this research paper seeks to present a comprehensive examination of algorithmic trading algorithms, encompassing a range of techniques that extend from supervised learning to sentiment-aware reinforcement-based tradin...
详细信息
Measuring algorithmic bias in machine learning has historically focused on statistical inequalities pertaining to specific groups. However, the most common metrics (i.e., those focused on individualor group-conditione...
详细信息
ISBN:
(纸本)9798400716188
Measuring algorithmic bias in machine learning has historically focused on statistical inequalities pertaining to specific groups. However, the most common metrics (i.e., those focused on individualor group-conditioned error rates) are not currently well-suited to educational settings because they assume that each individual observation is independent from the others. this is not statistically appropriate when studying certain common educational outcomes, because such metrics cannot account for the relationship between students in classrooms or multiple observations per student across an academic year. In this paper, we present novel adaptations of algorithmic bias measurements for regression for both independent and nested data structures. Using hierarchical linear models, we rigorously measure algorithmic bias in a machine learning model of the relationship between student engagement in an intelligent tutoring system and year-end standardized test scores. We conclude that classroom-level influences had a small but significant effect on models. Examining significance with hierarchical linear models helps determine which inequalities in educational settings might be explained by small sample sizes rather than systematic differences.
the goal of this tutorial is to provide the WSDM community with recent advances on the assessment and mitigation of data and algorithmic bias in recommender systems. We first introduce conceptual foundations, by prese...
详细信息
ISBN:
(纸本)9781450382977
the goal of this tutorial is to provide the WSDM community with recent advances on the assessment and mitigation of data and algorithmic bias in recommender systems. We first introduce conceptual foundations, by presenting the state of the art and describing real-world examples of how bias can impact on recommendation algorithms from several perspectives (e.g., ethical and system objectives). the tutorial continues with a systematic showcase of algorithmic countermeasures to uncover, assess, and reduce bias along the recommendation design process. A practical part then provides attendees with implementations of pre-, in-, and post-processing bias mitigation algorithms, leveraging open-source tools and public datasets;in this part, tutorial participants are engaged in the design of bias countermeasures and in articulating impacts on stakeholders. We conclude the tutorial by analyzing emerging open issues and future directions in this rapidly evolving research area (Website: https://***/wsdm2021).
Guided Personal learning Environment concept (gPLEc) is a novel PLE-building methodology which seeks to fulfill emergent learning needs of a learner through incorporating teachers' guidance element in learners'...
详细信息
ISBN:
(纸本)9781479940387
Guided Personal learning Environment concept (gPLEc) is a novel PLE-building methodology which seeks to fulfill emergent learning needs of a learner through incorporating teachers' guidance element in learners' PLE-building activity. Using Social Semantic Web (SSW) and Recommender System (RS) technologies the gPLEc integrates teachers' PLE-based learning competencies and learners' social web and interaction history data to generate personalized recommendations for each learner. the results, achieved so far, confirm importance of teachers' guidance element for successful implementation of the PLE vision. the expected outcome of this exploratory research is to gain knowledge to construct personalized elearning systems.
A pattern is a finite string of constant and variable symbols. the erasing language generated by a pattern p is the set of all strings that can be obtained by substituting (possibly empty) strings of constant symbols ...
详细信息
ISBN:
(纸本)3540202919
A pattern is a finite string of constant and variable symbols. the erasing language generated by a pattern p is the set of all strings that can be obtained by substituting (possibly empty) strings of constant symbols for the variables in p. the present paper deals withthe problem of learningthe erasing pattern languages and natural subclasses thereof within Angluin's model of learning with queries. the paper extends former studies along this line of research. It provides new results concerning the principal learning capabilities of query learners as well as the power and limitations of polynomial-time query learners. In addition, the paper focusses on a quite natural extension of Angluin's original model. In this extended model, the query learner is allowed to query languages which are themselves not object of learning. Query learners of the latter type are often more powerful and more efficient than standard query learners. Moreover, when studying this new model in a more general context, interesting relations to Cold's model of language learning from only positive data have been elaborated.
A persuasive teachable agent (PTA) is a pedagogical agent which uses persuasion to encourage positive learning attitudes and behaviors in student tutors. this paper presents a life-like animated autonomous PTA in the ...
