About Me
I’m an Assistant Professor at University of Novi Sad, Faculty of Philosophy. I completed my sociology PhD in 2019 and my main research interests are centered around applying statistical, computational and machine learning methods. In 2023, I was a Fulbright Visting Scholar at University of Virginia.
Currently I’m the maintainer of transforEmotion R package for sentiment analysis for text, image and video using transformer models (>5k installs on CRAN).
My Erdős number is 4 (A. Tomašević – M. Mitrović Danuklov – G. Caldarelli – B. Bollobás – P. Erdős).
You can find me on Mastodon.
Recent Research Articles
-
Decoding Emotion Dynamics in Videos using Dynamic Exploratory Graph Analysis and Zero-Shot Image Classification: A Simulation and Tutorial using the transforEmotion R package
BibTeX
@article{tomasevic_decoding_2024, title = {Decoding {Emotion} {Dynamics} in {Videos} using {Dynamic} {Exploratory} {Graph} {Analysis} and {Zero}-{Shot} {Image} {Classification}: {A} {Simulation} and {Tutorial} using the {transforEmotion} {R} package}, shorttitle = {Decoding {Emotion} {Dynamics} in {Videos} using {Dynamic} {Exploratory} {Graph} {Analysis} and {Zero}-{Shot} {Image} {Classification}}, url = {https://osf.io/hf3g7}, doi = {10.31234/osf.io/hf3g7}, abstract = {In this paper, we propose a novel approach for modeling and understanding the dynamics of emotion facial expression recognition (FER) scores. Recent advancements in deep learning and transformer-based neural network architectures enable the time series analysis of FER scores extracted from images and videos. This type of data can be important for psychological research of affective dynamics and emotion expression dynamics. However, the properties of such data are not well understood in the current literature. We propose a new method to simulate FER scores based on a modified version of the Damped Linear Oscillator with a measurement model (DLO-MM). We use this model to conduct a large-scale simulation and use dynamic Exploratory Graph Analysis to investigate the dimensionality of the data and use network scores to recover the values of the latent dimensions—positive and negative sentiment of the expressed emotions. Our results show that the DLO-MM model can be used to simulate FER scores for different patterns of emotion dynamics and that DynEGA can be used to uncover the latent structure of emotion dynamics expressed through FER scores. All methods presented in the paper are implemented in the transforEmotion R package and the tutorial section provides a step-by-step guide on how to simulate FER scores using DLO-MM and how to estimate FER scores from YouTube videos using transformer-based machine learning models.}, language = {en-us}, urldate = {2024-03-09}, author = {Tomašević, Aleksandar and Golino, Hudson and Christensen, Alexander P.}, month = jan, year = {2024}, note = {Publisher: OSF} }
-
The role of basic psychological needs in the relationships between identity orientations and adolescent mental health: A protocol for a longitudinal study
BibTeX
@article{Jovanovic2024-kk, title = “The role of basic psychological needs in the relationships between identity orientations and adolescent mental health: A protocol for a longitudinal study”, author = “Jovanovi{'c}, Veljko and Toma{\v s}evi{'c}, Aleksandar and {\v S}akan, Du{\v s}ana and Lazi{'c}, Milica and Gavrilov-Jerkovi{'c}, Vesna and Zotovi{'c}-Kosti{'c}, Marija and Obradovi{'c}, Vojana”, abstract = “Research into the role of identity orientations (the relative importance an individual places on different personal and social attributes and characteristics when defining her or his identity) in adolescent mental health is extremely limited. Furthermore, the potential mechanisms that might explain the associations between identity orientations and adolescent mental health are poorly understood. This study protocol describes a one-year longitudinal study across three time points to be initiated with the purpose of investigating the mediating role of basic psychological needs satisfaction and frustration in the relationship between identity orientations and various mental health indicators in adolescence. We aim to recruit a large sample of Serbian adolescents (N = 2,000 at Time 1), using a two-stage stratified random sampling. The data will be analyzed using the random intercept cross-lagged panel model (RI-CLPM), and the results will be contrasted with the traditional CLPM. The goal of this study is to make a theoretical contribution to research in the fields of identity, self-determination theory, and adolescent mental health, as well as to provide insights towards the development of evidence-based recommendations for creating prevention and promotion programs aimed at improving the well-being of adolescents.”, journal = “PloS one”, volume = 19, number = 1, pages = “e0296507”, month = jan, year = 2024, url = “http://dx.doi.org/10.1371/journal.pone.0296507", language = “en”, issn = “1932-6203”, pmid = “38166060”, doi = “10.1371/journal.pone.0296507”, pmc = “PMC10760749” }
-
The Face of Populism: Examining Differences in Facial Emotional Expressions of Political Leaders Using Machine Learning
BibTeX
