Search

This paper focuses on learning analytics framework behind Math Elements mathematics game. The game, was introduced at ECGBL 2012. The novelty value of this design study is in development process of visualizing and data mining technologies behind the learning analytics. The analytic tools provide 1) easy access to follow progress and 2) real time analysis on the learning process. The analytics gives fast and easy to understand view into learning process, still supporting the story, the game play and motivation towards game play. In this paper we show the user centered development process, the improvements done according to user feedback and open the future research focuses. [ABSTRACT FROM AUTHOR]

This paper focuses on learning analytics framework behind Math Elements mathematics game. The game, was  introduced at ECGBL 2012. The novelty value of this design study is in development process of visualizing and data mining  technologies behind the learning analytics. The analytic tools provide 1) easy access to follow progress and 2) real time  analysis on the learning process. The analytics gives fast and easy to understand view into learning process, still supporting  the story, the game play and motivation towards game play. In this paper we show the user centered development  process, the improvements done according to user feedback and open the future research focuses. [ABSTRACT FROM AUTHOR]

This paper focuses on learning analytics framework behind Math Elements mathematics game. The game, was introduced at ECGBL 2012. The novelty value of this design study is in development process of visualizing and data mining technologies behind the learning analytics. The analytic tools provide 1) easy access to follow progress and 2) real time analysis on the learning process. The analytics gives fast and easy to understand view into learning process, still supporting the story, the game play and motivation towards game play. In this paper we show the user centered development process, the improvements done according to user feedback and open the future research focuses. [ABSTRACT FROM AUTHOR]

Social media services, such as YouTube, Flickr and Slideshare, contain enormous number of content valuable for education. If the requested theme can be effectively searched or recognized, teacher can easily construct the course material from social media sources. However, the search engines are not optimal for educational purposes: Search engines can list numerous pieces of content that matches more or less perfectly to keywords. After search there are thousands of pieces of content to check manually if they really fit to the requested subject. A common method to increase information accessibility in social media applications is tagging. However, when tags are used only as single words, we easily end up to information overload. In this study the general aim is to construct teachable agents that can learn conceptual structures in terms of conceptual learning. Problems related to information retrieval or semantics are widely studied, but not from learning point of view. By combining theories about cognitive psychology of learning and machine learning, we could make a completely new approach to decrease information overload. According to results, we can say that simulating human way to learn fits for this purpose. [ABSTRACT FROM AUTHOR]

Data Mining refers to methods to find patterns, dependencies or other meaningful information from large data sets. Common methods for data mining are based on regression analysis, Bayesian models, clustering algorithms and neural networks. Data Mining has been successfully applied in science, business and logistics for years. However, educational Data Mining is relatively young discipline focusing on understanding students' use of interactive learning environments. According to original ideas of Data Mining, there are no hypotheses set in advance: the data will reveal the answers. The study focuses on the process of conceptual change (N=818) while trying to reveal playing behavior that facilitates it and learning transfer. In the paper we briefly describe the conceptual change approach, data mining methods and our research framework for transfer. Finally, the results of the study are presented and discussed. The main result is a finding that difficulties in understanding different numbering systems are mediated by fraction numbers with odd numbered nominators. These results show the strengths of Educational Data Mining: we could point out difficulties and their backgrounds, which would not have been found without mining approach. [ABSTRACT FROM AUTHOR]