GKGábor Kismihók

Gábor Kismihók

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Gábor Kismihók has a total of 206 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Predicting The Next Job and When to Change Jobs by Analyzing 300,000 Career Trajectories Using Hierarchical Bayesian Approach and Recurrent Neural Network

    by Vladimer Kobayashi, Stefan T. Mol, Gábor Kismihók, Evangelos Kanoulas

    Studies on physical job mobility have traditionally focused on examining underlying psychological and sociological factors influencing the decision to change jobs. Although, individual characteristics and attitudes play huge roles in job changes as possible antecedents, research have seldom investigated the actual job transitions people make as well as the timing of these transitions. The proliferation of resume data with job changes information would permit such investigation at a massive scale. In this study, we used novel analytical methods to study job transitions and solved two intimately interrelated problems. First is the prediction of whether a specific candidate is going to change job within a specified period. Second is to predict the most likely next job. Apart from the job transition, covariates such employment history, candidates’ educational attainment, among others were incorporated in the analysis. We found that it is possible to predict the timing and next job of candidates from job transitions alone. Also, the models we employed revealed the following: The likelihood that someone is going to change job within a period is an interplay of various factors including the type of industry someone belongs in, the number of previous jobs transitions, time in the labor market, and educational attainment. This study has direct contribution to recruitment and job recommendation since it does not only predict when a candidate is going to change job but also what transitions are enacted. Another contribution is its implication to job analysis because we demonstrated that job similarity can be deduced from the job transitions. Lastly, we managed to demonstrate that fields such as job mobility can be approached from a more data-driven perspective by applying modern analytical tool without disregarding theoretical considerations.

  • Open Access

    Designing Teacher-Centered Interfaces to Elicit Pedagogical Context for LLM-Based Content Generation

    by Abdolali Faraji, Mohammadreza Tavakoli, Mohammad Moein, Mohammadreza Molavi, Gábor Kismihók

    Large Language Models (LLMs) can help teachers generate and adapt educational materials, but most interactions still rely on free-form prompting, making instructional intent difficult to express and reuse. In this paper, we study how teacher-facing interfaces can elicit pedagogically meaningful contextual information and reduce ad hoc prompt engineering. We first conducted a requirement analysis with $$N=100$$ N = 100 teachers across 17 contextual fields. We measured importance and introduced fill deficit to identify “friction points” (i.e., information teachers consider important but are less likely to provide). Based on this analysis, we implemented a context-rich interface with targeted supports for important and friction-point fields. In a separate user study with a different sample of $$N=100$$ N = 100 teachers, the interface achieved high usability (SUS mean $$=80.33$$ = 80.33 ), low perceived workload, and increased willingness to provide contextual information, particularly for friction-point fields. For further validation, we conducted a comparative pilot with $$N=10$$ N = 10 experienced teachers; participants reported a greater tendency to use content generated with our context-rich interface (72.2%) than content generated with a baseline GPT interface (37.0%).

  • Open Access

    Personalized curricula through human-AI collaboration: Open learning platform development and validation from two experiments on knowledge acquisition

    by Abdolali Faraji, Mohammadreza Tavakoli, Mohammadreza Molavi, Stefan T. Mol, Gábor Kismihók

  • Cross-Dataset Bloom Question Classification: Supervised Models and Prompted LLMs

    by Abdolali Faraji, Mohammadreza Molavi, Zohreh Rasoulkhani, Mohammadreza Tavakoli, Gábor Kismihók

  • Open Access

    Data from the Researcher Mental Health Observatory STAIRCASE Survey

    by Jana Lasser, Stefan T. Mol, Alja Čontala, Ana Slavec, Andreja Zulim de Swarte, Anna Khachatryan, Anna Maria Eleuteri, Anupoma Haque, Baiba Jansone, Blerina Vrenozi, et al.

    The data presented here derives from the Sustainable Working Conditions in Academia survey (STAIRCASE) on researcher mental health. The survey addresses the ongoing mental health crisis in academia by providing comprehensive, multilevel data on researcher well-being and its structural determinants. We employed a cross-sectional between-participant study design to collect data from 4,296 researchers between September 15, 2023, and August 26, 2024. The sample, which primarily includes researchers based in European countries, has a mean age of 38.1 years (SD = 10.7) and consists of 63.7% female participants. Participants provided data on key mental health outcomes – including depression, anxiety, stress, burnout, and well-being – alongside detailed assessments of working conditions, leadership behavior, and organizational characteristics. The dataset facilitates a holistic, multilevel investigation of academic mental health beyond individual risk factors by including the individual, leadership, institutional, and national context. By enabling analyses across hierarchical levels this dataset provides the necessary evidence to identify systemic drivers of mental (ill) health and inform the development of effective, system-wide strategies for meaningful change in academic work environments.


