Ivan Dunđer

Prof. Dr. Ivan Dunđer

Department of Information and Communication Sciences, University of Zagreb, Zagreb, Croatia

Research Focus & Metrics

Academic Career Length

12Years (2015-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
6 April 2023 in Information
Verified
Journal Article
Open access
PDF file
RJRafał Tomasz Jaworski
Rafał Tomasz Jaworski
SSSanja Seljan
Sanja Seljan
IDIvan Dunđer
Ivan Dunđer
Parallel corpora have been widely used in the fields of natural language processing and translation as they provide crucial multilingual information. They are used to train machine translation systems, compile dictionaries, or generate inter-language word embeddings. There are many corpora available publicly; however, support for some languages is still limited. In this paper, the authors present a framework for collecting, organizing, and storing corpora. The solution was originally designed to obtain data for less-resourced languages, but it proved to work very well for the collection of high-value domain-specific corpora. The scenario is based on the collective work of a group of people who are motivated by the means of gamification. The rules of the game motivate the participants to submit large resources, and a peer-review process ensures quality. More than four million translated segments have been collected so far.

2 June 2025 in Electronics
Verified
Journal Article
Open access
PDF file
JKJosip Katalinić
Josip Katalinić
IDIvan Dunđer
Ivan Dunđer
During crises, people use X to share real-time updates. These posts reveal public sentiment and evolving emergency situations. However, the changing sentiment in tweets coupled with anomalous patterns may indicate significant events, misinformation or emerging hazards that require timely detection. By using a neural network, and employing deep learning techniques for crisis observation, this study proposes a pipeline for sentiment analysis and anomaly detection in crisis-related tweets. The authors used pre-trained BERT to classify tweet sentiment. For sentiment anomaly detection, autoencoders and recurrent neural networks (RNNs) with an attention mechanism were applied to capture sequential relationships and identify irregular sentiment patterns that deviate from standard crisis talk. Experimental results show that neural networks are more accurate than traditional machine learning methods for both sentiment categorization and anomaly detection tasks, with higher precision and recall for identifying sentiment shifts in the public. This study indicates that neural networks can be used for crisis management and the early detection of significant sentiment anomalies. This could be beneficial to emergency responders and policymakers and support data-driven decisions.

23 October 2024 in Electronics
Verified
Journal Article
Open access
PDF file
JKJosip Katalinić
Josip Katalinić
IDIvan Dunđer
Ivan Dunđer
SSSanja Seljan
Sanja Seljan
The perception of nuclear power, while central to energy policy and sustainability endeavors, remains a subject of considerable debate, in which some claim that the expansion of nuclear technology poses threats to global security, while others argue that its access should be shared for development and energy purposes. In this study, a total of 11,256 tweets were gathered over a three-month period using a keyword-based approach through the Twitter Standard Search API, focusing on terms related to nuclear energy. The k-means clustering algorithm was employed to analyze tweets with the aim of determining the underlying sentiments and perspectives within the public domain, while t-SNE was used for visualizing cluster separation. The results show distinct clusters reflecting various viewpoints on nuclear power, with 71.94% of tweets being neutral, 14.64% supportive, and 13.42% negative. This study also identifies a subset of users who appear to be seeking unbiased information, signaling an opportunity for educational outreach. By leveraging the immediacy and pervasiveness of X (formerly known as Twitter), this research provides a timely snapshot of the prevailing attitudes toward nuclear power and offers insights for policymakers, educators, and industry stakeholders.

10 November 2023 in Information
Verified
Journal Article
Open access
PDF file
JKJosip Katalinić
Josip Katalinić
IDIvan Dunđer
Ivan Dunđer
SSSanja Seljan
Sanja Seljan
Politically polarizing issues are a growing concern around the world, creating divisions along ideological lines, which was also confirmed during the 2022 United States midterm elections. The purpose of this study was to explore the relationship between the results of the 2022 U.S. midterm elections and the topics that were covered during the campaign. A dataset consisting of 52,688 tweets in total was created by collecting tweets of senators, representatives and governors who participated in the elections one month before the start of the elections. Using unsupervised machine learning, topic modeling is built on the collected data and visualized to represent topics. Furthermore, supervised machine learning is used to classify tweets to the corresponding political party, whereas sentiment analysis is carried out in order to detect polarity and subjectivity. Tweets from participating politicians, U.S. states and involved parties were found to correlate with polarizing topics. This study hereby explored the relationship between the topics that were creating a divide between Democrats and Republicans during their campaign and the 2022 U.S. midterm election outcomes. This research found that polarizing topics permeated the Twitter (today known as X) campaign, and that all elections were classified as highly subjective. In the Senate and House elections, this classification analysis showed significant misclassification rates of 21.37% and 24.15%, respectively, indicating that Republican tweets often aligned with traditional Democratic narratives.

