Sanja Candrlic
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Sanja Candrlic has a total of 42 co-authors. Here are the top co-authors by number of shared publications:
- Martina Asenbrener Katic
University of Rijeka
14 shared publications - Mile Pavlic
University of Rijeka
11 shared publications - Martina Holenko Dlab
Faculty of Informatics and Digital Technologies, University of Rijeka, 51000 Rijeka, Croatia
6 shared publications - Alen Jakupovic
Business Department, Polytechnic of Rijeka, Rijeka, Croatia
4 shared publications - Ivan Dražić
Faculty of Engineering, University of Rijeka, Vukovarska 58, 51000 Rijeka, Croatia
4 shared publications - Patrizia Poscic
University of Rijeka
4 shared publications
Latest Publications
- 1 June 2025
- Published by IATED Academy in EDULEARN Proceedings
- Vol. 1, 8826-8833
ENHANCING THE TEACHING PROCESS: A CASE STUDY USING HONEY & MUMFORD LEARNING STYLES
- 1 June 2025
- Published by IATED Academy in EDULEARN Proceedings
- Vol. 1, 8826-8833
ENHANCING THE TEACHING PROCESS: A CASE STUDY USING HONEY & MUMFORD LEARNING STYLES
- Open Access
- 21 March 2025
- Published by MDPI AG in Algorithms
- Vol. 18 (4) , 177
A Scoring Algorithm for the Early Prediction of Academic Risk in STEM Courses
Educational data mining (EDM) and learning analytics (LA) are widely applied to predict student performance, particularly in determining academic success or failure. This study presents the development of a scoring algorithm for the early identification of students at risk of failing science, technology, engineering, and mathematics (STEM) courses. The proposed approach follows a structured process: First, educational data are collected, processed, and statistically analyzed. Next, numerical variables are transformed into dichotomous predictors, and their relevance is assessed using Cramér’s V measure to quantify their association with course outcomes. The final step involves constructing a scoring system that dynamically evaluates student performance over 15 weeks of instruction. Prospective validation of the model demonstrated excellent predictive performance (accuracy = 0.93, sensitivity = 0.95, specificity = 0.92), confirming its effectiveness in early risk detection. The resulting scoring algorithm is distinguished by its methodological simplicity, ease of implementation, and adaptability to different educational settings, making it a practical tool for timely interventions.
- 21 March 2025
- Published by MDPI AG in Algorithms
- Vol. 18 (4) , 177
Open AccessA Scoring Algorithm for the Early Prediction of Academic Risk in STEM Courses
Educational data mining (EDM) and learning analytics (LA) are widely applied to predict student performance, particularly in determining academic success or failure. This study presents the development of a scoring algorithm for the early identification of students at risk of failing science, technology, engineering, and mathematics (STEM) courses. The proposed approach follows a structured process: First, educational data are collected, processed, and statistically analyzed. Next, numerical variables are transformed into dichotomous predictors, and their relevance is assessed using Cramér’s V measure to quantify their association with course outcomes. The final step involves constructing a scoring system that dynamically evaluates student performance over 15 weeks of instruction. Prospective validation of the model demonstrated excellent predictive performance (accuracy = 0.93, sensitivity = 0.95, specificity = 0.92), confirming its effectiveness in early risk detection. The resulting scoring algorithm is distinguished by its methodological simplicity, ease of implementation, and adaptability to different educational settings, making it a practical tool for timely interventions.
- 1 November 2024
- Published by IATED Academy
- Vol. 1, 9300-9306
UNVEILING STUDENT GROUP DIFFERENCES THROUGH HIERARCHICAL CLUSTERING: A DETAILED COMPARISON OF STEM AND SOCIAL SCIENCE COURSES
- 1 November 2024
- Published by IATED Academy
- Vol. 1, 9300-9306
UNVEILING STUDENT GROUP DIFFERENCES THROUGH HIERARCHICAL CLUSTERING: A DETAILED COMPARISON OF STEM AND SOCIAL SCIENCE COURSES
- 1 November 2024
- Published by IATED Academy in ICERI Proceedings
- Vol. 1, 9267-9274
DESIGNING ACTIVITIES FOR TEACHING STEM COURSES IN HIGHER EDUCATION
- 1 November 2024
- Published by IATED Academy in ICERI Proceedings
- Vol. 1, 9267-9274
DESIGNING ACTIVITIES FOR TEACHING STEM COURSES IN HIGHER EDUCATION
- 1 March 2024
- Published by IATED Academy in INTED Proceedings
- Vol. 1, 7305-7315
PERFORMANCE ANALYSIS OF VIRTUAL ASSISTANTS - A CASE STUDY BASED ON THE CROATIAN LANGUAGE
- 1 March 2024
- Published by IATED Academy in INTED Proceedings
- Vol. 1, 7305-7315
PERFORMANCE ANALYSIS OF VIRTUAL ASSISTANTS - A CASE STUDY BASED ON THE CROATIAN LANGUAGE
- Open Access
- 1 January 2024
- Published by Polytechnic of Rijeka University in Zbornik Veleučilišta u Rijeci
- Vol. 12 (1) , 223-242
The employment of machine learning algorithms for prediction in learning analytics and educational data mining within the context of higher education
U radu je prezentiran pregled literature u posljednjih pet godina o prediktivnim metodama analitika učenja i rudarenja obrazovnih podataka temeljenim na algoritmima strojnog učenja. Primarni kriterij odabira za analizirane radove bio je identificirati one koji koriste algoritme strojnog učenja za predviđanje ishoda u područjima analitika učenja i rudarenja obrazovnih podataka u kontekstu visokog obrazovanja. Važno je naglasiti da ne postoje univerzalne smjernice ili protokoli za predviđanje ishoda u obrazovanju, uključujući i visoko obrazovanje. Metodologija koja se koristi za takva predviđanja prvenstveno ovisi o ciljanoj varijabli i vrsti korištenih ulaznih podataka. U detaljnu analizu uključeno je 25 radova iz citatnih baza Web of Science CC i Scopus. Pomoću šest istraživačkih pitanja ispitano je što se želi predvidjeti u visokom obrazovanju, koji su ulazni podaci korišteni, koliko je algoritama strojnog učenja korišteno u pojedinom istraživanju i koji su bili najučinkovitiji. Također se ispitalo koje su druge tehnike prediktivnog modeliranja navedene te navodi li se programsko okruženje pomoću kojeg je predikcija izvršena.
