Educational data mining (EDM) is an emerging interdisciplinary research area that deals with the development of methods to explore data originating in an educational context. EDM uses computational approaches to analyze educational data in order to study educational questions. This paper surveys the most relevant studies carried out in this field to date. First, it introduces EDM and describes the different groups of user, types of educational environments, and the data they provide. It then goes on to list the most typical/common tasks in the educational environment that have been resolved through data-mining techniques, and finally, some of the most promising future lines of research are discussed.

/pdf/educational-data-mining-a-review-of-the-state-of-the-art-51aglgywl8.pdf

Educational Data Mining: A Review of the State of the Art

In the last 16 years, more than 200 research articles were published about research-paper recommender systems. We reviewed these articles and present some descriptive statistics in this paper, as well as a discussion about the major advancements and shortcomings and an overview of the most common recommendation concepts and approaches. We found that more than half of the recommendation approaches applied content-based filtering (55 %). Collaborative filtering was applied by only 18 % of the reviewed approaches, and graph-based recommendations by 16 %. Other recommendation concepts included stereotyping, item-centric recommendations, and hybrid recommendations. The content-based filtering approaches mainly utilized papers that the users had authored, tagged, browsed, or downloaded. TF-IDF was the most frequently applied weighting scheme. In addition to simple terms, n-grams, topics, and citations were utilized to model users' information needs. Our review revealed some shortcomings of the current research. First, it remains unclear which recommendation concepts and approaches are the most promising. For instance, researchers reported different results on the performance of content-based and collaborative filtering. Sometimes content-based filtering performed better than collaborative filtering and sometimes it performed worse. We identified three potential reasons for the ambiguity of the results. (A) Several evaluations had limitations. They were based on strongly pruned datasets, few participants in user studies, or did not use appropriate baselines. (B) Some authors provided little information about their algorithms, which makes it difficult to re-implement the approaches. Consequently, researchers use different implementations of the same recommendations approaches, which might lead to variations in the results. (C) We speculated that minor variations in datasets, algorithms, or user populations inevitably lead to strong variations in the performance of the approaches. Hence, finding the most promising approaches is a challenge. As a second limitation, we noted that many authors neglected to take into account factors other than accuracy, for example overall user satisfaction. In addition, most approaches (81 %) neglected the user-modeling process and did not infer information automatically but let users provide keywords, text snippets, or a single paper as input. Information on runtime was provided for 10 % of the approaches. Finally, few research papers had an impact on research-paper recommender systems in practice. We also identified a lack of authority and long-term research interest in the field: 73 % of the authors published no more than one paper on research-paper recommender systems, and there was little cooperation among different co-author groups. We concluded that several actions could improve the research landscape: developing a common evaluation framework, agreement on the information to include in research papers, a stronger focus on non-accuracy aspects and user modeling, a platform for researchers to exchange information, and an open-source framework that bundles the available recommendation approaches.

/pdf/research-paper-recommender-systems-a-literature-survey-3o8izjcp9m.pdf

Research-paper recommender systems: a literature survey

Please provide a short abstract of 100 to 250 words. The abstract should not contain any undefined abbreviations or unspecified references. Work planned but not completed should not appear in the abstract.

User Modeling and User-Adapted Interaction

This paper aims to provide the reader with a comprehensive background for understanding current knowledge on Learning Analytics (LA) and Educational Data Mining (EDM) and its impact on adaptive learning. It constitutes an overview of empirical evidence behind key objectives of the potential adoption of LA/EDM in generic educational strategic planning. We examined the literature on experimental case studies conducted in the domain during the past six years (2008-2013). Search terms identified 209 mature pieces of research work, but inclusion criteria limited the key studies to 40. We analyzed the research questions, methodology and findings of these published papers and categorized them accordingly. We used non-statistical methods to evaluate and interpret findings of the collected studies. The results have highlighted four distinct major directions of the LA/EDM empirical research. We discuss on the emerged added value of LA/EDM research and highlight the significance of further implications. Finally, we set our thoughts on possible uncharted key questions to investigate both from pedagogical and technical considerations.

/pdf/learning-analytics-and-educational-data-mining-in-practice-a-1k0fqkfbc6.pdf

Learning Analytics and Educational Data Mining in Practice: A Systematic Literature Review of Empirical Evidence.