30 June 2015
Verified
Conference Paper
Open access
SLSergej Lugovic
Sergej Lugovic
IDIvan Dunđer
Ivan Dunđer
Marko HorvatMarko Horvat
Marko Horvat
Introduction Humanity evidences major social, technological, economic and cultural transformations producing a new kind of society: network society [1]. Such an environment is described as turbulent, and is more complex, with higher uncertainty and with more interdependence. In such contextual turbulent environment, technocratic bureaucracies, with its mechanical authoritarian control structure of the organisational form, cannot absorb or reduce such environmental turbulence. The absorption and reduction are necessary, opening the way to a viable human future [2]. Information systems can be understood as the “extension of meaning engagement practice through mediating and organising social interactions” [3]. Empirical evidence of such a proposition can be found in a recent massive-scale experiment on Facebook users in which the emotional state of the user changed accordingly to the amount of positive or negative content in their news feed placed without their acknowledgment [4]. Besides emotions, patterns of the information system use can configure cognition and behaviour of a user in the process of accomplishing work-related tasks [5]. If an information system consists of social, technological and informational components, which are not separate but interrelated [6], and the social component of such a system changes according to patterns of behaviour, whereas there is an inherent inseparability between the technical and the social [7], can we search for causality between those patterns and adaptiveness of the information technology? Human and material agencies are shared building blocks of routines and technologies, but by being isolated, neither of them (human or material agencies) are important. Namely, what is essential is the moment when they become imbricated, i.e. interlocked in a particular sequence, and as a whole they produce, sustain, or change routines and technologies [8]. To observe this phenomenon and to find an answer to the aforementioned question, the particular sequence of the relationship between human and material agencies, the inherent inseparability between the technical and the social, and the complexity of real situations should be examined, rather than analysing separate aspects [9]. Science 2.0 as a socio-technical system In a recent proposal for development of science based on socio-technical progress, the term Science 2.0 emerged as a new phenomenon of interrelated socio-technical interactions, claiming that socio-technical systems are best studied at scale, in the real world, by rigorous observation, carefully chosen interventions and ambitious data collections [10]. In such an environment, which is fruitful for critiquing, suggesting, sharing ideas and data, communication is the heart of science, the most powerful tool ever invented for correcting errors, building on colleagues’ work and fashioning new knowledge [11]. To understand technology in society, we have to treat it as an action system, where its subfunctions could be performed by humans or technical objects (human or material agencies) acting as subsystems. This allows us to transform the abstract action system into a socio-technical system by conceiving an object for every suitable acting function and by integrating them into the human acting or working relations [9]. Software to be run on such a socio-technical system must be able to sense, interpret and respond [12] to patterns of system behaviour that emerge according to internal system properties or reflections to the environment. Secondary experience research The aim of this research is to investigate and eventually enable the exchange and (re)use of scientific papers created on the universities in the Danube region with their wider external environment including public, private and non-governmental organisations. Scientists working at the universities publish scientific papers and get the papers’ reflection according to the usage of the outside environment including public, private and non-governmental organisations. The main research question is, can we build an artefact in form of an information system that supports such an exchange and reflection? In a critical review of the literature related to university governance of knowledge transfer, institutionalisation of linkage between universities and industry is defined as a new phenomenon, underlying various forms of knowledge transfer activities, ranging from collaborative research projects involving universities and companies (e.g. research contracts), intellectual property rights and spin-offs, labour and student mobility, consultancy etc., as well as “soft” forms of knowledge transfer, such as attendance at conferences and creation of electronic networks. Universities’ governance of knowledge transfer applies only to research contracts, intellectual property rights and spin-offs, but most university knowledge is transferred via traditional channels such as personnel exchanges, publishing, consulting and conferences. However, these types of knowledge transfer activities have not been institutionalised and little attention has been paid to their management and governance [13]. We believe that an intervention into this area by designing an adaptive information system could extend the capabilities of human and material agencies. As a starting point for the conceptualisation of our research, we use primary and secondary experience proposed by John Dewey. The primary experience is the one with “minimum of incidental reflection”, while secondary experience is described as “what is experienced in consequence of continued and regulated reflective inquiry... experienced only because