详细信息
ISBN:
(纸本)9781479940387
A persuasive teachable agent (PTA) is a pedagogical agent which uses persuasion to encourage positive learning attitudes and behaviors in student tutors. this paper presents a life-like animated autonomous PTA in the 3D Virtual learning Environments (VLE) which makes use of the Goal Net agent model and persuasion theory. the PTA aims to autonomously exert social influence on the student tutors, encouraging them to teach the PTA. A case study is also presented to illustrate our approach.
Game-based learning (GBL) is growing rapidly as a gaming industry as well as a field of academic research. Developing GBL is not an easy task. It requires a tight collaboration with domain experts and this need consid...
详细信息
ISBN:
(纸本)9781538608524
Game-based learning (GBL) is growing rapidly as a gaming industry as well as a field of academic research. Developing GBL is not an easy task. It requires a tight collaboration with domain experts and this need considering a complex mix of disciplines and technologies. learningtheory, learning contents, and game design are three multidisciplinary challenges involved in proper GBL development. this paper attempts to address these challenges by demonstrating how GBL can be conceptualized from different theoretical perspectives on learning and discuss a number of fundamental elements of game design that are essential for effective learning. then, we propose a novel methodology of design and development of GBL model that facilitates the integration of flow experience with such game elements to support learning in games. Comparisons with existing frameworks are included. Evaluation and practical performance results supported by some case study called "A day without computer-mediated technology" are also demonstrated to verify the usability of the proposed model.
Mobile-based assessment offers a promising (complementary to paper-based and computer-based) assessment delivery mode. However, its successful implementation depends on users' acceptance. the present study is the ...
详细信息
ISBN:
(纸本)9781479940387
Mobile-based assessment offers a promising (complementary to paper-based and computer-based) assessment delivery mode. However, its successful implementation depends on users' acceptance. the present study is the first towards the investigation of the factors that influence the acceptance of mobile-based assessment. It combines two theoretical frameworks: Technology Acceptance Model and Self-Determination theory of Motivation. Partial Least Squares were used to test the proposed structural model. Perceived Autonomy, Perceived Relatedness and Perceived Competency, along with Perceived Usefulness and Perceived Ease of Use, influence Attitudes Towards Use and Behavior Intention to use Mobile-Based Assessment. the study confirms Technology Acceptance Model and showed that Self Determination theory can be useful in predicting students' acceptance in the context of mobile-based assessment.
Solomonoff unified Occam's razor and Epicurus' principle of multiple explanations to one elegant, formal, universal theory of inductive inference, which initiated the field of algorithmic information theory. H...
详细信息
ISBN:
(纸本)3540202919
Solomonoff unified Occam's razor and Epicurus' principle of multiple explanations to one elegant, formal, universal theory of inductive inference, which initiated the field of algorithmic information theory. His central result is that the posterior of his universal semimeasure M converges rapidly to the true sequence generating posterior mu, if the latter is computable. Hence, M is eligible as a universal predictor in case of unknown mu. We investigate the existence and convergence of computable universal (semi)measures for a hierarchy of computability classes: finitely computable, estimable, enumerable, and approximable. For instance, M is known to be enumerable, but not finitely computable, and to dominate all enumerable semimeasures. We define seven classes of (semi)measures based on these four computability concepts. Each class may or may not contain a (semi)measure which dominates all elements of another class. the analysis of these 49 cases can be reduced to four basic cases, two of them being new. We also investigate more closely the types of convergence, possibly implied by universality: in difference and in ratio, with probability 1, in mean sum, and for Martin-Lof random sequences. We introduce a generalized concept of randomness for individual sequences and use it to exhibit difficulties regarding these issues.
the difficult path of e-learning in vocational schools, mainly professor - student oriented, pushed a few researchers from the music and visual fields to build a new opinion through the student last trends: if the voc...
详细信息
ISBN:
(纸本)9781457717475
the difficult path of e-learning in vocational schools, mainly professor - student oriented, pushed a few researchers from the music and visual fields to build a new opinion through the student last trends: if the vocational study cannot be entirely based on e-learning technologies, there could be the mobile learning environments and the real world experiences transmitted to students from all over the world, interested in graduating different kind of courses from different higher education colleges, unified by a new legislation, at least in the European Union. the technical demonstrations made by great masters in their own studios, withthe help of a few teachers and students, give the possibility to follow step by step different kind of performing arts from music to visual arts, and to present the results through Internet servers to other remote european schools. the need to cooperate between european higher education schools through common projects fulfill the need of communication between students, teachers and peoples of different countries.
暂无评论