Programming online judges (POJs) are an emerging application scenario in e-learning recommendation areas. Specifically, they are e-learning tools usually used in programming practices for the automatic evaluation of source code developed by students when they are solving programming problems. Usually, they contain a large collection of such problems, to be solved by students at their own personalized pace. The more problems in the POJ the harder the selection of the right problem to solve according to previous users performance, causing information overload and a widespread discouragement. This paper presents a recommendation framework to mitigate this issue by suggesting problems to solve in programming online judges, through the use of fuzzy tools which manage the uncertainty related to this scenario. The evaluation of the proposal uses real data obtained from a programming online judge, and shows that the new approach improves previous recommendation strategies which do not consider uncertainty management in the programming online judge scenarios. Specifically, the best results were obtained for short recommendation lists.
The paper proposes a recommender system approach to cover online judge's domains. Online judges are e-learning tools that support the automatic evaluation of programming tasks done by individual users, and for this reason they are usually used for training students in programming contest and for supporting basic programming teachings. The proposal pretends to suggest problems assuming that a user must try to solve those problems already successfully solved by similar users. With this goal, the authors adopt the traditional collaborative filtering method with a new similarity measure adapted to the current domain, and the authors propose several transformations in the user-problem matrix to incorporate specific online judge's information. The authors evaluate the effect of the matrix configurations using Precision and Recall metrics, getting better results comparing with the authors method without transformations and with a representative state-of-art approach. Finally, the authors outline possible extensions to the current work.
The treatment of large data streams in the presence of concept drifts is one of the main challenges in the field of data mining, particularly when the algorithms have to deal with concepts that disappear and then reappear. This paper presents a new algorithm, called Fast Adapting Ensemble (FAE), which adapts very quickly to both abrupt and gradual concept drifts, and has been specifically designed to deal with recurring concepts. FAE processes the learning examples in blocks of the same size, but it does not have to wait for the batch to be complete in order to adapt its base classification mechanism. FAE incorporates a drift detector to improve the handling of abrupt concept drifts and stores a set of inactive classifiers that represent old concepts, which are activated very quickly when these concepts reappear. We compare our new algorithm with various well-known learning algorithms, taking into account, common benchmark datasets. The experiments show promising results from the proposed algorithm (regarding accuracy and runtime), handling different types of concept drifts.
Recommender systems are popular applications that help users to identify items that they could be interested in. A recent research area on recommender systems focuses on detecting several kinds of inconsistencies associated with the user preferences. However, the majority of previous works in this direction just process anomalies that are intentionally introduced by users. In contrast, this paper is centered on finding the way to remove non-malicious anomalies, specifically in collaborative filtering systems. A review of the state-of-the-art in this field shows that no previous work has been carried out for recommendation systems and general data mining scenarios, to exactly perform this preprocessing task. More specifically, in this paper we propose a method that is based on the extraction of knowledge from the dataset in the form of rating regularities (similar to frequent patterns), and their use in order to remove anomalous preferences provided by users. Experiments show that the application of the procedure as a preprocessing step improves the performance of a data-mining task associated with the recommendation and also effectively detects the anomalous preferences.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.