Olivera Grljević
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Olivera Grljević has a total of 21 co-authors. Here are the top co-authors by number of shared publications:
- Mirjana Marić
Faculty of Economics in Subotica, University of Novi Sad, 24000 Subotica, Serbia
4 shared publications Aleksandar Kovačević
University of Novi SadNovi SadSerbia
2 shared publications- Luka Gluščević
Faculty of Economics in Subotica University of Novi Sad Subotica Serbia
2 shared publications Zita Bošnjak
University of Novi SadNovi SadSerbia
2 shared publications- Aleksandar Kovačević
University of Novi Sad
1 shared publication Bulevar Mihajla Pupina 6/Iv Turism Organisation Of Vojvodina
1 shared publication
Latest Publications
- Open Access
- 17 September 2026
- Published by MDPI AG in Sustainability
- Vol. 18 (18) , 9561
From Functional to Social Centrality: A Sociotope-Based Analysis of a Settlement Centre in a Polycentric Urban Region
The development of polycentric urban regions has strengthened the role of suburban settlements as secondary centres. However, centrality continues to be assessed primarily through the concentration of urban functions and amenities, while its social dimension remains insufficiently explored. This study extends the application of sociotope mapping from public open spaces to the assessment of social centrality in suburban settlement centres. The proposed framework was applied to Veternik, a suburban settlement within the urban region of Novi Sad in Serbia, combining functional and spatial analysis, a questionnaire survey, the Relative Importance Index, and GIS-based sociotope mapping. Functional and spatial analysis identified the existing urban functions, amenities, and their spatial organisation, while the questionnaire survey examined residents’ everyday patterns and frequency of centre-use activities. The Relative Importance Index ranked the relative importance of these activities, and GIS-based sociotope mapping visualised the resulting centre-use values. The findings indicate that Veternik exhibits relatively developed functional centrality, whereas its social centrality remains limited, particularly when considered in relation to users’ perceptions of the centre of Novi Sad. The study demonstrates the potential of sociotope mapping as a complementary framework for assessing social centrality and supporting the planning of socially sustainable suburban settlement centres.
- 17 September 2026
- Published by MDPI AG in Sustainability
- Vol. 18 (18) , 9561
Open AccessFrom Functional to Social Centrality: A Sociotope-Based Analysis of a Settlement Centre in a Polycentric Urban Region
The development of polycentric urban regions has strengthened the role of suburban settlements as secondary centres. However, centrality continues to be assessed primarily through the concentration of urban functions and amenities, while its social dimension remains insufficiently explored. This study extends the application of sociotope mapping from public open spaces to the assessment of social centrality in suburban settlement centres. The proposed framework was applied to Veternik, a suburban settlement within the urban region of Novi Sad in Serbia, combining functional and spatial analysis, a questionnaire survey, the Relative Importance Index, and GIS-based sociotope mapping. Functional and spatial analysis identified the existing urban functions, amenities, and their spatial organisation, while the questionnaire survey examined residents’ everyday patterns and frequency of centre-use activities. The Relative Importance Index ranked the relative importance of these activities, and GIS-based sociotope mapping visualised the resulting centre-use values. The findings indicate that Veternik exhibits relatively developed functional centrality, whereas its social centrality remains limited, particularly when considered in relation to users’ perceptions of the centre of Novi Sad. The study demonstrates the potential of sociotope mapping as a complementary framework for assessing social centrality and supporting the planning of socially sustainable suburban settlement centres.