of the intervention of systematic thinking”. Dewey contrasted two different kinds of experience, primary and secondary, proposing that objects in secondary experience “get the meaning contained in a whole system of related objects; they are rendered continuous with the rest of nature and take on the import of the things they are now seen to be continuous with” [14]. In our view, the primary object in designing an information system is the one in which the observed object is excluded from the context with other objects, while secondary objects are those objects which are observed as a part of the higher-level system, consisting of the object itself and its relationships and behaviour in interaction with other related objects. Such a higher-level system includes an information system itself, but also its users and their information behaviour observed as a whole. To design such an information system, we have to understand the information behaviour in socio-technical systems consisting of technologies that support the interaction between scientists, organisations they are working for, and published papers. The environment consists of public, private and non-governmental organisations. Those three sectors together with the academic actors create a Quad Model [15] or Quadruple Helix [16] creating a framework for EU Digital Agenda for Europe in which government, industry, academia and civil participants work together [17]. To do so we have to extend our research not only to the design of the information system, but also towards the information behaviour research in such a socio-technical system. We have to research what type of information resource (e.g. abstract, full paper etc.), and what type of media (e.g. scientific journal, conference proceedings, web pages etc.), are being utilised, but also what are the patterns of information seeking behaviour in the process of accessing information resources. Those three research variables (type of information resources, type of communication channels and information seeking patterns) will provide us with insight into the phenomena of impact and usage of already published scientific papers by their environment (public, private and NGO). Such an insight is essential for the design of such an artefact, i.e. information system. Another research inquiry is the area of interaction, or precisely speaking, what are the motivation drivers and factors that influence the interaction between scientists and their environment. If we understand the motivation drivers and factors that influence interaction, we can implement them into the design of an information system. But we cannot know the effect of such functions in the information system, unless we incorporate them and put them into use. Theoretical background of research Main theoretical background of this research is in the Activity theory [18], describing the three-way relationship between a person (the subject), an object, to which an activity is directed, and the tools or instruments used in the activity. A further theoretical extension is in different models of information behaviour [19], which will provide us with the framework for collecting data about the usage of already published scientific papers existing in the area of interaction between universities, public, private and NGO organisations. In our research we will use the Documents of Action concept [20], which gives us an analytical framework to analyse usage, interaction and co-operations around already published scientific papers. Another theoretical concept used in this research is Evolutionary Learning [21], suggesting that sustainability requires collaboration among governments, businesses and civil society. A clear distinction was made between growth, development and evolution, where growth is the increase in size or quantity, development is an amelioration of conditions or quality, and evolution is a tendency towards greater structural complexity and organisational simplicity, more efficient modes of operation and greater dynamic harmony. Another theoretical contribution to this research is based on knowledge sharing communities [22] and communities of action [23] providing us with detailed frameworks for an information system functionality that supports both, social and technical, aspects of information behaviour. Also different social cybernetic concepts about self-organisation, self-reference, self-steering, autocatalysis and cross-catalysis and autopoiesis [24] will be used in researching feedback between the information system and its users. This proposed research also contributes to the discipline of information system design science [25-27] and contributes to the extended definition of the information system, seen as an artefact which consists of information, social and technical elements, creating a whole which is greater than the sum of its parts [6]. Conclusion We evidence a trend of blurring the line between technological and social in information system research, moving the focus from deterministic to more casual logic in their design. Main aim of our research is to search for feedback from users’ socio-cognitive behaviour that could be used as a signal that triggers information system adaption. One of the theoretical fields we are currently exploring is information behaviour, which results in patterns of that behaviour. As the dynamic of patterns is observable by a machine, we believe that there is a possibility to use this signal to automatically (or semi-automatically) trigger restructuring of the information system, to generate new functions to support existing and create new information system goals. We perceive an information system as a system consisting of informational, social and technological components acting as a whole, and that is aligned