Research in the field of Bioinfromatics, Data Science, Recommender Systems, Natural Language Processing, Digital Humanities, AI Ethics and Governance. 

Currently engaged in:

• The 5-D Project (Decoding Death and Dying in people with Dementia by Digital thanotyping)

Previously worked on:

• Language modeling, tokenization, homonymy resolution
• Textual fact extraction
• Natural language generation
• Literature digitalization and analysis
• Bias and fairness issues in recommender systems
• Popularity bias mitigation strategies for recommender systems
• AI Ethics and Governance

Doctoral thesis (PhD)

• Anastasiia Klimashevskaia (2025). Beyond Popularity: Investigating and Mitigating Bias in Recommender Systems. (external link)

Academic article

• Anastasiia Klimashevskaia; Snorre Alvsvåg; Christoph Trattner et al. (2025). Evaluating Sequential Recommendations in the Wild: A Case Study on Offline Accuracy, Click Rates, and Consumption. (external link)
• Anastasiia Klimashevskaia (2024). Philosophical Perspectives on Recommender Systems: Ethical Implications, Biases, and Their Impact on Autonomy and Privacy. (external link)

Lecture

• Anastasiia Klimashevskaia (2024). News in AI age: Alignment with Editorial Values and Ethics. (external link)
• Anastasiia Klimashevskaia (2023). Recommender Systems: Benefits and Pitfalls of Personalization. (external link)
• Anastasiia Klimashevskaia (2023). Recommender Systems, Natural Language Processing and Digital Humanities. (external link)
• Anastasiia Klimashevskaia (2023). Recommender Systems Beyond Accuracy: Biases and Unfairness in Personalization. (external link)
• Anastasiia Klimashevskaia (2023). Undesired Effects and Popularity Bias In Recommendation. (external link)
• Anastasiia Klimashevskaia (2022). Mitigating Popularity Bias in Recommendation: Potential and Limits of Calibration Approaches. (external link)
• Anastasiia Klimashevskaia (2023). Recommender Systems: Benefits and Pitfalls of Personalization. (external link)
• Anastasiia Klimashevskaia (2023). Addressing Popularity Bias in Recommender Systems: An Exploration of Self-Supervised Learning Models. (external link)
• Anastasiia Klimashevskaia (2023). Recommender Systems Beyond Accuracy: Biases and Unfairness in Personalization. (external link)

Academic literature review

• Anastasiia Klimashevskaia; Dietmar Jannach; Mehdi Elahi et al. (2024). A survey on popularity bias in recommender systems. (external link)
• Anastasiia Klimashevskaia (2022). Popularity Bias as Ethical and Technical Issue in Recommendation: A Survey. (external link)

Conference poster

• Anastasiia Klimashevskaia (2023). Addressing Popularity Bias in Recommender Systems: An Exploration of Self-Supervised Learning Models. (external link)
• Anastasiia Klimashevskaia (2024). Philosophical Perspectives on Recommender Systems Ethical Implications, Biases, and Their Impact on Autonomy and Privacy. (external link)
• Anastasiia Klimashevskaia (2021). Exploring Recommender Systems: Towards Fair and Ethical Recommendation. (external link)

Book anthology

• Anastasiia Klimashevskaia; Mehdi Elahi; Christoph Trattner (2023). Addressing Popularity Bias in Recommender Systems: An Exploration of Self-Supervised Learning Models. (external link)

Conference lecture

• Anastasiia Klimashevskaia (2022). Popularity Bias as Ethical and Technical Issue in Recommendation: A Survey. (external link)

Academic book chapter

• Anastasiia Klimashevskaia; Mehdi Elahi; Dietmar Jannach et al. (2023). Evaluating The Effects of Calibrated Popularity Bias Mitigation: A Field Study. (external link)
• Anastasiia Klimashevskaia; Mehdi Elahi; Dietmar Jannach et al. (2022). Mitigating Popularity Bias in Recommendation: Potential and Limits of Calibration Approaches.. (external link)

See a complete overview of publications in NVA.

Current:

• The 5-D project (Decoding Death and Dying in people with Dementia by Digital thanotyping)

Previously:

• GIRAI: Global Index on Responsible AI (Participated in data collection representing Norway for the 2nd edition of the Index)
• Investigating Bias Mitigation Techniques for Fairness and Diversity in Recommender Systems - PhD Research at MediaFutures in collaboration with TV2 Norway