- Open Access
- 1 January 2026
- Published by Centre for Evaluation in Education and Science (CEON/CEES) in Strategic Management
- Vol. 31 (1) , 30-51
An NLP approach to skill analysis in ICT job advertisements from a gender perspective
Background: The gender gap in the Information and Communication Technology (ICT) sector is strongly pronounced across Europe, including Serbia. Women are underrepresented in ICT education, entry positions, and throughout career trajectory. Although surveys and official statistics are commonly used to study gender disparities and skills in demand, job advertisements remain an underexplored organic data source in these studies. They can provide valuable insights into required hard and soft skills and a basis for measuring the influence of used language in job descriptions on gender distribution of applicants. Purpose: This paper investigates whether linguistic patterns and the framing of skill requirements in ICT job advertisements correlates with the gender distribution of applicants. The aim is to understand how specific wording or skill emphasis may differently attract male or female candidates. Study design/methodology/approach: Authors analyse 3,643 ICT job advertisements from Serbia with associated data on self-reported gender of applicants. Using a five-step methodology, the authors apply exploratory text analysis and natural language processing techniques, including n-gram analysis, feature engineering, and co-occurrence networks, to identify hard and soft skills patterns across maleand female-majority job postings. Findings/conclusions: The results offer insights into the language characteristics used in ICT job descriptions and gender-specific keywords reflecting hard and soft skills. Job advertisements that attract more male candidates use engineering-oriented terminology, such as programming and DevOps tools. In contrast, advertisements drawing more female candidates emphasise collaboration, teamwork, and emotional intelligence. Soft skills are more frequent in female-majority advertisements, while male-majority advertisements focus on narrower technical domains. Empirical findings suggest that how job advertisements frame requirements can reinforce gendered perceptions of role suitability. This has practical implications for human resource management and recruitment strategies in the ICT industry. Limitations/future research: Limitations include the use of percentage-based gender data and the evolving nature of the ICT labour market. Future research will expand the dataset, improve gender classification, and explore longitudinal trends to track changes over time.
- 1 January 2026
- Published by Centre for Evaluation in Education and Science (CEON/CEES) in Strategic Management
- Vol. 31 (1) , 30-51
Open AccessAn NLP approach to skill analysis in ICT job advertisements from a gender perspective
Background: The gender gap in the Information and Communication Technology (ICT) sector is strongly pronounced across Europe, including Serbia. Women are underrepresented in ICT education, entry positions, and throughout career trajectory. Although surveys and official statistics are commonly used to study gender disparities and skills in demand, job advertisements remain an underexplored organic data source in these studies. They can provide valuable insights into required hard and soft skills and a basis for measuring the influence of used language in job descriptions on gender distribution of applicants. Purpose: This paper investigates whether linguistic patterns and the framing of skill requirements in ICT job advertisements correlates with the gender distribution of applicants. The aim is to understand how specific wording or skill emphasis may differently attract male or female candidates. Study design/methodology/approach: Authors analyse 3,643 ICT job advertisements from Serbia with associated data on self-reported gender of applicants. Using a five-step methodology, the authors apply exploratory text analysis and natural language processing techniques, including n-gram analysis, feature engineering, and co-occurrence networks, to identify hard and soft skills patterns across maleand female-majority job postings. Findings/conclusions: The results offer insights into the language characteristics used in ICT job descriptions and gender-specific keywords reflecting hard and soft skills. Job advertisements that attract more male candidates use engineering-oriented terminology, such as programming and DevOps tools. In contrast, advertisements drawing more female candidates emphasise collaboration, teamwork, and emotional intelligence. Soft skills are more frequent in female-majority advertisements, while male-majority advertisements focus on narrower technical domains. Empirical findings suggest that how job advertisements frame requirements can reinforce gendered perceptions of role suitability. This has practical implications for human resource management and recruitment strategies in the ICT industry. Limitations/future research: Limitations include the use of percentage-based gender data and the evolving nature of the ICT labour market. Future research will expand the dataset, improve gender classification, and explore longitudinal trends to track changes over time.
