The final frontier in text mining
The outer space industry is rapidly evolving into a trillion-dollar sector, driven by significant investments from major tech companies. This transformation marks the beginning of the so-called ‘New Space’ era, characterized by the emergence of profit-oriented activities such as asteroid mining, communications, and travel. At the same time, the outer space industry significantly contributes to environmental pollution, with many satellites ultimately becoming debris orbiting Earth. This project aims to investigate how major corporate players in the commercial space industry communicate about the sustainability of their activities and the actions they take in this regard.
We are looking for someone with excellent organizational skills and attention to detail who also has substantive experience with text mining and natural language processing, particularly when applied to the social sciences and humanities. The ideal candidate will be familiar with state-of-the-art text mining methodology in Python or R, particularly in the domains of law and sustainability, and will have a practical understanding of building text mining pipelines for potentially messy real-world data. Knowledge of statistical analysis and/or visualization also helps.
What are you going to do
You will help to obtain and analyse textual data from online sources, primarily the websites of companies in the commercial space sector from different countries. Analysis will focus on quantitative methods that yield domain-specific topic overviews over text collections, but may also include qualitative methods such as critical discourse analysis. You will work in an interdisciplinary team that includes experts in law, discourse studies and text mining.
- Finding primary sources (company websites) pertaining to the topic
- Scraping and preprocessing textual web data using automated tools
- Conducting text analysis focused on sustainability and climate-related topics, including broader topic overviews and comparisons across companies from different countries, using appropriate quantitative and qualitative methods
- Evaluation of the quality of the analysis and reliability of results on the basis of domain expertise of collaborators in the project
What do you have to offer
You have an interest in academic research and are familiar with text mining methodology. You have previous experience in building data processing pipelines in Python and/or R. Previous experience with web scraping is preferred. The ideal candidate enjoys working in an interdisciplinary team, and an affinity with social sciences and/or humanities topics makes you particularly suited to this project.
What do we have to offer
A temporary contract for 8 hours a week for 16 weeks in the period of January-April 2026.
You will work here
You will join the "Profit Above Us" project funded by the UvA Sustainability Platform (USP). This project is an interdisciplinary collaboration between Dr. Diliara Valeeva (Social and Behavioural Data Science Centre), Dr. Julia Muraszkiewicz (Expert in Space Law), Dr. Xiaojuan Tan (Amsterdam Center for Language and Communication) and Dr. Jelke Bloem (Natural Language Processing group, ILLC). The UvA Sustainability Platform is an interdisciplinary UvA-wide community for generating knowledge on sustainability within our planetary boundaries.
The project combines the political science expertise of Dr. Valeeva, legal expertise of Dr. Muraszkiewicz, critical discourse analysis expertise of Dr. Tan and text mining expertise of Dr. Bloem. In addition, other research assistants are involved in the project, and we host a student research project for the Cultural Data & AI masters programme.
The UvA Sustainability Platform's activities are located at the REC (Roeterseiland) campus, while the Natural Language Processing Group of the ILLC is located in Lab42 at the SP (Science Park) campus. Meetings may take place at either of these locations.
Are you a master’s student eager to gain experience with research at the intersection of Natural Language Processing, Critical Discourse Analysis and space law? We are seeking a research assistant (RA) to join a small team for a new pilot study funded by the UvA Sustainability Platform (USP) entitled, Profit Above Us: The sustainability implications of commercial space activities.
The final frontier in text mining
The outer space industry is rapidly evolving into a trillion-dollar sector, driven by significant investments from major tech companies. This transformation marks the beginning of the so-called ‘New Space’ era, characterized by the emergence of profit-oriented activities such as asteroid mining, communications, and travel. At the same time, the outer space industry significantly contributes to environmental pollution, with many satellites ultimately becoming debris orbiting Earth. This project aims to investigate how major corporate players in the commercial space industry communicate about the sustainability of their activities and the actions they take in this regard.
We are looking for someone with excellent organizational skills and attention to detail who also has substantive experience with text mining and natural language processing, particularly when applied to the social sciences and humanities. The ideal candidate will be familiar with state-of-the-art text mining methodology in Python or R, particularly in the domains of law and sustainability, and will have a practical understanding of building text mining pipelines for potentially messy real-world data. Knowledge of statistical analysis and/or visualization also helps.
What are you going to do
You will help to obtain and analyse textual data from online sources, primarily the websites of companies in the commercial space sector from different countries. Analysis will focus on quantitative methods that yield domain-specific topic overviews over text collections, but may also include qualitative methods such as critical discourse analysis. You will work in an interdisciplinary team that includes experts in law, discourse studies and text mining.
- Finding primary sources (company websites) pertaining to the topic
- Scraping and preprocessing textual web data using automated tools
- Conducting text analysis focused on sustainability and climate-related topics, including broader topic overviews and comparisons across companies from different countries, using appropriate quantitative and qualitative methods
- Evaluation of the quality of the analysis and reliability of results on the basis of domain expertise of collaborators in the project
What do you have to offer
You have an interest in academic research and are familiar with text mining methodology. You have previous experience in building data processing pipelines in Python and/or R. Previous experience with web scraping is preferred. The ideal candidate enjoys working in an interdisciplinary team, and an affinity with social sciences and/or humanities topics makes you particularly suited to this project.
What do we have to offer
A temporary contract for 8 hours a week for 16 weeks in the period of January-April 2026.
You will work here
You will join the "Profit Above Us" project funded by the UvA Sustainability Platform (USP). This project is an interdisciplinary collaboration between Dr. Diliara Valeeva (Social and Behavioural Data Science Centre), Dr. Julia Muraszkiewicz (Expert in Space Law), Dr. Xiaojuan Tan (Amsterdam Center for Language and Communication) and Dr. Jelke Bloem (Natural Language Processing group, ILLC). The UvA Sustainability Platform is an interdisciplinary UvA-wide community for generating knowledge on sustainability within our planetary boundaries.
The project combines the political science expertise of Dr. Valeeva, legal expertise of Dr. Muraszkiewicz, critical discourse analysis expertise of Dr. Tan and text mining expertise of Dr. Bloem. In addition, other research assistants are involved in the project, and we host a student research project for the Cultural Data & AI masters programme.
The UvA Sustainability Platform's activities are located at the REC (Roeterseiland) campus, while the Natural Language Processing Group of the ILLC is located in Lab42 at the SP (Science Park) campus. Meetings may take place at either of these locations.
Please fill in the questionnaire below, and apply via the red button no later than Dec 19, 2025.
Question form Student or Research Assistant
Answer the questions below to apply for the research assistant position.
1. Personal data
Name:
E-mail address:
Current degree programme:
University where you are currently enrolled:
Study plans for 2025-2026:
Have you ever worked as a research assistant at the UvA before? If so, was that under the “compensation other than wages”?
2. Motivation
Why do you want to participate in this research project? Why does it seem interesting or useful to you? What do you hope to learn from it? Are there aspects of the project that particularly interest you?
3. Relevant prior knowledge and experience
What relevant prior knowledge or experience have you gained in your studies, activism or volunteer work, paid work, or personal life? What courses have you taken that are relevant to this topic? This can be about the methodology (Natural Language Processing, text mining, corpus analysis), about the content (sustainability and space law) and about your network (relevant contacts, for example with companies in the commercial space industry). Be as precise and specific as possible.
4. Availability
a) How many hours per week would you be able and willing to spend on this project?
b) Are there periods in the period Jan 2026 – Apr 2026 when you are not or less available?
For questions about the vacancy, you can contact:
Jelke Bloem (j.bloem@uva.nl)
