Papers by Olivera Grljevic
JWEE
Information and Communication Technology (ICT) sector in Serbia is fast growing and in constant h... more Information and Communication Technology (ICT) sector in Serbia is fast growing and in constant high demand for qualified workforce. In order to continuously fulfil the demand, the National strategy for gender equality defined as one of the actions, requalification of the unemployed women for different ICT profiles. Investing in education is the policy of creating human capital that influences the overall development of the society. Women empowerment through education is recognized as one of the prerequisite for sustainable ICT workforce generation. Data science represents particularly important field of ICT which is still in its development phase in Serbia. All industries with transaction-based processes and industries that use connected or mobile devices or similar, which generate high volumes of data on a daily bases can benefit from application of data science in terms of increased profits and ROI. While developing data science in Serbia and during the peak of productivity in th...
International Thematic Monograph. Modern Management Tools and Economy of Tourism Sector in Present Era, 2019
Online reviews posted on social media are a rich source of the customers' voice. In this chapter,... more Online reviews posted on social media are a rich source of the customers' voice. In this chapter, online reviews about various tourism destinations and attractions in Srem/Srijem region are used to analyze public stance and to uncover sources of satisfaction and dissatisfaction of visitors. Online reviews as unstructured data cannot be directly used for analysis, but require extensive data transformation and preparation which is done through annotation of data. Annotation is a process of enrichment of texts with specific meta-data. In presented research during the annotation process, the dataset, i.e. the corpus of collected reviews was labeled with information on sentiment, aspects, discourse functions, and information on a function different words have in expressions of opinion, sentiment or attitude within a review. The authors present their approach to annotation, the evaluation of the quality of conducted work, as well as the analysis of the resulting dataset, i.e. annotated corpus.
Travelers nowadays express their opinions, feelings, or (dis)satisfaction on the Web through revi... more Travelers nowadays express their opinions, feelings, or (dis)satisfaction on the Web through reviews and ratings of hotels, restaurants, or other travel-related entities and services. The paper proposes a novel approach to determining the sentiment orientation of reviews with attached average numerical ratings, which usually convey both positive and negative sentiment. It is shown that the analysis and comparison of subsets of reviews with the same attached mark in terms of writing style and vocabulary can significantly reduce the size of reviews with biased sentiment polarity.
International Conference on Information Society, 2014
Human capital provides organizations the ability and readiness for adaption to turbulent changes ... more Human capital provides organizations the ability and readiness for adaption to turbulent changes in the business environment. Human resources are the only active and creative part of work process. For this reason, the strategy of human resources development is one of the most important segments of the strategy of organization development. Organizations can improve their business performance by developing analytical systems. Using the analytical systems, organizations are able to continuously measure and assess its performance, take corrective actions and provide stabile position in today's competitive environment. The system should enable easy and efficient monitoring and analysis of data. Comparing planned values with actual achievements of management, organizations can identify critical points in terms of achieving the goals. This paper will present a theoretical and methodological foundation of human resource management, and describe developed OLAP analytical solution for human resource management performance measurement and evaluation. I.