- Open Access
- 29 January 2025
- Published by MDPI AG in Sustainability
- Vol. 17 (3) , 1109
Exploring Mobile Application User Experience Through Topic Modeling
Exploring user satisfaction and experience is the first step of software product improvement and business sustainability. The primary goal of this research is to investigate how companies can use topic modeling to understand mobile application user experience and offer methodological steps for identifying factors shaping it. SalesForce was selected for this case study as it was the most widely used CRM application in 2023. This study aims to uncover factors influencing positive and negative user experience, to compare and systematize them, and to indicate the business implications of topic modeling findings. For this study, authors collected 9081 online reviews of the SalesForce application from Google Play Store. The corpus is divided into three subsets based on the associated star ratings, where four and five stars indicate positive sentiment, three mixed sentiment, and two and one negative. Each subset is analyzed using the Latent Dirichlet Allocation algorithm, hyper-parameters were fine-tuned, and the experimental models were evaluated with coherence measures to determine the model with the optimal number of topics. The results indicate that the driving factors of positive experience are seamless functionality and reliability, design flaws and performance issues shape negative experiences, and mixed experiences arise from inconsistencies in usability and authentication challenges.
- 29 January 2025
- Published by MDPI AG in Sustainability
- Vol. 17 (3) , 1109
Open AccessExploring Mobile Application User Experience Through Topic Modeling
Exploring user satisfaction and experience is the first step of software product improvement and business sustainability. The primary goal of this research is to investigate how companies can use topic modeling to understand mobile application user experience and offer methodological steps for identifying factors shaping it. SalesForce was selected for this case study as it was the most widely used CRM application in 2023. This study aims to uncover factors influencing positive and negative user experience, to compare and systematize them, and to indicate the business implications of topic modeling findings. For this study, authors collected 9081 online reviews of the SalesForce application from Google Play Store. The corpus is divided into three subsets based on the associated star ratings, where four and five stars indicate positive sentiment, three mixed sentiment, and two and one negative. Each subset is analyzed using the Latent Dirichlet Allocation algorithm, hyper-parameters were fine-tuned, and the experimental models were evaluated with coherence measures to determine the model with the optimal number of topics. The results indicate that the driving factors of positive experience are seamless functionality and reliability, design flaws and performance issues shape negative experiences, and mixed experiences arise from inconsistencies in usability and authentication challenges.
- Open Access
- 1 January 2025
- Published by Centre for Evaluation in Education and Science (CEON/CEES) in Menadzment u hotelijerstvu i turizmu
- Vol. 13 (2) , 137-153
Topic modeling in hospitality and tourism research: Application areas, business insights, and managerial implications
Purpose - Topic modeling (TM) explores customer experience and behaviors from large volumes of textual data, such as online reviews uncovering (dis)satisfaction cues often overlooked by hospitality managers. Despite its potential, TM application in hospitality research is limited compared to other social science methods. This paper aims to investigate the scope of TM research in the hospitality domain and contribute to the understanding of the areas where it can be effectively applied, the purposes it can serve, and the types of problems it can address. Methodology - The research methodology is rooted in the systematic literature review - 40 relevant papers were collected and analysed to identify the areas of hospitality where TM is mostly applied, business insights derived from TM application, and commonly utilised TM approaches. Findings -TM research in hospitality is conducted in five research areas: accommodation and lodging, food and beverages, attractions and events, nature-based tourism, and travel services. Researchers apply TM to gain nine different business insights, such as dissatisfaction drivers, segment-based preferences, sentiments, preference changes over time, service quality perception, or underexplored areas. Implications - TM-based research provides actionable recommendations for the enhancement of managerial practices within the hospitality industry, such as promotion and destination management, service improvements, and reduction of overtourism.