with findings from related theoretical and empirical studies presented in this paper. Those components interact between each other and such an interaction, which is not only deterministic but casual, could provide fundaments for adaptive information systems which evolve along their usage. Researching interaction around scientific papers by universities, public, private and non-governmental organisations could provide us with valuable information on where and how to intervene in such a system. Building an artefact in form of an information system for the purpose of the research could provide us with empirical insights which of the interventions and interactions give optimal results in terms of information system performance. For example, if we knew what types of documents have the most impact on the environment and trigger the cognitive, communicative and co-operation processes [28] (with public, private, non-governmental organisations), we could further design amplification towards this area of the system which could then produce change in dynamics of information behaviour and related patterns. New patterns will open up new areas of research interests, which then again could be amplified or attenuated. In that way we could design feedback loops in the information system which could enable deterministic but also casual properties. References and Notes Castells, M. The rise of the network society: The information age: Economy, society, and culture, 2nd ed.; Volume 1; John Wiley & Sons: Hoboken (NJ), USA, 2011; p. 17. Trist, E.L.; The evolution of socio-technical systems; Quality of Working Life Centre: Toronto, Canada; 1981; p. 39. Aakhus, M.; Agerfalk, P.J.; Lyytinen, K.; Te'eni, D. Symbolic Action Research in Information Systems: Introduction to the Special Issue. MIS Quarterly 2014, 38(4), 1187-1200. Kramer, A.D.; Guillory, J.E.; Hancock, J.T. Experimental evidence of massive-scale emotional contagion through social networks. Proceedings of the National Academy of Sciences of the United States of America 2014, 111(24), 8788–8790. Ortiz de Guinea, A.; Webster, J. An Investigation of Information Systems Use Patterns: Technological Events as Triggers, the Effect of Time, and Consequences for Performance. MIS Quarterly 2013, 37(4), 1165-1188. Lee, A.S.; Thomas, M.A.; Baskerville, R.L. Going back to basics in design: From the IT artifact to the IS artifact. Proceedings of the Nineteenth Americas Conference on Information Systems 2013, 1757-1763. Orlikowski, W.J.; Scott, S.V. Sociomateriality: challenging the separation of technology, work and organization. The academy of management annals 2008, 2(1), 433-474. Leonardi, P.M. When flexible routines meet flexible technologies: Affordance, constraint, and the imbrication of human and material agencies. MIS Quarterly 2011, 35(1), 147-167. Ropohl, G. Philosophy of Socio-Technical Systems. Techné: Research in Philosophy and Technology 1999, 4(3), 186-194. Shneiderman, B. Computer science. Science 2.0. Science 2008, 319(5868), 1349-1350. Waldrop, M.M. Science 2.0. Scientific American 2008, 298(5), 68-73. Stock, G. Metaman: The merging of humans and machines into a global superorganism. New York: Simon and Schuster, recited from; Hofkirchner, W. (2007). A critical social systems view of the internet. Philosophy of the Social Sciences 1993, 37(4), 471-500. Geuna, A., Muscio, A. The governance of university knowledge transfer: A critical review of the literature. Minerva 2009, 47(1), 93-114. Dewey, J. Experience and Nature, George Allen & Unwin, Ltd: London, UK, 1929. Wilson III, E. J. How to Make a Region Innovative. strategy+ business 2012, 66, available at: http://www.strategy-business.com/article/12103?pg=all Carayannis, E.G; Campbell, D.F.J. “Mode 3” and “Quadruple Helix”: toward a 21st century fractal innovation ecosystem. International Journal of Technology Management 2009, 46(3/4), 201-234. EU. Open Innovation 2.0, available at: http://ec.europa.eu/digital-agenda/en/open-innovation-20 Wilson, T.D. (Ed.). Theory in information behaviour research, Chapter 1-Activity theory, Eiconics Ltd: Sheffield, UK, 2013. Wilson, T. D. Models in information behaviour research. Journal of documentation 1999, 55(3), 249-270. Zacklad, M. Documents for action (Dofa): infrastructures for Distributed collective Practices. Actes du workshop “Distributed Collective Practice: Building new Directions for Infrastructural Studies CSCW” 2004, p. 6. Laszlo, K.C.; Laszlo, A. Fostering a sustainable learning society through knowledge-based development. Systems Research and Behavioral Science 2007, 24(5), 493-503. Nousala, S.; Miles, A.; Kilpatrick, B.; Hall, W.P. Building knowledge sharing communities using team expertise access maps (TEAM). Proceedings of the KMAP05 Knowledge Management in Asia Pacific 2005, p. 30. Zacklad, M. Communities of action: a cognitive and social approach to the design of CSCW systems. Proceedings of the 2003 international ACM SIGGROUP conference on supporting group work 2003, 190-197. Geyer, F. The challenge of Sociocybernetics. "Challenges to Sociological Knowledge", Session 04: "Challenges from Other Disciplines", 13th World Congress of Sociology, 1994, available at: http://www.critcrim.org/redfeather/chaos/006challenges.html Hevner, A.R.; March, S.T.; Park, J.; Ram, S. Design science in information systems research. MIS Quarterly 2004, 28(1), 75-105. March, S.T.; Smith, G.F. Design and natural science research on information technology. Decision support systems 1995, 15(4), 251-266. Järvinen, P. Action research is similar to design science. Quality & Quantity 2007, 41(1), 37-54. Hofkirchner, W. How to Achieve a Unified Theory of Information. TripleC: Communication, Capitalism & Critique. Open Access Journal for a Global Sustainable Information Society 2009, 7(2), 357-368.
1