Strategic management, 2018
The value of а customer for the company is not measured only by the monetary effect, but also by ... more The value of а customer for the company is not measured only by the monetary effect, but also by the degree of its satisfaction. Satisfied customers spread positive word of mouth, while dissatisfied customers spread negative one (in online or offline environment). Their voice shapes company reputation and the reputation is one of the key parameters in choosing a product, service, or a company. In order to look into customer satisfaction, companies need to get certain feedback from consumers. The traditional way of collecting feedback from consumers is questionnaires. However, the way in which consumers express their opinions on social media opens up new opportunities and makes it easier for companies to cover a larger number of consumers, to collect data of interest and to continuously monitor the brand. Social media sites have significantly changed the nature of human activities, interactions and ways of disseminating information. Consumer behavior has changed accordingly. In search for information about products and services consumers are planning to buy or use, offline sources of information are increasingly replaced with online sources and e-WoM. Before making a purchase decision, consumers visit many sites and read the content and comments that other users have generated. Within these contents-texts that users voluntarily post on the Internet and make it publicly available-users freely express their views, opinions, describe their consumer experience, the problems they have encountered and the way in which the problems were addressed, they point to the aspects of products or services they are satisfied or dissatisfied with. These contents shape the opinions of future consumers in great extent and affect their consumer actions. Numerous studies have confirmed the impact these sources have on consumer behavior: • Consumers appreciate opinions of other individuals and trust them more than the company's promotional campaigns, • Consumers have equal trust in online comments and reviews as in personal recommendations from friends, • Online comments on products and services are on the third place according to the influence on buying decisions (after coupons and discounts). Each business can benefit from analysis of social media content since it comprises useful feedback from consumers in form of expressed opinions and attitudes. Opinions and attitudes are extremely subjective. Due to subjectivity it is necessary to analyze a collection of opinions of different people instead of a single opinion which expresses a subjective view of an individual. In addition to this large number of available sources, the amount of data makes it impossible to manually process them and identify the general pattern, problem or source of (dis)satisfaction. Hence, automated analysis of unstructured content from social media sites is required, i.e. the application of sentiment analysis or opinion mining. Sentiment analysis is a young research area which has rapidly developed during the past 10 years and it has achieved significant commercialization. The surrounding industries also experienced significant expansion. Sentiment analysis allows companies to analyze public opinion, attitudes and emotions directed at a particular entity (e.g. a particular person, a political candidate, a party, a law, a company, a specific product, or a product feature) which expresses particular sentiment or points to (usually positive, negative or neutral), as well as all variations and gradations of the sentiment. In addition to the significance of sentiment analysis for business, this paper deals with sentiment analysis process and underlying data mining techniques.
Enterprise Information Systems, Nov 1, 2020
Student recruitment and retention heavily depend on student satisfaction and word of mouth voiced... more 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.
The Electronic Library, Feb 3, 2020
Purpose-Student recruitment and retention are important issues for all higher education instituti... more 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 granularitythe 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 Results presented in this paper are a part of the research conducted within the grants III-47003 and III-44010 provided by the Ministry of Education and Science of the Republic of Serbia.
Ekonomika preduzeća, 2020
The Role of Knowledge-Based Technologies and Big Data Analytics in a Pandemic
The covid-19 pandemic has caused major turmoil in economic, social, societal, and health systems ... more The covid-19 pandemic has caused major turmoil in economic, social, societal, and health systems around the world. In order to bring it under control, large amounts of relevant data have been identified and collected, the analysis of which should enable understanding of the character and mechanisms of the disease and, based on that knowledge, suppress pandemics and return life to normal as soon as possible. The volume of collected data is enormous, and the sources and types are very different, so classical analytical approaches are not suitable for their processing, while intelligent software solutions and tools for big data analysis play a vital role in discovering the knowledge needed to make decisions. Over the past two years, there has been a wider use of artificial intelligence and big data analytics in both e-commerce and online shopping. The need for social distancing, lockdowns, and work from home has resulted in the sudden shift of business to the digital sphere, especially trade. The processing of data that is continuously generated through online activities represents a huge opportunity for companies, but also a new challenge to find a way to turn data into useful information, insights, and knowledge that can be applied in practice. The paper describes modern information technologies that best suit the newly created conditions due to the pandemic. The solutions described in the literature are presented, which, in response to the new reality due to the covid-19 pandemic, were created using these technologies.
