Jan Paralic

An approach to feature selection for sentiment analysis

Sentiment analysis deals with methods for automatic analysis of the subjective aspects of the text. In this contribution we first present an overview of main approaches currently used in sentiment analysis. We further focus on feature selection methods for sentiment analysis and propose a new approach to feature selection. Our approach has been experimentally evaluated on movie review dataset. The results show that the proposed method is computationally efficient and in exchange sacrifices only a small amount of accuracy.

Knowledge management in a distributed organisation

It has become very important for advanced organisations to make the best use of information gathered from various document sources inside companies and from external sources like the Internet. There are many technologies under development, which address knowledge discovery. On the other hand, there is a lack of efficient technologies focused on organising and sharing of existing knowledge. In this paper we introduce the research in scope of Know Webi (EC funded project). We focus our attention on two important issues — (i) how to capture tacit, contextual knowledge that is connected to the documents and (ii) how to support knowledge management in geographically distributed organisations through up-to-date communication and AI technologies

The role of ontologies in collaborative systems

This paper deals with the role of ontologies in collaborative systems. The research field of collaborative systems and their support by information and communication technologies describes theory called CSCW (computer supported cooperative work). During last few years the CSCW has been evolving and extending, e.g. CSCL (computer supported collaborative learning) has emerged. With a well-defined ontology structure, CSCL can accumulate the knowledge representation of learning objects, including participant background, group information, instruction designs, learning activities and learning outcomes.

Meteorological phenomena forecast using data mining prediction methods

The occurrence of various meteorological phenomena, such as fog or low cloud cover, has significant impact on many human activities as air or ship transport operations. The management of air traffic at the airports was the main reason to design effective mechanisms for timely prediction of these phenomena. In both these cases meteorologists already use some physical models based on differential equations as simulations. Our goal was to design, implement and evaluate a different approach based on suitable techniques and methods from data mining domain. The selected algorithms were applied on obtained historical data from meteorological observations at several airports in United Arab Emirates and Slovakia. In the first case, the fog occurrence was predicted based on data from METAR messages with algorithms based on neural networks and decision trees. The low cloud cover was forecasted at the national Slovak airport in Bratislava with decision trees. The whole data mining process was managed by CRISP-DM methodology, one of the most accepted in this domain.

Analyses of Knowledge Creation Processes Based on Different Types of Monitored Data

This paper presents specialized methods for analyzing knowledge creation processes and knowledge practices that are (at least partially) projected in work within a virtual collaborative environment. Support for such analysis and evaluation of knowledge creation processes is provided by historical data stored in a virtual working environment, and describes various aspects of the monitored processes (e.g. semantic information, content, log of activities, etc.). The proposed analytical methods cover different types of analysis, such as (a) statistic analysis, that provides information about processes, and the possibility to visualize such information based on user-selected presentation modes; (b) time-line based analysis that supports visualization of the real process execution with all relevant information, including the possibility to identify and further analyze working patterns in knowledge creation processes (projection of knowledge practices). Experimental evaluation of the proposed methods is carried out within the IST EU project called KP-Lab.

First Trials in Webocracy

The Webocracy project aims to empower citizens with innovative communication, access and polling system, supporting increased participation in democratic processes. One of the main project goals is to develop an open source web-based system called Webocrat as a multi-channel communication platform supporting e-government and e-democracy applications. Some of the Webocrat modules were tested in first trial of our two pilot applications, one of them running in Wolverhampton, UK and the other one in Kosice, Slovakia. Currently, whole integrated Webocrat system is being tested within the second trials.

On Patient’s Characteristics Extraction for Metabolic Syndrome Diagnosis: Predictive Modelling Based on Machine Learning

The work presented in this paper demonstrates how different data mining approaches can be applied to extend conventional combinations of variables determining the Metabolic Syndrome with new influential variables, which are easily available in the everyday physician‘s practice. The results have important consequences: patients with the Metabolic Syndrome can be recognized by using only some, one, or none of the conventional variables, when replaced with some other surrogate variables, available in patient health records, making diagnosis feasible in different work environments and at different time points of patient care. In addition, the results showed that there is a large diversity of patient groups, much larger than it was supposed earlier on when their identification was based on the conventional variables approach, indicating the underlying complexity of this syndrome. Finally, the discovered novel variables, indicating yet unknown pathogenetic pathways can be used to inspire future research.

Analytical Framework for Mirroring and Reflection of User Activities in E-Learning Environment

This chapter deals with evaluation of user activities and their participation in collaborative processes realized within the supporting virtual environment. The main goal behind proposed solution is to provide standalone package with all necessary functionalities to obtain data from examined virtual collaborative system in form of logs. For this purpose the following has been designed and implemented: a repository with predefined log format representing source historical data for analyzes; supporting middleware services for proposed analytical approaches; end-user tool for time-line based mirroring and analyses of user activities. These basic functionalities are extended with possibility to extract various summative statistics [10] about performed user activities and possibility to export data in predefined format (e.g. MS Excel) for analyses in third party tools as e.g. IBM SPSS Modeler. Described analytical framework has been designed, implemented and tested mainly within KP-Lab System that represents new interesting application in the domain of virtual environments or e-Learning systems. Proposed architecture was designed as generic platform with possibility to be integrated with other systems such as Moodle or Claroline in order to reflect different user practices.

Knowledge enhanced e-government portal

There is a growing number of e-Government portals and solutions available today. But what the users lack in particular is a customised assistance - help that meets the individual situation and competence [13]. In this paper, a system called Webocrat will be presented as an attempt to shift e-Government portals toward this direction, providing knowledge management strategy as its basis [11]. The Webocrat system applies a knowledge-based approach [5]. Information of all kinds produced by various modules is linked to a shared ontology representing an application domain. Such ontology serves as a means for structuring and organizing available information resulting in improved search capability and contents presentation.

A look at clp: Theory and application

Constraint logic programming CLP is a relatively new programming paradigm. During its 10 years of existence the theory of CLP has been increasingly understood and the two differ ent approaches domain technology and incremental linear solving have been implemented in various CLP systems. Meanwhile the commercial attractivity of CLP has been growing. Since 1989 a couple of commercial CLP systems appeared on the software market and have been successfully used in many real life applications. The power of CLP stems from its ability to solve hard combinatorial problems such as planning scheduling resource allocation and many others. How CLP originated from two declarative paradigms - constraint solving and logic programming - is informally explained and the relationship between the different ap proaches in CLP is presented. The main part of the article presents a real life scheduling appli cation for the largest Slovak metallurgy company using the CLP system ECL PS.