Emil Brajković
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Emil Brajković has a total of 25 co-authors. Here are the top co-authors by number of shared publications:
- Daniel Vasić
University of Mostar, Mostar, Bosnia and Herzegovina
4 shared publications - Tomislav Volarić
University of Mostar
4 shared publications - Ani Grubišić
Faculty of Science, University of Split, Split, Croatia
3 shared publications Daniel Vasić
3 shared publications- Branko Žitko
University of Split, Faculty of Science Split Croatia
2 shared publications Daniel Vasic
2 shared publications
Latest Publications
- 10 October 2025
- Published by Springer Nature
- p. 182-195
AI Technologies in Music Education: Personalized Learning for Elementary School Students
- 10 October 2025
- Published by Springer Nature
- p. 182-195
AI Technologies in Music Education: Personalized Learning for Elementary School Students
- 10 October 2025
- Published by Springer Nature
- p. 283-294
Application of the Random Forest Algorithm for Team Role Classification Based on Belbin’s Self-perception Inventory
- 10 October 2025
- Published by Springer Nature
- p. 283-294
Application of the Random Forest Algorithm for Team Role Classification Based on Belbin’s Self-perception Inventory
- 3 July 2024
- Published by Springer Nature
- p. 273-288
Application of the Decision Tree in the Business Process
- 3 July 2024
- Published by Springer Nature
- p. 273-288
Application of the Decision Tree in the Business Process
- Open Access
- 28 August 2023
- Published by Pensoft Publishers in JUCS - Journal of Universal Computer Science
- Vol. 29 (8) , 866-891
The evaluation of a semi-automatic authoring tool for knowledge extraction in the AC&NL Tutor
This paper describes and evaluates the performance of a semi-automatic authoring tool (SAAT) for knowledge extraction in the AC&NL Tutor, highlighting its strengths and weaknesses. We assessed the accuracy of automatic annotation tasks (Part-of-Speech tagging, Name Entity Recognition, Dependency parsing, and Coreference Resolution) performed on a dataset of 160 sentences from unstructured Wikipedia text on a computer. We compared the automatic annotations to the gold standard, created after human post-editing and validation. Human-error analysis included 3769 words, 582 subsentences, 1129 questions, 917 propositions, 1020 concepts, and 667 relations. It resulted in the error type classification and the set of custom rules further used for automatic error identification and correction. The results showed that an average of 68.7% of the error corrections referred to CoreNLP performance and 31.3% to the SAAT extraction algorithms. Our main contributions include an integrated approach to the comprehensive pre-processing of the text, knowledge extraction and visualization; the consolidated evaluation of natural language processing tasks and knowledge extraction output (sentences, subsentences, questions, concept maps) and the newly developed reference dataset.
- 28 August 2023
- Published by Pensoft Publishers in JUCS - Journal of Universal Computer Science
- Vol. 29 (8) , 866-891
Open AccessThe evaluation of a semi-automatic authoring tool for knowledge extraction in the AC&NL Tutor
This paper describes and evaluates the performance of a semi-automatic authoring tool (SAAT) for knowledge extraction in the AC&NL Tutor, highlighting its strengths and weaknesses. We assessed the accuracy of automatic annotation tasks (Part-of-Speech tagging, Name Entity Recognition, Dependency parsing, and Coreference Resolution) performed on a dataset of 160 sentences from unstructured Wikipedia text on a computer. We compared the automatic annotations to the gold standard, created after human post-editing and validation. Human-error analysis included 3769 words, 582 subsentences, 1129 questions, 917 propositions, 1020 concepts, and 667 relations. It resulted in the error type classification and the set of custom rules further used for automatic error identification and correction. The results showed that an average of 68.7% of the error corrections referred to CoreNLP performance and 31.3% to the SAAT extraction algorithms. Our main contributions include an integrated approach to the comprehensive pre-processing of the text, knowledge extraction and visualization; the consolidated evaluation of natural language processing tasks and knowledge extraction output (sentences, subsentences, questions, concept maps) and the newly developed reference dataset.
- 11 July 2023
- Published by Springer Nature
- p. 1-17
Evaluating Text Summarization Using FAHP and TOPSIS Methods in Intelligent Tutoring Systems
- 11 July 2023
- Published by Springer Nature
- p. 1-17
Evaluating Text Summarization Using FAHP and TOPSIS Methods in Intelligent Tutoring Systems
- 17 November 2021
- Published by Springer Nature
- p. 213-220
Comparison of Semantic Role Labeling Tools on Previously Unseen Hand Annotated Texts
- 17 November 2021
- Published by Springer Nature
- p. 213-220
Comparison of Semantic Role Labeling Tools on Previously Unseen Hand Annotated Texts
- 10 July 2020
- Published by Springer Nature
- p. 293-310
Declarative Knowledge Extraction in the AC&NL Tutor
- 10 July 2020
- Published by Springer Nature
- p. 293-310
Declarative Knowledge Extraction in the AC&NL Tutor
- 1 September 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-5
Development and Evaluation of Word Embeddings for Morphologically Rich Languages
- 1 September 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-5
Development and Evaluation of Word Embeddings for Morphologically Rich Languages
- Open Access
- 1 September 2018
- Published by ASTES Journal in Advances in Science, Technology and Engineering Systems Journal
- Vol. 3 (5) , 01-05
Evaluation of Methods for Sentence Similarity for Use in Intelligent Tutoring System
- 1 September 2018
- Published by ASTES Journal in Advances in Science, Technology and Engineering Systems Journal
- Vol. 3 (5) , 01-05
Open AccessEvaluation of Methods for Sentence Similarity for Use in Intelligent Tutoring System
- 1 March 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-5
Application of data mining in e-Leaming systems
E-learning represents a new context of education that continuously generates large amounts of information that describe the continuity of interaction between learning and teaching. However, an abundance of available information is an exponentially growing problem, because unstructured and uncontrolled information may be obsolete or incorrect, and their amount congests the education system without providing any articulated knowledge. Data Mining is a process that uses statistical and mathematical procedures, techniques of artificial intelligence and machine learning to identify and extract useful information and subsequent knowledge from large databases to its participants and is a suitable tool for solving the problem of “information overload”. In this paper, the application of the data mining methods on the classification of the natural language sentences is presented.
- 1 March 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-5
Application of data mining in e-Leaming systems
E-learning represents a new context of education that continuously generates large amounts of information that describe the continuity of interaction between learning and teaching. However, an abundance of available information is an exponentially growing problem, because unstructured and uncontrolled information may be obsolete or incorrect, and their amount congests the education system without providing any articulated knowledge. Data Mining is a process that uses statistical and mathematical procedures, techniques of artificial intelligence and machine learning to identify and extract useful information and subsequent knowledge from large databases to its participants and is a suitable tool for solving the problem of “information overload”. In this paper, the application of the data mining methods on the classification of the natural language sentences is presented.