Economic Themes, 2020
The focus of the paper is on identification of hidden patterns in the opinion of accounting profe... more The focus of the paper is on identification of hidden patterns in the opinion of accounting professionals, in order to identify the deficiencies in the legal accounting regulations and to examine their perspective on international and legal accounting regulations. The data collected through the questionnaire was divided using clustering data mining technique. We identified different groups of accountants with specific patterns regarding the expressed attitudes towards both regulations, as well as different groups of accountants with specific patterns regarding the way of obtaining information. The findings point to the prevailing negative attitude towards the legal accounting regulations quality, and differences in the habits and attitudes of certified and non-certified accountants, i.e. accountants who (don’t) use International Financial Reporting Standards. Since there are four developed models, we used them as a basis for proposing a model of information seeking that could mitiga...
Development of Creditworthiness Expert System
Combining Different Clustering Techniques for Improved Knowledge Discovery
Application of different clustering techniques can result in different basic data set partitions ... more Application of different clustering techniques can result in different basic data set partitions emphasizing diversified aspects of resulting clusters. Since analysts have a great responsibility for the successful interpretation of the results obtained through some of the available tools, and for giving meaning to what forms a qualitative set of clusters, additional information attained from different tools is of a great use to them. In this article we presented the clustering results of small and medium sized enterprises' (SMEs) data, obtained in DataEngine, iData Analyzer and Weka tools for intelligent analysis.
The linguistic construction of sentiment expressions in student opinionated content: A corpus-based study
Poznan Studies in Contemporary Linguistics, 2020
Motivated by an increasing use of social media for the expression of personal stance towards a ce... more 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 intens...
Anali Ekonomskog fakulteta u Subotici, 2018
Facta Universitatis, Series: Economics and Organization, 2019
Knowing what attracts or deters tourists to/from a tourist visit and what products to offer them ... more Knowing what attracts or deters tourists to/from a tourist visit and what products to offer them and to pay special attention to is crucial for good economic results. Such knowledge can be obtained by analysis of online comments and reviews that tourists leave on travel websites (such as Booking, TripAdvisor, Trivago, etc.). This paper describes the value which information about opinions and emotions hidden in online reviews has for managers who receive it, especially the knowledge of (dis)satisfaction of users with certain aspects of the tourist offer. Uncovered knowledge from online reviews provides a chance to take advantage of the strong points, and correct the shortcomings through timely corrective measures and actions. Contemporary approaches and methods of analyzing online reviews and the opportunities for development they provide in the tourism industry are described through a case study conducted over a subset of 20491 hotel reviews from TripAdvisor. We have conducted senti...
Document represents supplementary material of the paper entitled "Opinion Mining in Higher E... more Document represents supplementary material of the paper entitled "Opinion Mining in Higher Education: A Corpus-Based Approach" published in Enterprise Information System, special issue The Artificial Intelligence-enabled Enterprise Information Systems. It summarizes statistical and linguistic analysis of annotated corpus in domain of online reviews of higher education. Linguistic and statistical analysis were performed in order to provide an in-depth insight into the structure of the corpus. Our detail observations are given in this document.
Social Media Analytics in Higher Education and Challenges
SGEM2014 1 International Multidisciplinary Scientific GeoConference, 2014
Development of Serbian higher education corpus
2015 16th IEEE International Symposium on Computational Intelligence and Informatics (CINTI), 2015
Students' behavior on social media sites — A data mining approach
2013 IEEE 11th International Symposium on Intelligent Systems and Informatics (SISY), 2013
ABSTRACT Data preparation is crucial for the validity of the resulting data model and its subsequ... more ABSTRACT Data preparation is crucial for the validity of the resulting data model and its subsequent successful application. The paper presents a preprocessing of the data on the behavior of students on social media sites using the CRISP-DM methodology. Data was collected through questioner shared among prospect students of Faculty of Economics Subotica. This has created an adequate platform for the implementation of different intelligent methods. This paper illustrates the application of clustering techniques to these data in order to identify specific profiles and patterns of student behavior on social media sites.
Utilization of Internet Social Media Sites: Students’ Perspective
CBU International Conference Proceedings, 2014
Uploads
Papers by Olivera Grljevic