- 1 January 2025
- Published by Centre for Evaluation in Education and Science (CEON/CEES) in Menadzment u hotelijerstvu i turizmu
- Vol. 13 (2) , 137-153
Open AccessTopic modeling in hospitality and tourism research: Application areas, business insights, and managerial implications
Purpose - Topic modeling (TM) explores customer experience and behaviors from large volumes of textual data, such as online reviews uncovering (dis)satisfaction cues often overlooked by hospitality managers. Despite its potential, TM application in hospitality research is limited compared to other social science methods. This paper aims to investigate the scope of TM research in the hospitality domain and contribute to the understanding of the areas where it can be effectively applied, the purposes it can serve, and the types of problems it can address. Methodology - The research methodology is rooted in the systematic literature review - 40 relevant papers were collected and analysed to identify the areas of hospitality where TM is mostly applied, business insights derived from TM application, and commonly utilised TM approaches. Findings -TM research in hospitality is conducted in five research areas: accommodation and lodging, food and beverages, attractions and events, nature-based tourism, and travel services. Researchers apply TM to gain nine different business insights, such as dissatisfaction drivers, segment-based preferences, sentiments, preference changes over time, service quality perception, or underexplored areas. Implications - TM-based research provides actionable recommendations for the enhancement of managerial practices within the hospitality industry, such as promotion and destination management, service improvements, and reduction of overtourism.
- Open Access
- 1 January 2025
- Published by Centre for Evaluation in Education and Science (CEON/CEES) in Ekonomika
- Vol. 71 (1) , 15-24
Analyzing user experience from negative reviews: The Salesforce case study
The mobile business represents a rapidly growing market where user experience has a crucial role in sustaining the business. Its evaluation has gained interest, both in industry and academia, as it directly affects user satisfaction and loyalty, thus, competitiveness and company revenue. This paper aims to point to the reach of topic modeling in user experience evaluation. It is an effective approach to identifying aspects considered negative by mobile application users, relevant as a guideline for product improvement. The authors demonstrate this in the SalesForce mobile application case study using topic modeling to analyze 2.501 user reviews collected from the Google Play Store. Research results indicate key shortcomings of the application: compatibility, unreliability, slow loading, and excessive notifications. The research presents an innovative approach to user experience analysis and offers practical solutions for improving the SalesForce mobile business application.
- 1 January 2025
- Published by Centre for Evaluation in Education and Science (CEON/CEES) in Ekonomika
- Vol. 71 (1) , 15-24
Open AccessAnalyzing user experience from negative reviews: The Salesforce case study
The mobile business represents a rapidly growing market where user experience has a crucial role in sustaining the business. Its evaluation has gained interest, both in industry and academia, as it directly affects user satisfaction and loyalty, thus, competitiveness and company revenue. This paper aims to point to the reach of topic modeling in user experience evaluation. It is an effective approach to identifying aspects considered negative by mobile application users, relevant as a guideline for product improvement. The authors demonstrate this in the SalesForce mobile application case study using topic modeling to analyze 2.501 user reviews collected from the Google Play Store. Research results indicate key shortcomings of the application: compatibility, unreliability, slow loading, and excessive notifications. The research presents an innovative approach to user experience analysis and offers practical solutions for improving the SalesForce mobile business application.
- 1 January 2024
- Published by Association of Economists and Managers of the Balkans - Udekom Balkan
- p. 291-311
A Comprehensive Analysis of Online Reviews in the Srem Region through Topic Modeling
This chapter employs topic modeling to reveal the public stance and perception of tourist destinations in the Srem region, providing insights into their diverse appeal and variety of tourist profiles. Social media is the touch point with visitors of tourist attractions and consumers of tourist services. The collection of online reviews of tourist attractions in the Srem region is populated and used for modeling the hidden thematic structures. The authors identified an optimal model with 14 distinct topics through extensive experimentation, centered around nature, relaxation, shrines, and museum history. The topics indicate various tourist profiles active, gastronomic, leisure-seeking, history-loving, and family-oriented tourists. Knowing about the audience is valuable for targeted marketing strategies. The authors extracted and analyzed subsets of reviews related to Monasteries, Museums, Nature, and Nature Reserves indicating specific preferences of tourists within these categories, such as historical relevance of museums, use of modern technologies in exhibitions, or children-friendly content in nature reserves, and improvement areas, such as condition of roads, control of forest cutting, or garbage disposal management. This research offers clearly defined methodological steps and valuable insights for marketing and tourism development in the Srem region.
