26,537 Hits in 4.2 sec

Modeling peer assessment as a personalized predictor of teacher's grades: The case of OpenAnswer

Maria De Marsico, Andrea Sterbini, Marco Temperini
2016 2016 15th International Conference on Information Technology Based Higher Education and Training (ITHET)  
In our OpenAnswer system we have modeled peer-assessment as a Bayesian network connecting a set of sub-networks (each representing a participating student) to the corresponding answers of her graded peers  ...  to the whole dataset, which in turn improves against the predictions of the raw peer-assessment.  ...  INTRODUCTION AND RELATED WORK Peer assessment is seldom used and hard to correct.  ... 
doi:10.1109/ithet.2016.7760743 dblp:conf/ithet/MarsicoST16 fatcat:ghfh2j5w5vfofpqdynyvlgxuoi

Probabilistic Models for Competence Assessment in Education

Alejandra López de Aberasturi Gómez, Jordi Sabater-Mir, Carles Sierra
2022 Applied Sciences  
We start this paper by replicating two preexisting probabilistic models of peer assessment (PG1-bias and PAAS).  ...  Probabilistic models of competence assessment join the benefits of automation with human judgment.  ...  Model Let ε represent a person who needs to assess a set I of objects and let P be a set of peers able to assess objects in I.  ... 
doi:10.3390/app12052368 fatcat:ssbmp5xyofg3nkhnfijbmdhzre

Leveraging Cognitive Diagnosis to Improve Peer Assessment in MOOCs

Jia Xu, Qiuyun Li, Jing Liu, Pin Lv, Ge Yu
2021 IEEE Access  
We propose two new probabilistic graph models to improve the accuracy of cardinal peer assessments based on the well-accepted cognitive diagnosis technique.  ...  To improve accuracy, several probabilistic graph models have been proposed to model the reliability and bias of each grader.  ...  PROBABILISTIC GRAPH MODELS FOR PEER ASSESSMENT In this work, two probabilistic graph models, namely CD-PG 1 and CD-PG 2 , are proposed for cardinal peer assessment based on the cognitive diagnosis model  ... 
doi:10.1109/access.2021.3069055 fatcat:zmb32v4offe5ha23zex3mmjf2y

OpenAnswer, a framework to support teacher's management of open answers through peer assessment

Andrea Sterbini, Marco Temperini
2013 2013 IEEE Frontiers in Education Conference (FIE)  
Open-ended questions are an important means to support analysis and assessment of students; they can be of extraordinary effectiveness for the assessment of higher cognitive levels of the Bloom's Taxonomy  ...  In this paper we describe an approach to open answers evaluation based on the use of peer-assessment: in a social-collaborative e-learning setting implemented by the OpenAnswer web system, the students  ...  Learning the parameters of the model The Bayesian network modeling the peer-assessment depends on: • the CPTs describing the probabilistic dependencies of C and J respect to K. • the probability distribution  ... 
doi:10.1109/fie.2013.6684808 dblp:conf/fie/SterbiniT13 fatcat:wjzhsnlbmzehdb3j3rvm5wrkci

P2P reputation management: Probabilistic estimation vs. social networks

Zoran Despotovic, Karl Aberer
2006 Computer Networks  
probabilistic models that rely on the well known probabilistic estimation techniques but use only a limited fraction of the available feedback.  ...  We test their performance against various classes of collusive peer behavior and analyze their properties with respect to the implementation costs they incur and trust semantics they offer to the decision  ...  project Evergrow, No. 001935, and by the Swiss NSF as part of the project Computational Reputation Mechanisms for Enabling Peer-To-Peer Commerce in Decentralized Networks, No. 205121-105287/1.  ... 
doi:10.1016/j.comnet.2005.07.003 fatcat:f2isc64bara2ffnxhhxrxeieom

Towards a quantitative evaluation of the relationship between the domain knowledge and the ability to assess peer work

Maria De Marsico, Andrea Sterbini, Marco Temperini
2015 2015 International Conference on Information Technology Based Higher Education and Training (ITHET)  
In this work we present the preliminary results provided by the statistical modeling of the cognitive relationship between the knowledge about a topic a the ability to assess peer achievements on the same  ...  Our starting point is Bloom's taxonomy of educational objectives in the cognitive domain, and our outcomes confirm the hypothesized ranking.  ...  To understand how the Judgment ability of a student is placed respect to her Knowledge and to Correctness of her answers, we have modeled the probabilistic dependencies of J, C and G, as Gaussian distributions  ... 
doi:10.1109/ithet.2015.7218036 dblp:conf/ithet/MarsicoST15 fatcat:pqp5um6wojadxkhfwi5z2ezzf4

Probabilistic divergence of a TBM methodology from the ideal protocol [article]

Ashish Runthala
2020 bioRxiv   pre-print
The methods only assess the predicted structure against its native state/template, and do not estimate the accuracy for each modelling step.  ...  For a higher modelling accuracy and quicker implementation, template based algorithms have been extensively deployed and redefined.  ...  Acknowledgements The author acknowledges the University and department for providing the required resources/support. In compliance with the ethical standards  ... 
doi:10.1101/2020.07.05.160937 fatcat:es2ws6eehja7vmd22njj7lhv7y

Tuned Models of Peer Assessment in MOOCs [article]

