Filters








1,079 Hits in 4.9 sec

Evaluating the Robustness of Learning Analytics Results Against Fake Learners [chapter]

Giora Alexandron, José A. Ruipérez-Valiente, Sunbok Lee, David E. Pritchard
2018 Lecture Notes in Computer Science  
Because of their aberrant behavior, fake learners can bias the results of Learning Analytics (LA) models.  ...  We conclude that the LA study that we challenged was robust against fake learners.  ...  We build upon our previous research on both identifying fake learners, and pedagogic efficacy in MOOCs, to make a stride in the direction of evaluating the robustness of LA research against fake learners  ... 
doi:10.1007/978-3-319-98572-5_6 fatcat:glsd5ao4g5hmrgtrwvdb75pnja

Survey of review spam detection using machine learning techniques

Michael Crawford, Taghi M. Khoshgoftaar, Joseph D. Prusa, Aaron N. Richter, Hamzah Al Najada
2015 Journal of Big Data  
To date, we have not found any papers that study the effects of Big Data analytics for review spam detection.  ...  In this paper, we survey the prominent machine learning techniques that have been proposed to solve the problem of review spam detection and the performance of different approaches for classification and  ...  [1] and compared against supervised learning methods.  ... 
doi:10.1186/s40537-015-0029-9 fatcat:a3ic2fjbkvdarcsq3txozypn74

Lies Kill, Facts Save: Detecting COVID-19 Misinformation in Twitter

Mabrook S. Al-Rakhami, Atif M. Al-Amri
2020 IEEE Access  
For our analysis, we propose an ensemble-learning-based framework for verifying the credibility of a vast number of tweets.  ...  The results obtained with the proposed framework reveal high accuracy in detecting credible and non-credible tweets containing COVID-19 information.  ...  ACKNOWLEDGMENT The authors thank the Deanship of Scientific Research and RSSU at King Saud University for their technical support.  ... 
doi:10.1109/access.2020.3019600 pmid:34192115 pmcid:PMC8043503 fatcat:vg52c7qthvdmvhddsdd2e7koym

Exploiting Data Mining for Authenticity Assessment and Protection of High-Quality Italian Wines from Piedmont

Marco Arlorio, Jean Daniel Coisson, Giorgio Leonardi, Monica Locatelli, Luigi Portinale
2015 Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining - KDD '15  
This paper discusses the data mining approach followed in a project called TRAQUASwine, aimed at the definition of methods for data analytical assessment of the authenticity and protection, against fake  ...  mining on the resulting chemical profiles.  ...  showing a better robustness with respect to possible fake wines.  ... 
doi:10.1145/2783258.2788596 dblp:conf/kdd/ArlorioCLLP15 fatcat:p24uhy4et5hb3gm3h7fubewp6e

Using Virtual Exchange to Advance Media Literacy Competencies through Analysis of Contemporary Propaganda

2018 Journal of Media Literacy Education  
With the rise of so-called fake news as a global phenomenon, interest in propaganda analysis has advanced along with the recognition of the fundamentally social process of interpretation.  ...  and guide the civic actions of citizens.  ...  DEFINING PROPAGANDA IN THE CONTEXT OF FAKE NEWS The study of advertising and propaganda has long been a part of media literacy education and it is highly likely that the robust propaganda education programs  ... 
doi:10.23860/jmle-2018-10-2-9 fatcat:afoyvglrcvfqngin6uofcic5i4

Machine Learning Methods for Computer Security (Dagstuhl Perspectives Workshop 12371)

Anthony D. Joseph, Pavel Laskov, Fabio Roli, J. Doug Tygar, Blaine Nelson, Marc Herbstritt
2013 Dagstuhl Reports  
Unlike many other application domains of machine learning, security-related applications require careful consideration of their adversarial nature and novel learning methods with improved robustness against  ...  As a result of the twenty-two invited presentations, workgroup sessions and informal discussion, several priority areas of research were identified.  ...  This also facilitates the future evaluation of the algorithm because U can be used as an evaluation metric.  ... 
doi:10.4230/dagrep.2.9.109 dblp:journals/dagstuhl-reports/JosephLRTN12 fatcat:4x3ng2szxfg5jnkf5rtwsmttrm

A Method for Thematic and Structural Visualization of Academic Content

Alexander Amigud, Joan Arnedo-Moreno, Thanasis Daradoumis, Ana-Elena Guerrero-Roldan
2017 2017 IEEE 17th International Conference on Advanced Learning Technologies (ICALT)  
Research in the area of learner identity and authorship assurance is important because the award of course credits to unverified entities is detrimental to institutional credibility and public safety.  ...  This thesis builds upon the notion of learner identity being comprised of two distinct layers, physical and behavioral, where both criteria of identity and authorship need to be confirmed to maintain a  ...  At the core of this process is the question of what artifacts have learners produced as a result of the learning experience?  ... 
doi:10.1109/icalt.2017.24 dblp:conf/icalt/AmigudADG17 fatcat:voezr7hg6nfcxlubzzgsbnzpi4

Vulnerability-Aware Poisoning Mechanism for Online RL with Unknown Dynamics [article]