- 1 January 2024
- Published by Association of Economists and Managers of the Balkans - Udekom Balkan
- p. 291-311
A Comprehensive Analysis of Online Reviews in the Srem Region through Topic Modeling
This chapter employs topic modeling to reveal the public stance and perception of tourist destinations in the Srem region, providing insights into their diverse appeal and variety of tourist profiles. Social media is the touch point with visitors of tourist attractions and consumers of tourist services. The collection of online reviews of tourist attractions in the Srem region is populated and used for modeling the hidden thematic structures. The authors identified an optimal model with 14 distinct topics through extensive experimentation, centered around nature, relaxation, shrines, and museum history. The topics indicate various tourist profiles active, gastronomic, leisure-seeking, history-loving, and family-oriented tourists. Knowing about the audience is valuable for targeted marketing strategies. The authors extracted and analyzed subsets of reviews related to Monasteries, Museums, Nature, and Nature Reserves indicating specific preferences of tourists within these categories, such as historical relevance of museums, use of modern technologies in exhibitions, or children-friendly content in nature reserves, and improvement areas, such as condition of roads, control of forest cutting, or garbage disposal management. This research offers clearly defined methodological steps and valuable insights for marketing and tourism development in the Srem region.
- Open Access
- 1 January 2024
- Published by Centre for Evaluation in Education and Science (CEON/CEES) in Anali Ekonomskog fakulteta u Subotici
- No. 52,p. 21-37
Application of artificial intelligence in digital marketing
Contemporary digital technologies have significantly influenced the transformation of marketing activities in companies over the past decade. Artificial intelligence is considered one of the most disruptive modern technologies. Their implementation is the most significant challenge of digital marketing. Artificial intelligence can automate customer service, generate content, and enable targeted ad campaigns. The problem identified by the authors is that smaller companies and entrepreneurs lack the necessary knowledge and understanding of artificial intelligence techniques that could enhance digital marketing strategies. By reviewing current literature, this paper aims to explain the digital marketing strategies and the role and place of various artificial intelligence techniques for their improvement. In line with the defined goal, the paper presents three case studies on industry giants - Coca-Cola, Starbucks, and Nike - illustrating successful implementations of artificial intelligence and machine learning techniques in their digital marketing.
- 1 January 2024
- Published by Centre for Evaluation in Education and Science (CEON/CEES) in Anali Ekonomskog fakulteta u Subotici
- No. 52,p. 21-37
Open AccessApplication of artificial intelligence in digital marketing
Contemporary digital technologies have significantly influenced the transformation of marketing activities in companies over the past decade. Artificial intelligence is considered one of the most disruptive modern technologies. Their implementation is the most significant challenge of digital marketing. Artificial intelligence can automate customer service, generate content, and enable targeted ad campaigns. The problem identified by the authors is that smaller companies and entrepreneurs lack the necessary knowledge and understanding of artificial intelligence techniques that could enhance digital marketing strategies. By reviewing current literature, this paper aims to explain the digital marketing strategies and the role and place of various artificial intelligence techniques for their improvement. In line with the defined goal, the paper presents three case studies on industry giants - Coca-Cola, Starbucks, and Nike - illustrating successful implementations of artificial intelligence and machine learning techniques in their digital marketing.
- 1 November 2020
- Published by Taylor & Francis in Enterprise Information Systems
- Vol. 16 (5)
Opinion mining in higher education: a corpus-based approach
Student recruitment and retention heavily depend on student satisfaction and word of mouth voiced through surveys, social media, and review websites. The amount of online reviews makes their manual analysis intractable, revealing the need for automated approaches. The paper presents the first Serbian language corpus manually annotated for opinions in the domain of higher education. Agreement among annotators was calculated using the Fleiss’ kappa and agr metrics. Statistical and linguistic analyses of the corpus revealed information useful for hand-crafted rules for sentiment analysis. Using developed corpus, dictionary- and machine learning-based approaches to sentiment analysis are benchmarked. Both exhibit high performance.