  • Open Access

    Embedding-Based Rankings of Educational Resources based on Learning Outcome Alignment: Benchmarking, Expert Validation, and Learner Performance

    by Mohammadreza Molavi Hajiagha, Mohammad Moein, Mohammadreza Tavakoli, Abdolali Faraji, Gábor Kismihók, Stefan T. Mol

    As the online learning landscape evolves, the need for personalization is increasingly evident. Although educational resources are burgeoning, educators face challenges selecting materials that both align with intended learning outcomes and address diverse learner needs. Large Language Models (LLMs) are attracting growing interest for their potential to create learning resources that better support personalization, but verifying coverage of intended outcomes still requires human alignment review, which is costly and limits scalability. We propose a framework that supports the cost-effective automation of evaluating alignment between educational resources and intended learning outcomes. Using human-generated materials, we benchmarked LLM-based text-embedding models and found that the most accurate model (Voyage) achieved 79% accuracy in detecting alignment. We then applied the optimal model to LLM-generated resources and, via expert evaluation, confirmed that it reliably assessed correspondence to intended outcomes (83% accuracy). Finally, in a three-group experiment with 360 learners, higher alignment scores were positively related to greater learning performance, χ2(2, N = 360) = 15.39, p <.001. These findings show that embedding-based alignment scores can facilitate scalable personalization by confirming alignment with learning outcomes, which allows teachers to focus on tailoring content to diverse learner needs.

  • Open Access

    Embedding-Based Rankings of Educational Resources based on Learning Outcome Alignment: Benchmarking, Expert Validation, and Learner Performance

    by Mohammadreza Molavi, Mohammad Moein, Mohammadreza Tavakoli, Abdolali Faraji, Stefan T. Mol, Gábor Kismihók

    As the online learning landscape evolves, the need for personalization is increasingly evident. Although educational resources are burgeoning, educators face challenges selecting materials that both align with intended learning outcomes and address diverse learner needs. Large Language Models (LLMs) are attracting growing interest for their potential to create learning resources that better support personalization, but verifying coverage of intended outcomes still requires human alignment review, which is costly and limits scalability. We propose a framework that supports the cost-effective automation of evaluating alignment between educational resources and intended learning outcomes. Using human-generated materials, we benchmarked LLM-based text-embedding models and found that the most accurate model (Voyage) achieved 79% accuracy in detecting alignment. We then applied the optimal model to LLM-generated resources and, via expert evaluation, confirmed that it reliably assessed correspondence to intended outcomes (83% accuracy). Finally, in a three-group experiment with 360 learners, higher alignment scores were positively related to greater learning performance, chi-squared(2, N = 360) = 15.39, p < 0.001. These findings show that embedding-based alignment scores can facilitate scalable personalization by confirming alignment with learning outcomes, which allows teachers to focus on tailoring content to diverse learner needs.

  • LLM-Driven Personalized Answer Generation and Evaluation

    by Mohammadreza Molavi, Mohammadreza Tavakoli, Abdolali Faraji, Gábor Kismihók


  • Designing Effective LLM-Assisted Interfaces for Curriculum Development

    by Abdolali Faraji, Mohammadreza Tavakoli, Mohammad Moein, Mohammadreza Molavi, Gábor Kismihók


  • Open Access

    Designing Effective LLM-Assisted Interfaces for Curriculum Development

    by Abdolali Faraji, Mohammadreza Tavakoli, Mohammad Moein, Mohammadreza Molavi, Gábor Kismihók

    Large Language Models (LLMs) have the potential to transform the way a dynamic curriculum can be delivered. However, educators face significant challenges in interacting with these models, particularly due to complex prompt engineering and usability issues, which increase workload. Additionally, inaccuracies in LLM outputs can raise issues around output quality and ethical concerns in educational content delivery. Addressing these issues requires careful oversight, best achieved through cooperation between human and AI approaches. This paper introduces two novel User Interface (UI) designs, UI Predefined and UI Open, both grounded in Direct Manipulation (DM) principles to address these challenges. By reducing the reliance on intricate prompt engineering, these UIs improve usability, streamline interaction, and lower workload, providing a more effective pathway for educators to engage with LLMs. In a controlled user study with 20 participants, the proposed UIs were evaluated against the standard ChatGPT interface in terms of usability and cognitive load. Results showed that UI Predefined significantly outperformed both ChatGPT and UI Open, demonstrating superior usability and reduced task load, while UI Open offered more flexibility at the cost of a steeper learning curve. These findings underscore the importance of user-centered design in adopting AI-driven tools and lay the foundation for more intuitive and efficient educator-LLM interactions in online learning environments.