Competitive programming presents challenges for students seeking to enhance programming and algorithmic skills. This research introduces a system that efficiently matches problem statements to editorials that describe the solution, helping students find relevant learning resources. The main component of this system is our learning-to-rank model, which achieves a P@1 score of 0.93, indicating its proficiency in identifying the most relevant editorial for a specific problem statement. While our model is smaller in scale compared to general models like GPT-4, it distinguishes itself with comparable results and notable computational efficiency. Additionally, we have developed a new dataset of 1550 competitive programming problem statements and their editorials. Integrated into a competitive programming platform, it has the potential to evolve into an adaptive learning system, customizing paths based on individual user performance. Our code and data are public at https://github.com/DinuGeorge0019/MatchingProblemStatementsToEditorialsInCP.

In competitive programming, understanding a problem often requires more than just the official solution. Users typically turn to comments in the contest’s thread for additional insights. These comments often contain irrelevant information, necessitating the manual identification of relevant ones. This paper introduces CommentThreadFilter, a system designed to classify comments as either Relevant or Irrelevant for the main thread post. Leveraging base models like BERT, RoBERTa, and SciBERT, we evaluate the system’s performance on the newly created CFComments dataset. The dataset is the first of its kind, comprising 19 labelled comment threads in the competitive programming domain, manually annotated by two experts, alongside 1131 unlabeled comment threads. The proposed models, combined with a weak augmentation on the text, achieve an F1-score of 86%, outperforming the 77% F1-score obtained using gpt-3.5-turbo. By effectively filtering comments as Relevant or Irrelevant, our system enhances the user’s ability to gain valuable insights and better comprehend the underlying problem.

In the digital era, managing vast quantities of uncategorised text-based documents poses a significant challenge for institutions, as experienced by the Universidad Politécnica de Valencia (UPV) with their internal educational video system. Due to the lack of proper categorisation, the issue is represented by the difficulty students face in finding relevant content and the teachers keeping it updated. The paper aims to propose various Machine Learning and Deep Learning techniques aimed at assigning meaningful topics to these transcriptions, similar to how Wikipedia uses succinct, context-rich labels for its articles. This approach streamlines content access, enhances internal tracking and adds significant value to the institutions by improving data management and user experience.

Investigating learning performance predictors is an important part of the educational process. Active participation or engagement is one such predictor, which has been widely analyzed in traditional learning settings, but less in the emerging social-media based learning environments. This paper explores the relationship between students' active participation on three social media tools (wiki, blog, microblogging tool) and their academic performance, in the context of a project-based learning scenario. Two cohorts, with a total of 119 students, are included in the study. Multiple linear regression is used to build easily interpretable models, which explain the final grade in terms of social media activity. Results indicate that engagement with social media tools is a good predictor of the student performance. More specifically, the models show that several features have an influence on the grade, such as: the frequency of blog posts, the average length of the tweets, the number of wiki page revisions, the average number of revisions for each distinct wiki page, the number of blog comments, the number of wiki file uploads.

Abstract—This paper introduces an optimized version of the standard K-Means algorithm. The optimization refers to the running time and it comes from the observation that after a certain number of iterations, only a small part of the data elements change their cluster, so there is no need to re-distribute all data elements. Therefore the implementation proposed in this paper puts an edge between those data elements which won’t change their cluster during the next iteration and those who might change it, reducing significantly the workload in case of very big data sets. The prototype implementation showed up to 70 % reduction of the running time. I.

In e-Learning domain there has been observed an important effort towards designing and integrating support system software. These software systems may be fully integrated or run as services along e-Learning platforms and have as main goal increasing the effectiveness of the e-Learning processes. This paper proposes a novel structure of a support system for e-Learning infrastructure that is based on data representing learner's activities and processes. Data relevance is based on well discipline structuring based on concept maps. Markov chain modeling and classification is used as main intelligent procedure for data analysis.

This paper presents a personalized delivery system aimed at directing the learner to the next resources that need to be accessed in order to obtain best proficiency. The analysis is performed at chapter level. A concept map is has been created for a chapter and than concepts were classified using Naive Bayes classifier. The system recommends concepts that need further study which mean either resource access and study or more self-testing.

Improving learner's proficiency is a continuous issue in e-Learning systems. This paper presents a solution for advising the learner regarding the resources he should access and study in order to obtain a required proficiency level. The solution uses a Naive Bayes as classification algorithm with input data represented by learner's performed activities. The performed activities are logged and used as training and testing data. The obtained classifier is used for new students and provides them with necessary information regarding what resources need to access and study.

Evaluation of accumulated knowledge level for a student is a critical aspect in any learning program and therefore in an e-Learning system. Proper estimation of accumulated knowledge may bring valuable information regarding the student and the effort that he needs to have in order to achieve certain goals. On the other hand, proper estimation can bring very useful information about e-Learning system efficiency. In this context this paper presents a procedure of estimating studentpsilas accumulated knowledge based on concept maps. The procedure computes the percentage of covered concepts for a discipline that is partitioned in chapters.