- 1 November 2020
- Published by Taylor & Francis in Enterprise Information Systems
- Vol. 16 (5)
Opinion mining in higher education: a corpus-based approach
Student recruitment and retention heavily depend on student satisfaction and word of mouth voiced through surveys, social media, and review websites. The amount of online reviews makes their manual analysis intractable, revealing the need for automated approaches. The paper presents the first Serbian language corpus manually annotated for opinions in the domain of higher education. Agreement among annotators was calculated using the Fleiss’ kappa and agr metrics. Statistical and linguistic analyses of the corpus revealed information useful for hand-crafted rules for sentiment analysis. Using developed corpus, dictionary- and machine learning-based approaches to sentiment analysis are benchmarked. Both exhibit high performance.
- 25 June 2020
- Published by Walter de Gruyter GmbH in Poznan Studies in Contemporary Linguistics
- Vol. 56 (2) , 207-249
The linguistic construction of sentiment expressions in student opinionated content: A corpus-based study
Motivated by an increasing use of social media for the expression of personal stance towards a certain target, we analyse the language used to produce such opinionated content with expressions of sentiment, which represents the main data source for sentiment analysis. We use the first manually annotated corpus for sentiment analysis of the Serbian language developed for the service sector of higher education. Our study focuses on how various linguistic constructions, used in different context, influence the sentiment polarity of a text. Our findings indicate that sentiment expressions and negation have a most significant role in determining whether the text conveys positive, neutral, or negative sentiment, while intensifiers (words which either increase or decrease sentiment) have a considerable influence on sentiment intensity. We also present an analysis of the impact of conjunctions, conditional sentences, comparative and modal verbs, and pronouns on sentiment polarity and intensity. Based on the derived observations, we propose a set of rules that could be integrated with machine learning algorithms into an automated sentiment analysis system for the Serbian language. Our findings also make a much-needed contribution to the few currently available resources for natural language processing of Serbian.
- 25 June 2020
- Published by Walter de Gruyter GmbH in Poznan Studies in Contemporary Linguistics
- Vol. 56 (2) , 207-249
The linguistic construction of sentiment expressions in student opinionated content: A corpus-based study
Motivated by an increasing use of social media for the expression of personal stance towards a certain target, we analyse the language used to produce such opinionated content with expressions of sentiment, which represents the main data source for sentiment analysis. We use the first manually annotated corpus for sentiment analysis of the Serbian language developed for the service sector of higher education. Our study focuses on how various linguistic constructions, used in different context, influence the sentiment polarity of a text. Our findings indicate that sentiment expressions and negation have a most significant role in determining whether the text conveys positive, neutral, or negative sentiment, while intensifiers (words which either increase or decrease sentiment) have a considerable influence on sentiment intensity. We also present an analysis of the impact of conjunctions, conditional sentences, comparative and modal verbs, and pronouns on sentiment polarity and intensity. Based on the derived observations, we propose a set of rules that could be integrated with machine learning algorithms into an automated sentiment analysis system for the Serbian language. Our findings also make a much-needed contribution to the few currently available resources for natural language processing of Serbian.