- 1 January 2024
- Published by Polytechnic of Rijeka University in Zbornik Veleučilišta u Rijeci
- Vol. 12 (1) , 223-242
Open AccessThe employment of machine learning algorithms for prediction in learning analytics and educational data mining within the context of higher education
U radu je prezentiran pregled literature u posljednjih pet godina o prediktivnim metodama analitika učenja i rudarenja obrazovnih podataka temeljenim na algoritmima strojnog učenja. Primarni kriterij odabira za analizirane radove bio je identificirati one koji koriste algoritme strojnog učenja za predviđanje ishoda u područjima analitika učenja i rudarenja obrazovnih podataka u kontekstu visokog obrazovanja. Važno je naglasiti da ne postoje univerzalne smjernice ili protokoli za predviđanje ishoda u obrazovanju, uključujući i visoko obrazovanje. Metodologija koja se koristi za takva predviđanja prvenstveno ovisi o ciljanoj varijabli i vrsti korištenih ulaznih podataka. U detaljnu analizu uključeno je 25 radova iz citatnih baza Web of Science CC i Scopus. Pomoću šest istraživačkih pitanja ispitano je što se želi predvidjeti u visokom obrazovanju, koji su ulazni podaci korišteni, koliko je algoritama strojnog učenja korišteno u pojedinom istraživanju i koji su bili najučinkovitiji. Također se ispitalo koje su druge tehnike prediktivnog modeliranja navedene te navodi li se programsko okruženje pomoću kojeg je predikcija izvršena.
- 24 September 2023
- Published by Springer Nature
- p. 665-675
Predicting Students’ Academic Success Based on Various Course Activities: A Case Study
- 24 September 2023
- Published by Springer Nature
- p. 665-675
Predicting Students’ Academic Success Based on Various Course Activities: A Case Study
- 20 August 2023
- Published by Springer Nature
- p. 856-869
Monolayer Network Representation and Analysis of the Curriculum
- 20 August 2023
- Published by Springer Nature
- p. 856-869
Monolayer Network Representation and Analysis of the Curriculum
- Open Access
- 11 March 2022
- Published by MDPI AG in Electronics
- Vol. 11 (6) , 889
A Corpus-Based Sentence Classifier for Entity–Relationship Modelling
Automated creation of a conceptual data model based on user requirements expressed in the textual form of a natural language is a challenging research area. The complexity of natural language requires deep insight into the semantics buried in words, expressions, and string patterns. For the purpose of natural language processing, we created a corpus of business descriptions and an adherent lexicon containing all the words in the corpus. Thus, it was possible to define rules for the automatic translation of business descriptions into the entity–relationship (ER) data model. However, since the translation rules could not always lead to accurate translations, we created an additional classification process layer—a classifier which assigns to each input sentence some of the defined ER method classes. The classifier represents a formalized knowledge of the four data modelling experts. This rule-based classification process is based on the extraction of ER information from a given sentence. After the detailed description, the classification process itself was evaluated and tested using the standard multiclass performance measures: recall, precision and accuracy. The accuracy in the learning phase was 96.77% and in the testing phase 95.79%.
- 11 March 2022
- Published by MDPI AG in Electronics
- Vol. 11 (6) , 889
Open AccessA Corpus-Based Sentence Classifier for Entity–Relationship Modelling
Automated creation of a conceptual data model based on user requirements expressed in the textual form of a natural language is a challenging research area. The complexity of natural language requires deep insight into the semantics buried in words, expressions, and string patterns. For the purpose of natural language processing, we created a corpus of business descriptions and an adherent lexicon containing all the words in the corpus. Thus, it was possible to define rules for the automatic translation of business descriptions into the entity–relationship (ER) data model. However, since the translation rules could not always lead to accurate translations, we created an additional classification process layer—a classifier which assigns to each input sentence some of the defined ER method classes. The classifier represents a formalized knowledge of the four data modelling experts. This rule-based classification process is based on the extraction of ER information from a given sentence. After the detailed description, the classification process itself was evaluated and tested using the standard multiclass performance measures: recall, precision and accuracy. The accuracy in the learning phase was 96.77% and in the testing phase 95.79%.
- 1 March 2022
- Published by IATED Academy in INTED Proceedings
- Vol. 1, 2865-2872
EVOLUTION OF THE DATA MODELLING COURSE DURING COVID-19 PANDEMIC
Information about the paper titled "EVOLUTION OF THE DATA MODELLING COURSE DURING COVID-19 PANDEMIC" at IATED Digital Library
- 1 March 2022
- Published by IATED Academy in INTED Proceedings
- Vol. 1, 2865-2872
EVOLUTION OF THE DATA MODELLING COURSE DURING COVID-19 PANDEMIC
Information about the paper titled "EVOLUTION OF THE DATA MODELLING COURSE DURING COVID-19 PANDEMIC" at IATED Digital Library