@misc{major2023Face, title = {The {{Face}} of {{Populism}}: {{Examining Differences}} in {{Facial Emotional Expressions}} of {{Political Leaders Using Machine Learning}}}, shorttitle = {The {{Face}} of {{Populism}}}, author = {Major, Sara and Toma{\v s}evi{'c}, Aleksandar}, year = {2023}, number = {arXiv:2304.09914}, eprint = {2304.09914}, primaryclass = {physics}, publisher = {{arXiv}}, urldate = {2023-04-21}, archiveprefix = {arxiv}, copyright = {All rights reserved}, keywords = {Computer Science - Computer Vision and Pattern Recognition,Computer Science - Computers and Society,Computer Science - Machine Learning,Computer Science - Social and Information Networks,J.4,Physics - Physics and Society} }
-
Sustainability of Stack Exchange Q&A communities: the role of trust
BibTeX
@article{vranic2023Sustainability, title = {Sustainability of {{Stack Exchange Q}}&{{A}} Communities: The Role of Trust}, shorttitle = {Sustainability of {{Stack Exchange Q}}&{{A}} Communities}, author = {Vrani{'c}, Ana and Toma{\v s}evi{'c}, Aleksandar and Alori{'c}, Aleksandra and Mitrovi{'c} Dankulov, Marija}, year = {2023}, journal = {EPJ Data Science}, volume = {12}, number = {1}, pages = {1–24}, publisher = {{SpringerOpen}}, doi = {10.1140/epjds/s13688-023-00381-x}, abstract = {Knowledge-sharing communities are fundamental elements of a knowledge-based society. Understanding how different factors influence their sustainability is of crucial importance. We explore the role of the social network structure and social trust in their sustainability. We analyze the early evolution of social networks in four pairs of active and closed Stack Exchange communities on topics of physics, astronomy, economics, and literature and use a dynamical reputation model to quantify the evolution of social trust in them. In addition, we study the evolution of two active communities on mathematics topics and two closed communities about startups and compare them with our main results. Active communities have higher local cohesiveness and develop stable, better-connected, trustworthy cores. The early emergence of a stable and trustworthy core may be crucial for sustainable knowledge-sharing communities.}, copyright = {2023 The Author(s)} }
Current Research Interests
- Data Science
- Computational Social Science
- Network Science
- Network Psychometrics
Professional Activities
- 2021 - Network Science Society, member
- 2021 - Center for Sociological Research, University of Novi Sad, coordinator
- 2022 - Society for the Improvement of Psychological Science, member
- 2022 - Psychometric Society, member
Software
I’m a Linux 🐧 geek, so naturally I support FOSS in everything I do.
I enjoy coding in R, Python and Julia. I don’t enjoy JavaScript.
Whenever possible I prefer plain text (txt
, md
, tex
) to alternatives. I like to own my files and don’t depend on proprietary software to read them in 5, 10 years or more. I’m also a fan of single text file productivty, you can check out my VSCode extension Working Memory for more details.
Publications
Computational Social Science & Complex Networks
-
Major, S., & Tomašević, A. (2023). The Face of Populism: Examining Differences in Facial Emotional Expressions of Political Leaders Using Machine Learning (arXiv:2304.09914). arXiv. http://arxiv.org/abs/2304.09914
- GitHub repository: https://github.com/atomashevic/face-of-populism
-
Vranić, A., Tomašević, A., Alorić, A., & Mitrović Dankulov, M. (2023). Sustainability of Stack Exchange Q&A communities: The role of trust. EPJ Data Science, 12(1), Article 1. https://doi.org/10.1140/epjds/s13688-023-00381-x
- GitHub repository: https://github.com/ana-vranic/Stack-Exchange-communities
Network Psychometrics
-
Dinić, B. M., Sokolovska, V., & Tomašević, A. (2021). The narcissism network and centrality of narcissism features. Current Psychology. https://doi.org/10.1007/s12144-020-01250-w
-
Dinić, B. M., Wertag, A., Sokolovska, V., & Tomašević, A. (2021). The good, the bad, and the ugly: Revisiting the Dark Core. Current Psychology. https://doi.org/10.1007/s12144-021-01829-x
-
Dinić, B. M., Wertag, A., Tomašević, A., & Sokolovska, V. (2020). Centrality and redundancy of the Dark Tetrad traits. Personality and Individual Differences, 155, 109621. https://doi.org/10.1016/j.paid.2019.109621
-
Sokolovska, V., Dinić, B., & Tomašević, A. (2018). Aggressiveness in the HEXACO personality model. Psihologija, 51(4), 449–468. https://doi.org/10.2298/PSI170705022S
Belief Networks
- Tomašević, A. (2021). Measuring the influence of beliefs in belief networks. ArXiv:2110.09154 [Physics, Stat]. http://arxiv.org/abs/2110.09154
- GitHub repostiory: https://github.com/atomashevic/belief-influence
Other
-
Jovanović, V., Tomašević, A., Šakan, D., Lazić, M., Gavrilov-Jerković, V., Zotović-Kostić, M., & Obradović, V. (2024). The role of basic psychological needs in the relationships between identity orientations and adolescent mental health: A protocol for a longitudinal study. PloS One, 19(1), e0296507. https://doi.org/10.1371/journal.pone.0296507
-
Lukić, V., & Tomašević, A. (2020). Immigrant integration regimes in Europe: Incorporating the Western Balkan countries. Acta Geographica Slovenica, 60(1), 143-153-143–153. https://doi.org/10.3986/AGS.7286
Consultancy
Over the years I’ve consulted with a number of companies and organizations. Most of it is survey design, research and data analysis. Contact me if you’re interested in my services.
Past clients:
At the start of COVID-19 pandemic I was happy to volunteer for Data Versus Corona in attempt to use R
and Shiny
to visualize the pandemic.