- 27 January 2020
- Published by Emerald Publishing in The Electronic Library
- Vol. 38 (1) , 44-64
Aspect-based sentiment analysis of reviews in the domain of higher education
Purpose: Student recruitment and retention are important issues for all higher education institutions. Constant monitoring of student satisfaction levels is therefore crucial. Traditionally, students voice their opinions through official surveys organized by the universities. In addition to that, nowadays, social media and review websites such as “Rate my professors” are rich sources of opinions that should not be ignored. Automated mining of students’ opinions can be realized via aspect-based sentiment analysis (ABSA). ABSA s is a sub-discipline of natural language processing (NLP) that focusses on the identification of sentiments (negative, neutral, positive) and aspects (sentiment targets) in a sentence. The purpose of this paper is to introduce a system for ABSA of free text reviews expressed in student opinion surveys in the Serbian language. Sentiment analysis was carried out at the finest level of text granularity – the level of sentence segment (phrase and clause). Design/methodology/approach: The presented system relies on NLP techniques, machine learning models, rules and dictionaries. The corpora collected and annotated for system development and evaluation comprise students’ reviews of teaching staff at the Faculty of Technical Sciences, University of Novi Sad, Serbia, and a corpus of publicly available reviews from the Serbian equivalent of the “Rate my professors” website. Findings: The research results indicate that positive sentiment can successfully be identified with the F-measure of 0.83, while negative sentiment can be detected with the F-measure of 0.94. While the F-measure for the aspect’s range is between 0.49 and 0.89, depending on their frequency in the corpus. Furthermore, the authors have concluded that the quality of ABSA depends on the source of the reviews (official students’ surveys vs review websites). Practical implications: The system for ABSA presented in this paper could improve the quality of service provided by the Serbian higher education institutions through a more effective search and summary of students’ opinions. For example, a particular educational institution could very easily find out which aspects of their service the students are not satisfied with and to which aspects of their service more attention should be directed. Originality/value: To the best of the authors’ knowledge, this is the first study of ABSA carried out at the level of sentence segment for the Serbian language. The methodology and findings presented in this paper provide a much-needed bases for further work on sentiment analysis for the Serbian language that is well under-resourced and under-researched in this area.
- 27 January 2020
- Published by Emerald Publishing in The Electronic Library
- Vol. 38 (1) , 44-64
Aspect-based sentiment analysis of reviews in the domain of higher education
Purpose: Student recruitment and retention are important issues for all higher education institutions. Constant monitoring of student satisfaction levels is therefore crucial. Traditionally, students voice their opinions through official surveys organized by the universities. In addition to that, nowadays, social media and review websites such as “Rate my professors” are rich sources of opinions that should not be ignored. Automated mining of students’ opinions can be realized via aspect-based sentiment analysis (ABSA). ABSA s is a sub-discipline of natural language processing (NLP) that focusses on the identification of sentiments (negative, neutral, positive) and aspects (sentiment targets) in a sentence. The purpose of this paper is to introduce a system for ABSA of free text reviews expressed in student opinion surveys in the Serbian language. Sentiment analysis was carried out at the finest level of text granularity – the level of sentence segment (phrase and clause). Design/methodology/approach: The presented system relies on NLP techniques, machine learning models, rules and dictionaries. The corpora collected and annotated for system development and evaluation comprise students’ reviews of teaching staff at the Faculty of Technical Sciences, University of Novi Sad, Serbia, and a corpus of publicly available reviews from the Serbian equivalent of the “Rate my professors” website. Findings: The research results indicate that positive sentiment can successfully be identified with the F-measure of 0.83, while negative sentiment can be detected with the F-measure of 0.94. While the F-measure for the aspect’s range is between 0.49 and 0.89, depending on their frequency in the corpus. Furthermore, the authors have concluded that the quality of ABSA depends on the source of the reviews (official students’ surveys vs review websites). Practical implications: The system for ABSA presented in this paper could improve the quality of service provided by the Serbian higher education institutions through a more effective search and summary of students’ opinions. For example, a particular educational institution could very easily find out which aspects of their service the students are not satisfied with and to which aspects of their service more attention should be directed. Originality/value: To the best of the authors’ knowledge, this is the first study of ABSA carried out at the level of sentence segment for the Serbian language. The methodology and findings presented in this paper provide a much-needed bases for further work on sentiment analysis for the Serbian language that is well under-resourced and under-researched in this area.