Lifelong learning has become an essential part of each profession. For this reason, personalized and adaptive learning has been drawing attention of professionals in the field of formal as well as... Show More

Lifelong learning has become an essential part of each profession. For this reason, personalized and adaptive learning has been drawing attention of professionals in the field of formal as well as informal education in the last few years. The effort has been made to design adaptive study supports regarding students' requirements, abilities and current knowledge. In the Czech Republic, particularly at the University of Ostrava, a team of educators, didactics professionals and IT professionals has been applying their mind to personalized learning in the electronic environment. They have been developing a suitable learning environment to fit students' learning styles. The paper describes a general model and a theory of adaptive eLearning from the perspective of the University of Ostrava professionals. It also demonstrates hard facts of the research in the field of language learning. This paper, Individualization of foreign language teaching through adaptive eLearning, is an extended version of the paper published in the ICWL 2015 workshop proceedings.

In a question-answering system, learner generated content including asked and answered questions is a meaningful resource to capture learning interests. This paper proposes an approach based on... Show More

In a question-answering system, learner generated content including asked and answered questions is a meaningful resource to capture learning interests. This paper proposes an approach based on question topic mining for revealing learners' concerned topics in real community question-answering systems. The authors' approach firstly preprocesses all questions associated with learners. Afterwards, it analyzes each question with text features and generates a weight feature matrix using a revised TF/IDF method. In order to decrease the sparsity issue of data distribution, the authors employ three concept-mapping strategies including named entity recognition, synonym extension, and hyponym replacement. Applying an SVM classifier, their approach categorizes user questions into representative topics. Three experiments are conducted based on a TREC dataset and an actual dataset containing 1,120 questions posted by learners from a commercial question-answering community. Results demonstrate the effectiveness of the method compared with conventional classifiers as baselines.

Common problems identified by students during their interaction with supervisors are too little instructions as well as infrequent and insufficient supervisor feedback. The SciPro system has been... Show More

Common problems identified by students during their interaction with supervisors are too little instructions as well as infrequent and insufficient supervisor feedback. The SciPro system has been developed to tackle these problems. This paper describes, analyze and discuss the interaction between students and supervisors using the SciPro system. Through two use cases involving two supervisors and 38 bachelor and master students, the authors show that the structure implemented in SciPro supports and allows for different pedagogical approaches and supervision styles. Ten different types of interactions in the thesis process are identified. In order to explain why some students do not complete within the timeframe, the authors identify six categories of problems: 1) language skills, 2) inability to apply research methods, 3) ability for self-study, 4) lack of creativity, 5) limited knowledge about how to write academic work, and 6) lack of motivation. The collaborative stage of group-supervision may be one possible way to deal with the different type of support for the process of managing student theses.

The paper focuses on the field of learning styles in e-learning. The study is structured in two main parts: (1) a brief overview of traditional approaches to learning styles is presented and their... Show More

The paper focuses on the field of learning styles in e-learning. The study is structured in two main parts: (1) a brief overview of traditional approaches to learning styles is presented and their role in the process of instruction is set; this part results in the reflection of current state, when learning styles are considered within e-learning; (2) results of meta-analysis dealing with learning styles in the e-learning environment are introduced focusing on two periods (2001-2007, 2008-2014) and journals in selected databases ProQuest Central, Elsevier Science Direct and ERIC. Totally 5,361 papers were collected and structured according to three criteria: (1) time period, (2) relevancy of information sources and (3) relevant key words. Collected data underwent the chí-squared test for independence and the analysis of adjusted residuals on the significance level a=0.05. No statistically significant changes were discovered in the research sample, however, some shifts were detected in this field. Finally, the results were discussed and relating conclusions provided.

Teaching and learning are increasingly taking advantage of the rapid growth in Internet resources, open content, mobile technologies and social media platforms. However, due to the generally... Show More

Teaching and learning are increasingly taking advantage of the rapid growth in Internet resources, open content, mobile technologies and social media platforms. However, due to the generally unstructured nature and overwhelming quantity of learning content, effective learning remains challenging. In an effort to close this gap, the authors designed and built an Open Content Social Learning (OCSL) system that compares different pedagogical strategies and algorithms intended to improve learning. Their results have shown increased effectiveness when recommending learning activities in a pedagogically appropriate order based on learning goals, historical learning preferences, and behaviors from other learners who had similar goals.

With the development of e-commerce, websites such as Amazon and eBay have become very popular. Users post reviews of products and rate the helpfulness of reviews on these websites. Reviews written... Show More

With the development of e-commerce, websites such as Amazon and eBay have become very popular. Users post reviews of products and rate the helpfulness of reviews on these websites. Reviews written by a user and reviews rated by a user reflect the user's interests and disinterest. Thus, they are very useful for user profiling. In this study, the authors explore users' reviews and ratings of reviews for personalized searching and propose a review-based user profiling method. To satisfy a user's basic information needs, expressed in the form of a query, they also propose a priority-based result ranking strategy. For evaluation, they conduct experiments on a real-life data set. The experimental results show that their method can significantly improve retrieval quality.