Educational data mining and learning analytics for 21st century higher education: A review and synthesis

In this paper we present a method for adaptive selection of test questions according to the individual needs of students within a web-based educational system. It functions as a combination of three particular methods. The first method is based on the course structure and focuses on the selection of the most appropriate topic for learning. The second uses Item Response Theory to select the k-best questions with adequate difficulty for a particular learner. The last is based on the usage history and prioritizes questions according to specific strategies, e.g. to filter out the questions that were recently asked. We describe how these methods evaluate user answers to gather information concerning their characteristics for a more precise selection of further questions. We describe an evaluation of the impact of a proposed method through two different types of experiments in the domain of learning programming, which both showed that our method for adaptive test question selection increases the overall learning outcome, especially for lower than average performing students.

/pdf/on-the-impact-of-adaptive-test-question-selection-for-108zy4cym1.pdf

On the impact of adaptive test question selection for learning efficiency

State-of-the-art learning management systems provide their stake-holders with many features coming from Web 20 paradigm, but often ignore the need for personalization and adaptation during the learning More, learning activities are often fragmented – a student needs to make a decision whether he or she wants to take questions or read explanatory materials In addition, majority of current solutions do not provide a truly interactive environment, where students are allowed to participate in content creation and maintenance In this paper, we address these issues by proposing and developing a framework for Adaptive Web-based Learning 20 We describe basic requirements for such a framework and provide an overview of all its important underlying models and functionality

/pdf/alef-a-framework-for-adaptive-web-based-learning-2-0-3jm1rn36xr.pdf

ALEF: A Framework for Adaptive Web-Based Learning 2.0

Throughout the last decade, there has been an alarming decrease in daily physical activity among both children and adults. Medical experts agree that physical activity is critical to maintaining fitness, reducing weight and improving health. Yet so many people have difficulty increasing and maintaining physical activity in everyday life. We have created a solution called Move2Play, which encourages a healthier lifestyle and motivates to participate in regular physical activity. We have integrated four essential parts that form the basis for long-term progress and sustainability - Activity Recommendation, Tracking, Evaluation and Motivation. In order to recognize and assess physical activity, we have developed a system for mobile phones that collects data from various sensors, such as accelerometer, GPS and GSM. We provide personalization, i.e. we have proposed and realized activity recommendation for an individual user to ensure that the users engage in regular exercise, as opposed to occasional outbursts of activity, which are unhealthy and even harmful. We discuss our proposed mechanisms of activity recommendation and the concept of motivation, which represent a key element for any system that fights the sedentary lifestyle of the modern generation.

Move2Play: an innovative approach to encouraging people to be more physically active

As the Web grows and the amount of available informa- tion increases, new problems such as information over- load or lost-in-hyperspace problem emerge. The solution is to shift from \one-size-ts-all " approach and to pro- vide personalized surng experience, which would take into account dierences among users. These dierences are captured in a user model, a structure holding all rel- evant user-related information. We present contributions in both data collection and processing stages of user mod- eling process, focusing on open corpus web-based sys- tems, where the content can be dynamically added or changed and we have no content available in the design stage of the web-based system. We introduce two meth- ods falling within the scope of data collection stage, a method for comprehensive logging of user activity on the Web with preserved semantics, which combines client side and server side logging into a stream of user events with clearly dened meaning, and a method for capturing logs of \wild" Web surng based on a specialized proxy sever. The second group of methods, devoted to actual user model creation within an open corpus environment con- sists of a method for user model inference based on rules expressing navigational patterns, a method for term-based open corpus user modeling, which can be applied to cap- ture user's interest across the third-party web-sites and web-based systems. We proposed also a method for nd- ing relations between terms based on folksonomies, which supports our term-based user modeling approach. The proposed methods were evaluated by means of software tools that were incorporated in research projects aimed

/pdf/towards-social-based-user-modeling-and-personalization-11h6tnp3ds.pdf

Towards Social-based User Modeling and Personalization

IVIany current web-based information systems need to adapt to individual user characteristics in order to streamline common tasks and enable users to use them efficiently. In this paper we describe an approach to user characteristics acquisition based on automatic analysis of user behavior thus minimizing the amount of necessary user involvement. We stress the importance of appropriate data collection and propose a novel approach to logging, in which we preserve the semantics of logged evelrts. This has a significant inrpact on the successive log analysis, which focuses on the estimation of user characteristics from user navigation.

/pdf/user-characteristics-acquisition-from-logs-with-semantics-3wljy2n99u.pdf

Michal Barla

Papers

On the impact of adaptive test question selection for learning efficiency

ALEF: A Framework for Adaptive Web-Based Learning 2.0

Move2Play: an innovative approach to encouraging people to be more physically active

Towards Social-based User Modeling and Personalization

User Characteristics Acquisition from Logs with Semantics.