Yanchao Sun, Da Huo, Furong Huang
2021 arXiv   pre-print
Poisoning attacks on Reinforcement Learning (RL) systems could take advantage of RL algorithm's vulnerabilities and cause failure of the learning.  ...  However, prior works on poisoning RL usually either unrealistically assume the attacker knows the underlying Markov Decision Process (MDP), or directly apply the poisoning methods in supervised learning  ...  The (δ-)robustness radius of a policy π in an MDP M is defined as the maximal robustness radius of all states, i.e., ρ(π, M) = min s∈S ρ(π, s) Remarks. (1) A deterministic policy is robust against any  ... 
arXiv:2009.00774v3 fatcat:ki6t6mwmt5ebho5k3szpxuurfi

STEP-GAN: A Step-by-Step Training for Multi Generator GANs with application to Cyber Security in Power Systems [article]

Mohammad Adiban, Arash Safari, Giampiero Salvi
2020 arXiv   pre-print
In recent years, however, advances in the field of machine learning, have raised concerns about cyber attacks on these systems.  ...  As a consequence, our system is robust to unseen attacks. Moreover, the proposed model considerably reduces the well-known mode collapse problem of GAN-based models.  ...  As a result, our system is potentially more robust to unseen attacks.  ... 
arXiv:2009.05184v1 fatcat:exh5b336qffffdwa354hj3jvju

The L2 motivational self system: A meta-analysis

Ali H. Al-Hoorie
2018 Studies in Second Language Learning and Teaching  
The results showed that the three components of the L2 motivational self system (the ideal L2 self, the ought-to L2 self, and the L2 learning experience) were significant predictors of subjective intended  ...  The results also suggest that the strong correlation between the L2 learning experience and intended effort reported in the literature is, due to substantial wording overlap, partly an artifact of lack  ...  A meta-analysis can offer a baseline against which the effectiveness of reformation attempts can be evaluated.  ... 
doi:10.14746/ssllt.2018.8.4.2 fatcat:gvyqeec275fjfhlbbozenr2fpy

The eyes know it: FakeET – An Eye-tracking Database to Understand Deepfake Perception [article]

Parul Gupta, Komal Chugh, Abhinav Dhall, Ramanathan Subramanian
2020 arXiv   pre-print
Negativity (ERN) triggers in the EEG responses, and the ability of the raw EEG signal to distinguish between real and fake videos.  ...  Given that the principal purpose of deepfakes is to deceive human observers, FakeET is designed to understand and evaluate the ease with which viewers can detect synthetic video artifacts.  ...  User-centered Evaluation The user studies conducted for the field of Deepfakes have aimed to evaluate human performance in the task of forgery detection.  ... 
arXiv:2006.06961v2 fatcat:5ppqezyczjaojhanmn25il3lyy

A Survey on Resilient Machine Learning [article]

Atul Kumar, Sameep Mehta
2017 arXiv   pre-print
Maliciously created input samples can affect the learning process of a ML system by either slowing down the learning process, or affecting the performance of the learned mode, or causing the system make  ...  We present a survey of this emerging area in machine learning.  ...  attacks and make machine learning algorithms more robust against these attacks.  ... 
arXiv:1707.03184v1 fatcat:qjylw7bvkzbdlbrof5cfpy2jyq

An Obfuscated Attack Detection Approach for Collaborative Recommender Systems

Saakshi Kapoor, Vishal Gupta, Rohit Kumar
2018 Journal of Computing and Information Technology  
attacks in which fake profiles are inserted into the database in order to bias its output.  ...  In the recent times, we have loads and loads of information available over the Internet.  ...  Verbert et al. (2011) [35] presented datasets that can capture learner interactions with tools and resources and can be used for learning analytics research.  ... 
doi:10.20532/cit.2018.1003948 fatcat:ag7taakngzestemnlipfaaxx44

Occurence of A Cyber Security Eco-System: A Nature Oriented Project and Evaluation of An Indirect Social Experiment [article]

Utku Kose
2019 arXiv   pre-print
In this sense, it is thought that the findings and comments presented in the study will give important ideas to everyone involved in cyber security education, life-long learning processes, and the technology  ...  Because of todays technological developments and the influence of digital systems into every aspect of our lives, importance of cyber security improves more and more day-by-day.  ...  Although some teams were more robust against tricking, tricking levels for all teams show existence of an eco-system.  ... 
arXiv:1910.07083v1 fatcat:ixeroptvozeuvjtau64yjkulmq

IRRODL Volume 15, Number 4

Various Authors
2014 International Review of Research in Open and Distance Learning  
The results show how practitioners of six different OEPs learn, while acting and collaborating through a combination of offline and online networks.  ...  ./14 iii The final two papers involve conceptual frameworks using learning analytics.  ...  Acknowledgements This study is conducted within the frame of the POERUP project, funded by the lifelong learning program of the European Commission (POERUP, 2013).  ... 
doi:10.19173/irrodl.v15i4.1989 fatcat:n6eco2dbjjbdpk5buikozdjrf4
« Previous Showing results 1 — 15 out of 1,079 results