what kinds of value are created from them, as they move through the data infrastructure; and how infrastructure evolution relates to, and shapes, existing data-based value creation practices. The findings show that infrastructure development can have unpredictable consequences for data-based value creation, shaping shared practices in complex ways and through a web of interdependent situations. The paper argues for an understanding of infrastructural innovation that accounts for the situational interdependencies of data use and reuse. Uniquely positioned, the paper demonstrates the importance of research that looks critically into processes of data use in infrastructures to keep abreast of the social consequences of developments in big data and data analytics aimed at exploiting all kinds of digital traces for multiple purposes.

Over the past decades, the topic of data quality became extremely important in various application fields. Originally developed for data warehouses, it received a strong push with the big data concept and artificial intelligence systems. In the presented chapter, we are looking at traditional data quality dimensions, which mainly have a more technical nature. However, we concentrate mostly on the idea of defining a single data quality determinant, which does not substitute the dimensions but allows us to look at the data quality from the point of view of users and particular applications. We consider this approach, which is known as a fit-to-use indicator, in two domains. The first one is the test data for complicated multi-component software systems on the example of a stock exchange. The second domain is scientific research on the example of validation of handwriting psychology. We demonstrate how the fit-to-use determinant of data quality can be defined and formalized and what benefit to the improvement of data quality it can give.

Abstract Effective enforcement of laws and regulations hinges heavily on robust inspection policies. While data-driven approaches to testing the effectiveness of these policies are gaining popularity, they suffer significant drawbacks, particularly a lack of explainability and generalizability. This paper proposes an approach to crafting inspection policies that combines data-driven insights with behavioral theories to create an agent-based simulation model that we call a theory-infused phenomenological agent-based model (TIP-ABM). Moreover, this approach outlines a systematic process for combining theories and data to construct a phenomenological ABM, beginning with defining macro-level empirical phenomena. Illustrated through a case study of the Dutch inland shipping sector, the proposed methodology enhances explainability by illuminating inspectors’ tacit knowledge while iterating between statistical data and underlying theories. The broader generalizability of the proposed approach beyond the inland shipping context requires further research.

Introduction: classroom interaction is very important for learning, especially in language classes where communication, feedback, and engagement are key to skill development. However traditional methods of watching and evaluating students in the classroom are typically subjective, time-consuming, and not easy to scale, which makes it challenging to make decisions about education based on data. Methods: this research suggests a data modeling approach based on deep learning (DMA-DL) to examine how people interact in English classrooms to help make decisions about education that are based on data and evidence. The suggested structure combines together several types of classroom data, such as audio recordings, video feeds, and written transcripts of conversations between teachers and students. Advanced deep learning architectures are used to automatically find semantic, temporal, and behavioral aspects that show how people interact, like turn-taking, questioning methods, response delay, and learner participation. Recurrent and attention-based models are employed to represent temporal dependencies, whereas convolutional neural networks facilitate comprehensive evaluation of auditory and visual signals.Results: the approach additionally utilizes representation learning to produce interaction indicators that are easy to comprehend and compatible with educational theories. The collected interaction elements are combined into a structured data model that allows it evaluates how well the teaching methods and student engagement are working. Experimental study performed on authentic classroom datasets illustrates that the suggested methodology attains significant accuracy in recognizing interaction patterns and proficiently differentiates between various teaching styles and levels of engagement. DMA-DL attains an overall interaction classification accuracy of 94.6%, outperforming DBDM (88.3%), SLR (86.9%), and EBNE (90.5%). In addition, the model records precision of 93.8%, recall of 94.1%, and an F1-score of 94.0%, indicating consistent predictive reliability across multiple interaction categories.Conclusions: the analytics provide teachers and administrators useful information that helps them make decisions about things like improving the curriculum, designing lessons, and professional development.