Chris Piech, Jonathan Huang, Zhenghao Chen, Chuong Do, Andrew Ng, Daphne Koller
2013 arXiv   pre-print
In this paper, we develop algorithms for estimating and correcting for grader biases and reliabilities, showing significant improvement in peer grading accuracy on real data with 63,199 peer grades from  ...  We also show that our model can lead to more intelligent assignment of graders to gradees.  ...  Acknowledgments We thank Chinmay Kulkarni and Scott Klemmer for providing assistance with the HCI datasets and Leonidas Guibas and John Mitchell for discussions and support.  ... 
arXiv:1307.2579v1 fatcat:ruih27ky6rafdm2sinqi7gxbga

Page 1037 of American Society of Civil Engineers. Collected Journals Vol. 128, Issue 10 [page]

2002 American Society of Civil Engineers. Collected Journals  
With the aim of facilitating their use in practice, the probabilistic models are constructed by developing correction terms to existing determin- istic models in common use.  ...  The probabilistic capacity models are used in a formulation to assess the fragility of structural components, with due consider- ation given to the different natures of aleatory and epistemic un- certainties  ... 


Karl Aberer, Philippe Cudré-Mauroux, Anwitaman Datta, Zoran Despotovic, Manfred Hauswirth, Magdalena Punceva, Roman Schmidt
2003 SIGMOD record  
In [1] we present our decentralized trust management model that analyzes past interactions among peers to make a probabilistic assessment of whether any given peer cheated in its past interactions.  ...  Trust assessments themselves are made based on an analysis of peer interactions modeled as stochastic processes.  ... 
doi:10.1145/945721.945729 fatcat:jqedfgk6zrc4zmjreqikxw7lwe

Decentralized Probabilistic Text Clustering

Odysseas Papapetrou, Wolf Siberski, Norbert Fuhr
2012 IEEE Transactions on Knowledge and Data Engineering  
The algorithm offers probabilistic guarantees for the correctness of each document assignment to a cluster.  ...  Extensive experimental evaluation with up to 1 million peers and 1 million documents demonstrates the scalability and effectiveness of the algorithm.  ...  , (d) to assess the effects of load balancing.  ... 
doi:10.1109/tkde.2011.120 fatcat:joxcz4hk65h3rbir5ceqqwaujq

A Service-Oriented Architecture for Student Modeling in Peer Assessment Environments [chapter]

Gabriel Badea, Elvira Popescu, Andrea Sterbini, Marco Temperini
2018 Lecture Notes in Computer Science  
of the learner, as mentioned in the previous section: K, the level of knowledge; J, the ability to assess peers' work; and C, the correctness of the answer provided by the student.  ...  Student Modeling Service Concept and Architecture First we describe the model of Bayesian Network (BN) data representation, for a peer assessment session, as proposed in [9] .  ... 
doi:10.1007/978-3-030-03580-8_4 fatcat:up6qof5hbne7xoeulpc4lhhrj4

Restructuring of amygdala subregion apportion across adolescence [article]

Claire E Campbell, Adam F Mezher, Sandrah P Eckel, Julian Michael Tyszka, Wolfgang M Pauli, Bonnie J Nagel, Megan M Herting
2019 bioRxiv   pre-print
Generalized Additive Mixed Models (GAMM) were used to assess how demographic variables (e.g. age, sex) and physical development (e.g. BMI and pubertal status) were associated with amygdala RVFs.  ...  While pubertal development was found to be associated with RVFs in the BLVPL, CEN, and ATA in males, best-fit model comparisons revealed that age was the best predictor of relative volumes of these subregions  ...  of freedom (Ref.df), F-score, p-value, and Adjusted R 2 for each model is shown; p-value < 0.0056 bolded (Bonferroni corrected) .  ... 
doi:10.1101/690875 fatcat:zy2ca6wulfa7dlzc7ik47of3ym

A Probabilistic Approach to Predict Peers' Performance in P2P Networks [chapter]

Zoran Despotovic, Karl Aberer
2004 Lecture Notes in Computer Science  
However, most of the proposed solutions exhibit the following two problems: huge implementation overhead and unclear trust related model semantics.  ...  Thus, no complex exploration of the feedback is necessary. Instead, simple, intuitive and efficient probabilistic estimation methods suffice.  ...  Discussion and Future Work We propose in this paper a simple probabilistic method to assess peers' performance in a P2P network (or more specifically their trustworthiness).  ... 
doi:10.1007/978-3-540-30104-2_6 fatcat:mmo54xfh7ze2fmp3laz3sjp5ta

Integrating multimodal connectivity improves prediction of individual cognitive abilities [article]

Elvisha Dhamala, Keith Jamison, Abhishek Jaywant, Sarah Dennis, Amy Kuceyeski
2020 bioRxiv   pre-print
Specifically, we evaluate whether integrating functional and structural connectivity improves prediction of individual crystallised and fluid abilities in 415 unrelated healthy young adults from the Human  ...  First, we demonstrate that integrating functional and structural information - at both a model input or output level - significantly outperforms functional or structural connectivity alone to predict individual  ...  Automated manifold surgery: constructing geometrically accurate and topologically correct models of the human cerebral cortex. IEEE Trans Med Imaging, 20, 70-80.  ... 
doi:10.1101/2020.06.25.172387 fatcat:wd44vxxfkrb4rcg76gzalmy4kq
« Previous Showing results 1 — 15 out of 26,537 results