Johannes Zenkert

Knowledge discovery from social media using big data-provided sentiment analysis SoMABiT

In today’s competitive business world, being aware of customer needs and market-oriented production is a key success factor for industries. To this aim, the use of efficient analytical algorithms ensures better understanding of customer feedback and improves the next generation of products. Accordingly, the dramatic increase in the use of social media in daily life provides beneficial sources for market analytics. Yet how traditional analytic algorithms and methods can be scaled up for such disparate and multistructured data sources is a major challenge. This paper presents and discusses the technological and scientific focus of SoMABiT as a social media analysis platform using big data technology. Sentiment analysis has been employed in order to discover knowledge from social media. The use of MapReduce and the development of a distributed algorithm towards an integrated platform that can scale for any data volume and provide social media-driven knowledge is the main novelty of the proposed concept in comparison to the state-of-the-art technologies.

Sentiment analysis in financial markets A framework to utilize the human ability of word association for analyzing stock market news reports

As financial markets getting faster and more complex, it is difficult for market participants to manage the information overload. Sentiment analysis is a useful text mining method to process textual content and filter the results with analysis methods to relevant and meaningful information. The paper in hand introduces a new method for sentiment analysis in financial markets which combines word associations and lexical resources. Based on stock market news from January 2000 to February 2014 we analyzed documents on different levels. The results are presented and evaluated in this paper.

Improving CBR adaptation for recommendation of associated references in a knowledge-based learning assistant system

Abstract Case adaptation is a challenging phase of case-based reasoning (CBR) for recommendation of a matched case solution. Our proposed knowledge-based recommendation system analyzes the combination of visual and textual information in CBR medical system. In this paper a case-based reasoner uses medical expressions in a textual analysis to create word association profiles. Case-based Learning Assistant System (DePicT CLASS) finds significant references and learning materials by utilizing profile of words associations according to the problem description. This research proposes a new adaptation mechanism based on substitution, abstraction, and compositional method for collaborative recommendation in medical vocational educational training. The DePicT CLASS adaptation mechanism has a combination of value comparison based on requested word association profiles and manual adaptation based on user collaborative recommendation. In the adaptation process of the system, attract rate and adapt rate are defined and utilized for evaluating the adaptation results. Therefore, recommendation is a combination of references and learning materials with highest valued keyword association strength from the most similar cases.

Multidimensional knowledge representation of text analytics results in knowledge bases

In the age of digitization, intelligent systems have to cope with an ever-growing amount of data. Therefore, knowledge representation plays a key-role for applications to handle continuously created data and to enable an access on flexible and extensively well-described data structures. This paper introduces a knowledge base design which has the capability of dimensional structuring of semantically-related data and explains how text analytic results can be integrated into a knowledge base. The paper discusses the main advantages of this design and shows how the data can be arranged in the knowledge base. The multidimensional structure of the knowledge base helps to resolve one of the main challenges of knowledge discovery which is the extraction of meaningful information from data in a context.

The COMALAT Approach to Individualized E-Learning in Job-Specific Language Competences

COMALAT (Competence Oriented Multilingual Adaptive Language Assessment and Training) project aims to strengthen the mobility of young workers across Europe, by improving job‐specific language competence tailored individually to particular needs. In this work we will concentrate on the COMALAT learning management system (LMS), which is a language learning system for Vocational Education and Training (VET). COMALAT LMS aims at providing learning material as an Open Educational Resource (OER) and is capable of self‐adapting to the needs of different learners. Each learner is treated individually in acquiring new language skills related to job‐specific competences. In addition, it is specifically tailored towards addressing competence areas, and therefore it is not a generic language learning platform. We discuss some technical details of the COMALAT platform and present the various aspects of system adaptability which tries to imitate the help provided by an instructor by observing the users’ strengths, weaknesses and progress in general, during the learning process. Also we discuss the digital e‐learning materials in COMALAT.

Discovering contextual knowledge with associated information in dimensional structured knowledge bases

The visualization and simplification of complex semantically-related knowledge is one of the main challenges in knowledge discovery. In this regard, the knowledge map is a good visualization instrument to represent and provide suitable information with analysis potential. Multidimensional knowledge bases aim to support this objective and store automatically extracted facts and their dimensional relations from textual knowledge resources. In this paper, a dynamic layout structure for knowledge maps based on dimensional information is introduced. The Concept of the Imitation of the Mental Ability of Word Association (CIMAWA) is applied in this approach to create a graphical structure as arrangement of associated information on different levels of textual information.